Skip to content

Instantly share code, notes, and snippets.

@kdoodoo

kdoodoo/resnet fer plus.ipynb

Created December 14, 2020 09:02
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save kdoodoo/c0d916f8c58c4a9f27175a180112f547 to your computer and use it in GitHub Desktop.
Save kdoodoo/c0d916f8c58c4a9f27175a180112f547 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
resnet fer plus.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#CAT5000\n",
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"from tensorflow.keras import layers\n",
"from tensorflow.keras.layers import Dense, Flatten, Input,Conv2D, Activation,Dropout,MaxPooling2D, AveragePooling2D\n",
"from tensorflow.keras.models import Sequential, Model\n",
"from tensorflow.keras.callbacks import ModelCheckpoint\n",
"\n",
"from tensorflow.keras import datasets, layers, models,preprocessing\n",
"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
"\n",
"# from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
"\n",
"import matplotlib.pyplot as plt\n",
"\n",
" \n",
"from tensorflow.python.client import device_lib\n",
"\n",
"\n",
"from sklearn.utils import class_weight\n",
"# from sklearn.utils.class_weight import compute_class_weight, compute_sample_weight\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"\n",
"import numpy as np\n",
"import IPython.display as display\n",
"from PIL import Image\n",
"import matplotlib.pyplot as plt\n",
"import os\n",
"import pathlib\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"#ok\n",
"import numpy as np\n",
"import IPython.display as display\n",
"from PIL import Image\n",
"import matplotlib.pyplot as plt\n",
"import os\n",
"import pathlib"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"train_dir = pathlib.Path('./train_FER/')\n",
"test_dir = pathlib.Path('./test_FER/')\n",
"# classnames =['anger', 'contempt', 'disgust', 'fear', 'happiness', 'neutral', 'sadness', 'surprise']\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.utils.class_weight import compute_sample_weight,compute_class_weight\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"np.set_printoptions(linewidth=np.inf)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"image_generator = ImageDataGenerator(rescale=1./255,\n",
" shear_range=0.1,\n",
" zoom_range=0.05,\n",
" rotation_range=10,\n",
" horizontal_flip=True, \n",
"# vertical_flip=True,\n",
" \n",
" \n",
" \n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"image_generator_V = ImageDataGenerator(rescale=1./255,\n",
" \n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 28385 images belonging to 8 classes.\n"
]
}
],
"source": [
"train_images = image_generator.flow_from_directory(train_dir,\n",
" target_size=(48, 48),\n",
" batch_size=32,\n",
" class_mode = \"categorical\",\n",
" color_mode = 'grayscale',\n",
" shuffle=True,\n",
"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'anger': 0,\n",
" 'contempt': 1,\n",
" 'disgust': 2,\n",
" 'fear': 3,\n",
" 'happiness': 4,\n",
" 'neutral': 5,\n",
" 'sadness': 6,\n",
" 'surprise': 7}"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_images.class_indices"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"# X_train,Y_train = next(iter(train_images)) \n",
"\n",
"for X_train,Y_train in train_images:\n",
" break"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(32, 48, 48, 1)"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train.shape"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([0, 0, 0, ..., 7, 7, 7])"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_images.classes"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([0, 1, 2, 3, 4, 5, 6, 7])"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.unique(train_images.classes)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n",
"class_weights = class_weight.compute_class_weight(\n",
" 'balanced',\n",
" np.unique(train_images.classes), \n",
" train_images.classes)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 1.44057044, 21.11979167, 18.57657068, 5.41698473, 0.47144898, 0.34464546, 1.00513456, 0.99750492])"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_weights"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"# dict\n",
"from sklearn.utils import class_weight\n",
"class_weights = dict(zip(np.unique(train_images.classes), class_weight.compute_class_weight('balanced',\n",
" np.unique(train_images.classes),\n",
" train_images.classes))) "
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{0: 1.440570442549736,\n",
" 1: 21.119791666666668,\n",
" 2: 18.576570680628272,\n",
" 3: 5.416984732824427,\n",
" 4: 0.4714489768801488,\n",
" 5: 0.3446454589606605,\n",
" 6: 1.0051345609065157,\n",
" 7: 0.9975049198763003}"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_weights"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 3545 images belonging to 8 classes.\n"
]
}
],
"source": [
"test_images = image_generator_V.flow_from_directory(test_dir,\n",
" target_size=(48, 48),\n",
" batch_size=32,\n",
" class_mode = \"categorical\",\n",
" color_mode = 'grayscale',\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"# X_val,Y_val = next(iter(test_images)) \n",
"\n",
"for X_val,Y_val in test_images:\n",
" break"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"# batch_size = 32\n",
"# img_height = 48\n",
"# img_width = 48"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"# train_ds = tf.keras.preprocessing.image_dataset_from_directory(\n",
"# train_dir,\n",
"# # validation_split=0.2,\n",
"# # subset=\"training\",\n",
"# label_mode= 'categorical', \n",
"# color_mode='grayscale',\n",
"# seed=123,\n",
"# image_size=(img_height, img_width),\n",
"# batch_size=batch_size)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"# test_ds = tf.keras.preprocessing.image_dataset_from_directory(\n",
"# test_dir,\n",
"\n",
"# label_mode= 'categorical', \n",
"# color_mode='grayscale',\n",
"# seed=123,\n",
"# image_size=(img_height, img_width),\n",
"# batch_size=batch_size)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"# for train_x, train_y in train_ds:\n",
"# # print(\"train_x:\", train_x)\n",
"# # print(\"train_y:\", train_y)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"# train_x"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# # train_x, train_y = train_ds\n",
"# X_val,Y_val = next(iter(test_ds))"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"# train_y.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"# class_names = train_ds.class_names\n",
"# print(class_names)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"8"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# len(class_names)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"# len(train_y) \n"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"# train_image_generator = ImageDataGenerator(rescale=1./255,\n",
"# shear_range=0.1,\n",
"# zoom_range=0.05,\n",
"# rotation_range=10,\n",
"# horizontal_flip=False, \n",
"# vertical_flip=True)\n",
"# test_image_generator = ImageDataGenerator(rescale=1./255)\n"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# train_images = train_image_generator.flow_from_directory(train_dir,\n",
"# target_size=(48, 48),\n",
"# batch_size=128,\n",
"# # classes = list(CLASS_NAMES),\n",
"# shuffle=True)\n",
"# test_images = train_image_generator.flow_from_directory(test_dir,\n",
"# target_size=(48, 48),\n",
"# batch_size=128,\n",
"# # classes = list(CLASS_NAMES),\n",
"# shuffle=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
"# normalization_layer = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"# normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))\n",
"# image_batch, labels_batch = next(iter(normalized_ds))\n",
"# first_image = image_batch[0]\n",
"# # Notice the pixels values are now in `[0,1]`.\n",
"# print(np.min(first_image), np.max(first_image)) "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"# normalized_val = test_ds.map(lambda x, y: (normalization_layer(x), y))\n",
"\n",
"# X_val,Y_val = next(iter(normalized_val))"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"# first_image1 = X_val[0]\n",
"# print(np.min(first_image1), np.max(first_image1)) "
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"# train_y[1]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"# # class_wei#ghts = compute_class_weight('balanced', np.unique(labels_batch), labels_batch)\n",
"\n",
"# # sample_wts = compute_sample_weight('balanced', labels_batch)\n",
"\n",
"# # #training_log_loss = metrics.log_loss(y, training_probabilities, sample_weight= sample_wts)\n",
"# class_wts = np.array(class_weights, dtype=\"float\")"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"# class_wts"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"# AUTOTUNE = tf.data.experimental.AUTOTUNE\n",
"\n",
"# train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)\n",
"# test_ds = test_ds.cache().prefetch(buffer_size=AUTOTUNE)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"# model = tf.keras.applications.ResNet50( include_top=True, weights=None , input_tensor=None, input_shape=None,\n",
"# pooling=None, classes=10 )"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"# ['anger', 'contempt', 'disgust', 'fear', 'happiness', 'neutral', 'sadness', 'surprise']\n"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: \"resnet\"\n",
"__________________________________________________________________________________________________\n",
"Layer (type) Output Shape Param # Connected to \n",
"==================================================================================================\n",
"img (InputLayer) [(None, 48, 48, 1)] 0 \n",
"__________________________________________________________________________________________________\n",
"conv2d_37 (Conv2D) (None, 46, 46, 32) 320 img[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_38 (Conv2D) (None, 44, 44, 64) 18496 conv2d_37[0][0] \n",
"__________________________________________________________________________________________________\n",
"max_pooling2d_1 (MaxPooling2D) (None, 14, 14, 64) 0 conv2d_38[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_39 (Conv2D) (None, 14, 14, 64) 36928 max_pooling2d_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_40 (Conv2D) (None, 14, 14, 64) 36928 conv2d_39[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_17 (Add) (None, 14, 14, 64) 0 conv2d_40[0][0] \n",
" max_pooling2d_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_41 (Conv2D) (None, 14, 14, 64) 36928 add_17[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_42 (Conv2D) (None, 14, 14, 64) 36928 conv2d_41[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_18 (Add) (None, 14, 14, 64) 0 conv2d_42[0][0] \n",
" add_17[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_43 (Conv2D) (None, 14, 14, 64) 36928 add_18[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_44 (Conv2D) (None, 14, 14, 64) 36928 conv2d_43[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_19 (Add) (None, 14, 14, 64) 0 conv2d_44[0][0] \n",
" add_18[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_45 (Conv2D) (None, 14, 14, 64) 36928 add_19[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_46 (Conv2D) (None, 14, 14, 64) 36928 conv2d_45[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_20 (Add) (None, 14, 14, 64) 0 conv2d_46[0][0] \n",
" add_19[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_47 (Conv2D) (None, 14, 14, 64) 36928 add_20[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_48 (Conv2D) (None, 14, 14, 64) 36928 conv2d_47[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_21 (Add) (None, 14, 14, 64) 0 conv2d_48[0][0] \n",
" add_20[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_49 (Conv2D) (None, 14, 14, 64) 36928 add_21[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_50 (Conv2D) (None, 14, 14, 64) 36928 conv2d_49[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_22 (Add) (None, 14, 14, 64) 0 conv2d_50[0][0] \n",
" add_21[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_51 (Conv2D) (None, 14, 14, 64) 36928 add_22[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_52 (Conv2D) (None, 14, 14, 64) 36928 conv2d_51[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_23 (Add) (None, 14, 14, 64) 0 conv2d_52[0][0] \n",
" add_22[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_53 (Conv2D) (None, 14, 14, 64) 36928 add_23[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_54 (Conv2D) (None, 14, 14, 64) 36928 conv2d_53[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_24 (Add) (None, 14, 14, 64) 0 conv2d_54[0][0] \n",
" add_23[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_55 (Conv2D) (None, 14, 14, 64) 36928 add_24[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_56 (Conv2D) (None, 14, 14, 64) 36928 conv2d_55[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_25 (Add) (None, 14, 14, 64) 0 conv2d_56[0][0] \n",
" add_24[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_57 (Conv2D) (None, 14, 14, 64) 36928 add_25[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_58 (Conv2D) (None, 14, 14, 64) 36928 conv2d_57[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_26 (Add) (None, 14, 14, 64) 0 conv2d_58[0][0] \n",
" add_25[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_59 (Conv2D) (None, 14, 14, 64) 36928 add_26[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_60 (Conv2D) (None, 14, 14, 64) 36928 conv2d_59[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_27 (Add) (None, 14, 14, 64) 0 conv2d_60[0][0] \n",
" add_26[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_61 (Conv2D) (None, 14, 14, 64) 36928 add_27[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_62 (Conv2D) (None, 14, 14, 64) 36928 conv2d_61[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_28 (Add) (None, 14, 14, 64) 0 conv2d_62[0][0] \n",
" add_27[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_63 (Conv2D) (None, 14, 14, 64) 36928 add_28[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_64 (Conv2D) (None, 14, 14, 64) 36928 conv2d_63[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_29 (Add) (None, 14, 14, 64) 0 conv2d_64[0][0] \n",
" add_28[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_65 (Conv2D) (None, 14, 14, 64) 36928 add_29[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_66 (Conv2D) (None, 14, 14, 64) 36928 conv2d_65[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_30 (Add) (None, 14, 14, 64) 0 conv2d_66[0][0] \n",
" add_29[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_67 (Conv2D) (None, 14, 14, 64) 36928 add_30[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_68 (Conv2D) (None, 14, 14, 64) 36928 conv2d_67[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_31 (Add) (None, 14, 14, 64) 0 conv2d_68[0][0] \n",
" add_30[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_69 (Conv2D) (None, 14, 14, 64) 36928 add_31[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_70 (Conv2D) (None, 14, 14, 64) 36928 conv2d_69[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_32 (Add) (None, 14, 14, 64) 0 conv2d_70[0][0] \n",
" add_31[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_71 (Conv2D) (None, 14, 14, 64) 36928 add_32[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_72 (Conv2D) (None, 14, 14, 64) 36928 conv2d_71[0][0] \n",
"__________________________________________________________________________________________________\n",
"add_33 (Add) (None, 14, 14, 64) 0 conv2d_72[0][0] \n",
" add_32[0][0] \n",
"__________________________________________________________________________________________________\n",
"conv2d_73 (Conv2D) (None, 12, 12, 64) 36928 add_33[0][0] \n",
"__________________________________________________________________________________________________\n",
"global_average_pooling2d_1 (Glo (None, 64) 0 conv2d_73[0][0] \n",
"__________________________________________________________________________________________________\n",
"dense_2 (Dense) (None, 256) 16640 global_average_pooling2d_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"dropout_1 (Dropout) (None, 256) 0 dense_2[0][0] \n",
"__________________________________________________________________________________________________\n",
"dense_3 (Dense) (None, 8) 2056 dropout_1[0][0] \n",
"==================================================================================================\n",
"Total params: 1,329,992\n",
"Trainable params: 1,329,992\n",
"Non-trainable params: 0\n",
"__________________________________________________________________________________________________\n"
]
}
],
"source": [
"inputs = keras.Input(shape=(48, 48, 1), name=\"img\")\n",
"x = layers.Conv2D(32, 3, activation=\"relu\")(inputs)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\")(x)\n",
"block_1_output = layers.MaxPooling2D(3)(x)\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_1_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_2_output = layers.add([x, block_1_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_2_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_3_output = layers.add([x, block_2_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_3_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_4_output = layers.add([x, block_3_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_4_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_5_output = layers.add([x, block_4_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_5_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_6_output = layers.add([x, block_5_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_6_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_7_output = layers.add([x, block_6_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_7_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_8_output = layers.add([x, block_7_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_8_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_9_output = layers.add([x, block_8_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_9_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_10_output = layers.add([x, block_9_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_10_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_11_output = layers.add([x, block_10_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_11_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_12_output = layers.add([x, block_11_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_12_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_13_output = layers.add([x, block_12_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_13_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_14_output = layers.add([x, block_13_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_14_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_15_output = layers.add([x, block_14_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_15_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_16_output = layers.add([x, block_15_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_16_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_17_output = layers.add([x, block_16_output])\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(block_17_output)\n",
"x = layers.Conv2D(64, 3, activation=\"relu\", padding=\"same\")(x)\n",
"block_18_output = layers.add([x, block_17_output])\n",
"\n",
"\n",
"\n",
"x = layers.Conv2D(64, 3, activation=\"relu\")(block_18_output)\n",
"x = layers.GlobalAveragePooling2D()(x)\n",
"x = layers.Dense(256, activation=\"relu\")(x)\n",
"x = layers.Dropout(0.5)(x)\n",
"# outputs = layers.Dense(8, activation=\"softmax\")(x)\n",
"outputs = layers.Dense(8)(x)\n",
"\n",
"\n",
"model = keras.Model(inputs, outputs, name=\"resnet\")\n",
"model.summary()\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"model.compile(\n",
" optimizer = tf.keras.optimizers.SGD(learning_rate=0.0001, momentum=0.2, nesterov=True),\n",
"# optimizer=keras.optimizers.RMSprop(1e-4),\n",
" loss=keras.losses.CategoricalCrossentropy (from_logits=True),\n",
"# loss= tf.nn.softmax_cross_entropy_with_logits,\n",
"\n",
"# sample_weight_mode=\"temporal\",\n",
"\n",
" metrics=['accuracy'])"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{0: 1.440570442549736,\n",
" 1: 21.119791666666668,\n",
" 2: 18.576570680628272,\n",
" 3: 5.416984732824427,\n",
" 4: 0.4714489768801488,\n",
" 5: 0.3446454589606605,\n",
" 6: 1.0051345609065157,\n",
" 7: 0.9975049198763003}"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_weights"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"import datetime\n",
"log_dir = \"./logs/\" + datetime.datetime.now().strftime(\"n\"+\"%Y%m%d-%H%M%S\")\n",
"tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"\n",
"# python -m tensorboard.main --logdir foo:\"C:\\Users\\Administrator\\Desktop\\Winter\\FERPlus-master\\FERPlus-master_NEW\\logs\" --port=8000\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.9161 - accuracy: 0.4688 - val_loss: 2.8774 - val_accuracy: 0.1875\n",
"Epoch 2/5000\n",
"1/1 [==============================] - 0s 146ms/step - loss: 0.9226 - accuracy: 0.3438 - val_loss: 2.9362 - val_accuracy: 0.1875\n",
"Epoch 3/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8172 - accuracy: 0.4375 - val_loss: 2.9261 - val_accuracy: 0.1875\n",
"Epoch 4/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7953 - accuracy: 0.5938 - val_loss: 2.8649 - val_accuracy: 0.2188\n",
"Epoch 5/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7990 - accuracy: 0.4375 - val_loss: 2.8283 - val_accuracy: 0.1875\n",
"Epoch 6/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8063 - accuracy: 0.5312 - val_loss: 2.9679 - val_accuracy: 0.2188\n",
"Epoch 7/5000\n",
"1/1 [==============================] - 0s 232ms/step - loss: 0.9128 - accuracy: 0.5000 - val_loss: 2.7525 - val_accuracy: 0.2188\n",
"Epoch 8/5000\n",
"1/1 [==============================] - 0s 225ms/step - loss: 0.7690 - accuracy: 0.4688 - val_loss: 2.9480 - val_accuracy: 0.2188\n",
"Epoch 9/5000\n",
"1/1 [==============================] - 0s 247ms/step - loss: 0.7793 - accuracy: 0.5312 - val_loss: 2.8349 - val_accuracy: 0.1875\n",
"Epoch 10/5000\n",
"1/1 [==============================] - 0s 230ms/step - loss: 0.9130 - accuracy: 0.3125 - val_loss: 2.8922 - val_accuracy: 0.1875\n",
"Epoch 11/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.8866 - accuracy: 0.4375 - val_loss: 2.9487 - val_accuracy: 0.1875\n",
"Epoch 12/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.8055 - accuracy: 0.5625 - val_loss: 2.9507 - val_accuracy: 0.1875\n",
"Epoch 13/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7656 - accuracy: 0.5000 - val_loss: 2.9514 - val_accuracy: 0.1875\n",
"Epoch 14/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8771 - accuracy: 0.4688 - val_loss: 2.8523 - val_accuracy: 0.1875\n",
"Epoch 15/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7849 - accuracy: 0.5938 - val_loss: 2.9211 - val_accuracy: 0.2188\n",
"Epoch 16/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8525 - accuracy: 0.4062 - val_loss: 2.8651 - val_accuracy: 0.1875\n",
"Epoch 17/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.0014 - accuracy: 0.2188 - val_loss: 2.9964 - val_accuracy: 0.1875\n",
"Epoch 18/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6951 - accuracy: 0.5625 - val_loss: 2.8912 - val_accuracy: 0.1875\n",
"Epoch 19/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7896 - accuracy: 0.5938 - val_loss: 2.9775 - val_accuracy: 0.1875\n",
"Epoch 20/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7115 - accuracy: 0.5625 - val_loss: 2.9056 - val_accuracy: 0.1875\n",
"Epoch 21/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.8771 - accuracy: 0.4688 - val_loss: 3.1357 - val_accuracy: 0.1562\n",
"Epoch 22/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.9017 - accuracy: 0.4375 - val_loss: 2.9707 - val_accuracy: 0.1875\n",
"Epoch 23/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.9736 - accuracy: 0.4062 - val_loss: 3.1846 - val_accuracy: 0.1875\n",
"Epoch 24/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8178 - accuracy: 0.4062 - val_loss: 2.9332 - val_accuracy: 0.1875\n",
"Epoch 25/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7609 - accuracy: 0.5000 - val_loss: 3.0867 - val_accuracy: 0.1875\n",
"Epoch 26/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.8391 - accuracy: 0.6250 - val_loss: 2.9758 - val_accuracy: 0.1875\n",
"Epoch 27/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8642 - accuracy: 0.5000 - val_loss: 2.9331 - val_accuracy: 0.1875\n",
"Epoch 28/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8920 - accuracy: 0.4688 - val_loss: 3.0746 - val_accuracy: 0.2188\n",
"Epoch 29/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.9470 - accuracy: 0.4688 - val_loss: 2.9772 - val_accuracy: 0.2188\n",
"Epoch 30/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8218 - accuracy: 0.5000 - val_loss: 3.0404 - val_accuracy: 0.1875\n",
"Epoch 31/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.9240 - accuracy: 0.3438 - val_loss: 2.9937 - val_accuracy: 0.1875\n",
"Epoch 32/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8709 - accuracy: 0.4375 - val_loss: 2.9956 - val_accuracy: 0.1875\n",
"Epoch 33/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.9375 - accuracy: 0.3125 - val_loss: 2.9892 - val_accuracy: 0.1875\n",
"Epoch 34/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8235 - accuracy: 0.5312 - val_loss: 3.0058 - val_accuracy: 0.1875\n",
"Epoch 35/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.8040 - accuracy: 0.5312 - val_loss: 3.1039 - val_accuracy: 0.1875\n",
"Epoch 36/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.9581 - accuracy: 0.4688 - val_loss: 3.0517 - val_accuracy: 0.1875\n",
"Epoch 37/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.9074 - accuracy: 0.4375 - val_loss: 3.0705 - val_accuracy: 0.1875\n",
"Epoch 38/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.8152 - accuracy: 0.3750 - val_loss: 2.9925 - val_accuracy: 0.1875\n",
"Epoch 39/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7095 - accuracy: 0.5312 - val_loss: 3.0653 - val_accuracy: 0.1875\n",
"Epoch 40/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8571 - accuracy: 0.5312 - val_loss: 2.9441 - val_accuracy: 0.1875\n",
"Epoch 41/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9335 - accuracy: 0.4062 - val_loss: 3.0686 - val_accuracy: 0.1875\n",
"Epoch 42/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8236 - accuracy: 0.5312 - val_loss: 2.9715 - val_accuracy: 0.1875\n",
"Epoch 43/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8142 - accuracy: 0.5625 - val_loss: 3.0746 - val_accuracy: 0.1875\n",
"Epoch 44/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.7998 - accuracy: 0.5312 - val_loss: 2.9658 - val_accuracy: 0.1875\n",
"Epoch 45/5000\n",
"1/1 [==============================] - 0s 229ms/step - loss: 0.7893 - accuracy: 0.5312 - val_loss: 3.0033 - val_accuracy: 0.1562\n",
"Epoch 46/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.7737 - accuracy: 0.5625 - val_loss: 3.0614 - val_accuracy: 0.1875\n",
"Epoch 47/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8285 - accuracy: 0.4688 - val_loss: 3.0084 - val_accuracy: 0.1875\n",
"Epoch 48/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7498 - accuracy: 0.4688 - val_loss: 3.0071 - val_accuracy: 0.1875\n",
"Epoch 49/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7996 - accuracy: 0.5625 - val_loss: 3.0956 - val_accuracy: 0.1562\n",
"Epoch 50/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8071 - accuracy: 0.5000 - val_loss: 2.9423 - val_accuracy: 0.1875\n",
"Epoch 51/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7908 - accuracy: 0.5000 - val_loss: 3.1534 - val_accuracy: 0.1875\n",
"Epoch 52/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.9042 - accuracy: 0.4375 - val_loss: 2.9651 - val_accuracy: 0.1875\n",
"Epoch 53/5000\n",
"1/1 [==============================] - 0s 212ms/step - loss: 0.8799 - accuracy: 0.3750 - val_loss: 3.0837 - val_accuracy: 0.1562\n",
"Epoch 54/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.8764 - accuracy: 0.5000 - val_loss: 3.1520 - val_accuracy: 0.1562\n",
"Epoch 55/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7770 - accuracy: 0.4688 - val_loss: 3.0178 - val_accuracy: 0.1875\n",
"Epoch 56/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7219 - accuracy: 0.5938 - val_loss: 2.9837 - val_accuracy: 0.1875\n",
"Epoch 57/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.8615 - accuracy: 0.4688 - val_loss: 3.1517 - val_accuracy: 0.1562\n",
"Epoch 58/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.9000 - accuracy: 0.3438 - val_loss: 2.9491 - val_accuracy: 0.1875\n",
"Epoch 59/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.8834 - accuracy: 0.5312 - val_loss: 3.1878 - val_accuracy: 0.1562\n",
"Epoch 60/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.8189 - accuracy: 0.4688 - val_loss: 2.9732 - val_accuracy: 0.1875\n",
"Epoch 61/5000\n",
"1/1 [==============================] - 0s 233ms/step - loss: 0.7938 - accuracy: 0.5938 - val_loss: 3.2153 - val_accuracy: 0.1562\n",
"Epoch 62/5000\n",
"1/1 [==============================] - 0s 228ms/step - loss: 0.8007 - accuracy: 0.5000 - val_loss: 2.9712 - val_accuracy: 0.1875\n",
"Epoch 63/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.8145 - accuracy: 0.5000 - val_loss: 3.1723 - val_accuracy: 0.1562\n",
"Epoch 64/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.9624 - accuracy: 0.3750 - val_loss: 2.9923 - val_accuracy: 0.1875\n",
"Epoch 65/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8199 - accuracy: 0.5938 - val_loss: 3.0419 - val_accuracy: 0.1562\n",
"Epoch 66/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8835 - accuracy: 0.5000 - val_loss: 3.0110 - val_accuracy: 0.1875\n",
"Epoch 67/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8388 - accuracy: 0.5000 - val_loss: 3.0886 - val_accuracy: 0.1562\n",
"Epoch 68/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.9197 - accuracy: 0.2500 - val_loss: 3.0972 - val_accuracy: 0.1562\n",
"Epoch 69/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7683 - accuracy: 0.4688 - val_loss: 3.0290 - val_accuracy: 0.1562\n",
"Epoch 70/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6709 - accuracy: 0.5000 - val_loss: 3.1577 - val_accuracy: 0.1562\n",
"Epoch 71/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8593 - accuracy: 0.4062 - val_loss: 2.9715 - val_accuracy: 0.1562\n",
"Epoch 72/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9170 - accuracy: 0.4062 - val_loss: 2.9882 - val_accuracy: 0.1562\n",
"Epoch 73/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.9133 - accuracy: 0.4062 - val_loss: 3.0371 - val_accuracy: 0.1562\n",
"Epoch 74/5000\n",
"1/1 [==============================] - 0s 221ms/step - loss: 0.8794 - accuracy: 0.4688 - val_loss: 3.0522 - val_accuracy: 0.1562\n",
"Epoch 75/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.8733 - accuracy: 0.4688 - val_loss: 3.0111 - val_accuracy: 0.1562\n",
"Epoch 76/5000\n",
"1/1 [==============================] - 0s 223ms/step - loss: 0.9904 - accuracy: 0.4688 - val_loss: 3.2228 - val_accuracy: 0.1875\n",
"Epoch 77/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8448 - accuracy: 0.5000 - val_loss: 2.9417 - val_accuracy: 0.1875\n",
"Epoch 78/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 0.7816 - accuracy: 0.5312 - val_loss: 3.1121 - val_accuracy: 0.1562\n",
"Epoch 79/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.8427 - accuracy: 0.4062 - val_loss: 3.0185 - val_accuracy: 0.1875\n",
"Epoch 80/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8814 - accuracy: 0.4062 - val_loss: 3.0004 - val_accuracy: 0.1875\n",
"Epoch 81/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7384 - accuracy: 0.5000 - val_loss: 3.0175 - val_accuracy: 0.1875\n",
"Epoch 82/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8501 - accuracy: 0.4375 - val_loss: 3.1474 - val_accuracy: 0.1562\n",
"Epoch 83/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8205 - accuracy: 0.5625 - val_loss: 3.0124 - val_accuracy: 0.1875\n",
"Epoch 84/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.7714 - accuracy: 0.5625 - val_loss: 3.0230 - val_accuracy: 0.1875\n",
"Epoch 85/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8344 - accuracy: 0.3750 - val_loss: 3.1112 - val_accuracy: 0.1875\n",
"Epoch 86/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.8518 - accuracy: 0.4375 - val_loss: 3.0100 - val_accuracy: 0.1875\n",
"Epoch 87/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.9060 - accuracy: 0.4688 - val_loss: 3.0261 - val_accuracy: 0.1875\n",
"Epoch 88/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.8267 - accuracy: 0.4688 - val_loss: 2.9431 - val_accuracy: 0.1875\n",
"Epoch 89/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7526 - accuracy: 0.5312 - val_loss: 3.0763 - val_accuracy: 0.1875\n",
"Epoch 90/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7500 - accuracy: 0.5625 - val_loss: 2.9595 - val_accuracy: 0.1875\n",
"Epoch 91/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7334 - accuracy: 0.5938 - val_loss: 3.0659 - val_accuracy: 0.1875\n",
"Epoch 92/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8003 - accuracy: 0.5000 - val_loss: 3.0075 - val_accuracy: 0.1875\n",
"Epoch 93/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8760 - accuracy: 0.4688 - val_loss: 3.1394 - val_accuracy: 0.1562\n",
"Epoch 94/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7311 - accuracy: 0.4688 - val_loss: 3.0091 - val_accuracy: 0.1875\n",
"Epoch 95/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.7452 - accuracy: 0.5938 - val_loss: 3.1394 - val_accuracy: 0.1875\n",
"Epoch 96/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9321 - accuracy: 0.2812 - val_loss: 3.0200 - val_accuracy: 0.1875\n",
"Epoch 97/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7969 - accuracy: 0.4688 - val_loss: 3.0344 - val_accuracy: 0.1875\n",
"Epoch 98/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7943 - accuracy: 0.5312 - val_loss: 3.0767 - val_accuracy: 0.1562\n",
"Epoch 99/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8524 - accuracy: 0.4688 - val_loss: 3.0654 - val_accuracy: 0.1562\n",
"Epoch 100/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.8055 - accuracy: 0.5312 - val_loss: 3.1921 - val_accuracy: 0.1562\n",
"Epoch 101/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.8222 - accuracy: 0.4688 - val_loss: 2.9818 - val_accuracy: 0.1875\n",
"Epoch 102/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.9581 - accuracy: 0.2812 - val_loss: 3.3507 - val_accuracy: 0.1562\n",
"Epoch 103/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8817 - accuracy: 0.5000 - val_loss: 2.9569 - val_accuracy: 0.1875\n",
"Epoch 104/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7711 - accuracy: 0.5000 - val_loss: 3.0470 - val_accuracy: 0.1562\n",
"Epoch 105/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8146 - accuracy: 0.4688 - val_loss: 2.9983 - val_accuracy: 0.1562\n",
"Epoch 106/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.8949 - accuracy: 0.4375 - val_loss: 3.3989 - val_accuracy: 0.1875\n",
"Epoch 107/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.8580 - accuracy: 0.4375 - val_loss: 2.9552 - val_accuracy: 0.1875\n",
"Epoch 108/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7614 - accuracy: 0.5625 - val_loss: 3.1345 - val_accuracy: 0.1562\n",
"Epoch 109/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7184 - accuracy: 0.5000 - val_loss: 3.0734 - val_accuracy: 0.1562\n",
"Epoch 110/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.8120 - accuracy: 0.4375 - val_loss: 3.1628 - val_accuracy: 0.1562\n",
"Epoch 111/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8950 - accuracy: 0.4375 - val_loss: 3.0322 - val_accuracy: 0.1562\n",
"Epoch 112/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7722 - accuracy: 0.5312 - val_loss: 3.1108 - val_accuracy: 0.1562\n",
"Epoch 113/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7435 - accuracy: 0.5000 - val_loss: 3.2050 - val_accuracy: 0.1875\n",
"Epoch 114/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7617 - accuracy: 0.5625 - val_loss: 2.9977 - val_accuracy: 0.1562\n",
"Epoch 115/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7491 - accuracy: 0.4375 - val_loss: 3.0952 - val_accuracy: 0.1562\n",
"Epoch 116/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7565 - accuracy: 0.5625 - val_loss: 3.0454 - val_accuracy: 0.1562\n",
"Epoch 117/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9514 - accuracy: 0.5000 - val_loss: 3.1430 - val_accuracy: 0.1562\n",
"Epoch 118/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7749 - accuracy: 0.4688 - val_loss: 3.0301 - val_accuracy: 0.1562\n",
"Epoch 119/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.0338 - accuracy: 0.5000 - val_loss: 3.0850 - val_accuracy: 0.1562\n",
"Epoch 120/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6898 - accuracy: 0.6250 - val_loss: 3.0540 - val_accuracy: 0.1562\n",
"Epoch 121/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8061 - accuracy: 0.5000 - val_loss: 3.1894 - val_accuracy: 0.1562\n",
"Epoch 122/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8426 - accuracy: 0.4688 - val_loss: 3.0425 - val_accuracy: 0.1875\n",
"Epoch 123/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8565 - accuracy: 0.4062 - val_loss: 3.1758 - val_accuracy: 0.1875\n",
"Epoch 124/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7467 - accuracy: 0.5625 - val_loss: 3.0349 - val_accuracy: 0.1562\n",
"Epoch 125/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8292 - accuracy: 0.4688 - val_loss: 3.1305 - val_accuracy: 0.1562\n",
"Epoch 126/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8749 - accuracy: 0.4062 - val_loss: 3.1086 - val_accuracy: 0.1875\n",
"Epoch 127/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7822 - accuracy: 0.6250 - val_loss: 3.0549 - val_accuracy: 0.1875\n",
"Epoch 128/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7889 - accuracy: 0.4375 - val_loss: 3.0075 - val_accuracy: 0.1875\n",
"Epoch 129/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8175 - accuracy: 0.4688 - val_loss: 3.0833 - val_accuracy: 0.1875\n",
"Epoch 130/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7070 - accuracy: 0.4688 - val_loss: 3.0511 - val_accuracy: 0.1875\n",
"Epoch 131/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6991 - accuracy: 0.5625 - val_loss: 3.0927 - val_accuracy: 0.1875\n",
"Epoch 132/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7904 - accuracy: 0.5312 - val_loss: 3.0857 - val_accuracy: 0.1875\n",
"Epoch 133/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9637 - accuracy: 0.2500 - val_loss: 3.1217 - val_accuracy: 0.1875\n",
"Epoch 134/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.8908 - accuracy: 0.4375 - val_loss: 3.2077 - val_accuracy: 0.1875\n",
"Epoch 135/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8428 - accuracy: 0.3125 - val_loss: 3.0378 - val_accuracy: 0.1875\n",
"Epoch 136/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7127 - accuracy: 0.5625 - val_loss: 3.1159 - val_accuracy: 0.1562\n",
"Epoch 137/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8592 - accuracy: 0.5000 - val_loss: 3.0625 - val_accuracy: 0.1875\n",
"Epoch 138/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6971 - accuracy: 0.5938 - val_loss: 3.1388 - val_accuracy: 0.1562\n",
"Epoch 139/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9732 - accuracy: 0.4062 - val_loss: 3.1193 - val_accuracy: 0.1875\n",
"Epoch 140/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7100 - accuracy: 0.5000 - val_loss: 3.1474 - val_accuracy: 0.1875\n",
"Epoch 141/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6639 - accuracy: 0.5938 - val_loss: 3.1480 - val_accuracy: 0.1875\n",
"Epoch 142/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7993 - accuracy: 0.5312 - val_loss: 3.1098 - val_accuracy: 0.1875\n",
"Epoch 143/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7437 - accuracy: 0.5938 - val_loss: 3.0799 - val_accuracy: 0.1875\n",
"Epoch 144/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7345 - accuracy: 0.5312 - val_loss: 3.2424 - val_accuracy: 0.1875\n",
"Epoch 145/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8268 - accuracy: 0.4375 - val_loss: 3.0187 - val_accuracy: 0.1875\n",
"Epoch 146/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7662 - accuracy: 0.4688 - val_loss: 3.1917 - val_accuracy: 0.1562\n",
"Epoch 147/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7933 - accuracy: 0.5625 - val_loss: 3.1778 - val_accuracy: 0.1875\n",
"Epoch 148/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.8119 - accuracy: 0.5000 - val_loss: 3.0617 - val_accuracy: 0.1875\n",
"Epoch 149/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.8830 - accuracy: 0.5000 - val_loss: 3.3439 - val_accuracy: 0.1562\n",
"Epoch 150/5000\n",
"1/1 [==============================] - 0s 223ms/step - loss: 0.8746 - accuracy: 0.3438 - val_loss: 2.9865 - val_accuracy: 0.1562\n",
"Epoch 151/5000\n",
"1/1 [==============================] - 0s 216ms/step - loss: 0.8585 - accuracy: 0.5000 - val_loss: 3.0703 - val_accuracy: 0.1562\n",
"Epoch 152/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8412 - accuracy: 0.4062 - val_loss: 3.0781 - val_accuracy: 0.1562\n",
"Epoch 153/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8042 - accuracy: 0.5000 - val_loss: 3.1262 - val_accuracy: 0.1562\n",
"Epoch 154/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7199 - accuracy: 0.5625 - val_loss: 3.0748 - val_accuracy: 0.1562\n",
"Epoch 155/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7649 - accuracy: 0.5625 - val_loss: 3.1121 - val_accuracy: 0.1562\n",
"Epoch 156/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8618 - accuracy: 0.5000 - val_loss: 3.2416 - val_accuracy: 0.1875\n",
"Epoch 157/5000\n",
"1/1 [==============================] - 0s 205ms/step - loss: 0.8720 - accuracy: 0.4688 - val_loss: 3.0845 - val_accuracy: 0.1562\n",
"Epoch 158/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8192 - accuracy: 0.4062 - val_loss: 3.0793 - val_accuracy: 0.1562\n",
"Epoch 159/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7339 - accuracy: 0.5625 - val_loss: 3.1594 - val_accuracy: 0.1562\n",
"Epoch 160/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7612 - accuracy: 0.5312 - val_loss: 3.1299 - val_accuracy: 0.1562\n",
"Epoch 161/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8208 - accuracy: 0.3750 - val_loss: 3.2135 - val_accuracy: 0.1562\n",
"Epoch 162/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8391 - accuracy: 0.5938 - val_loss: 3.0147 - val_accuracy: 0.1562\n",
"Epoch 163/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7309 - accuracy: 0.5625 - val_loss: 3.1984 - val_accuracy: 0.1562\n",
"Epoch 164/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8646 - accuracy: 0.3750 - val_loss: 3.0047 - val_accuracy: 0.1562\n",
"Epoch 165/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6845 - accuracy: 0.5312 - val_loss: 3.1597 - val_accuracy: 0.1562\n",
"Epoch 166/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9167 - accuracy: 0.4062 - val_loss: 3.2302 - val_accuracy: 0.1562\n",
"Epoch 167/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.8144 - accuracy: 0.4062 - val_loss: 2.9789 - val_accuracy: 0.1562\n",
"Epoch 168/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7722 - accuracy: 0.5000 - val_loss: 3.2627 - val_accuracy: 0.1562\n",
"Epoch 169/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7748 - accuracy: 0.4375 - val_loss: 3.0710 - val_accuracy: 0.1562\n",
"Epoch 170/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7934 - accuracy: 0.4062 - val_loss: 3.2477 - val_accuracy: 0.1562\n",
"Epoch 171/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8154 - accuracy: 0.4375 - val_loss: 3.1105 - val_accuracy: 0.1562\n",
"Epoch 172/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7685 - accuracy: 0.5312 - val_loss: 3.0858 - val_accuracy: 0.1562\n",
"Epoch 173/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8341 - accuracy: 0.5000 - val_loss: 3.1035 - val_accuracy: 0.1562\n",
"Epoch 174/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7139 - accuracy: 0.5938 - val_loss: 3.1358 - val_accuracy: 0.1562\n",
"Epoch 175/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7352 - accuracy: 0.6250 - val_loss: 3.0986 - val_accuracy: 0.1562\n",
"Epoch 176/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7944 - accuracy: 0.4688 - val_loss: 3.0788 - val_accuracy: 0.1562\n",
"Epoch 177/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9080 - accuracy: 0.3438 - val_loss: 3.2023 - val_accuracy: 0.1562\n",
"Epoch 178/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8076 - accuracy: 0.4688 - val_loss: 3.0856 - val_accuracy: 0.1562\n",
"Epoch 179/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7706 - accuracy: 0.5000 - val_loss: 3.1091 - val_accuracy: 0.1562\n",
"Epoch 180/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7839 - accuracy: 0.6250 - val_loss: 3.1132 - val_accuracy: 0.1562\n",
"Epoch 181/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8844 - accuracy: 0.5625 - val_loss: 3.2584 - val_accuracy: 0.1562\n",
"Epoch 182/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8577 - accuracy: 0.4375 - val_loss: 3.0094 - val_accuracy: 0.1562\n",
"Epoch 183/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8220 - accuracy: 0.5312 - val_loss: 3.1804 - val_accuracy: 0.1562\n",
"Epoch 184/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8562 - accuracy: 0.5625 - val_loss: 3.0799 - val_accuracy: 0.1562\n",
"Epoch 185/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6695 - accuracy: 0.5625 - val_loss: 3.2203 - val_accuracy: 0.1562\n",
"Epoch 186/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8168 - accuracy: 0.4688 - val_loss: 2.9760 - val_accuracy: 0.1875\n",
"Epoch 187/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9009 - accuracy: 0.4062 - val_loss: 3.3421 - val_accuracy: 0.1562\n",
"Epoch 188/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.7031 - accuracy: 0.5938 - val_loss: 3.0746 - val_accuracy: 0.1562\n",
"Epoch 189/5000\n",
"1/1 [==============================] - 0s 205ms/step - loss: 0.7136 - accuracy: 0.5938 - val_loss: 3.1852 - val_accuracy: 0.1562\n",
"Epoch 190/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6745 - accuracy: 0.6250 - val_loss: 3.0976 - val_accuracy: 0.1562\n",
"Epoch 191/5000\n",
"1/1 [==============================] - 0s 203ms/step - loss: 0.6392 - accuracy: 0.5625 - val_loss: 3.1637 - val_accuracy: 0.1562\n",
"Epoch 192/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7933 - accuracy: 0.4062 - val_loss: 3.1438 - val_accuracy: 0.1562\n",
"Epoch 193/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8203 - accuracy: 0.4688 - val_loss: 3.2819 - val_accuracy: 0.1562\n",
"Epoch 194/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7185 - accuracy: 0.5625 - val_loss: 3.1773 - val_accuracy: 0.1562\n",
"Epoch 195/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6901 - accuracy: 0.5625 - val_loss: 3.0760 - val_accuracy: 0.1875\n",
"Epoch 196/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8590 - accuracy: 0.4688 - val_loss: 3.4434 - val_accuracy: 0.1562\n",
"Epoch 197/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7412 - accuracy: 0.5312 - val_loss: 2.9155 - val_accuracy: 0.1875\n",
"Epoch 198/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.9653 - accuracy: 0.4375 - val_loss: 3.3292 - val_accuracy: 0.1562\n",
"Epoch 199/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8154 - accuracy: 0.4375 - val_loss: 2.9607 - val_accuracy: 0.1875\n",
"Epoch 200/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9271 - accuracy: 0.3125 - val_loss: 3.3596 - val_accuracy: 0.1562\n",
"Epoch 201/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7898 - accuracy: 0.4688 - val_loss: 3.0587 - val_accuracy: 0.1562\n",
"Epoch 202/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8418 - accuracy: 0.5312 - val_loss: 3.3914 - val_accuracy: 0.1250\n",
"Epoch 203/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7232 - accuracy: 0.4688 - val_loss: 3.0658 - val_accuracy: 0.1875\n",
"Epoch 204/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9864 - accuracy: 0.4062 - val_loss: 3.7570 - val_accuracy: 0.1562\n",
"Epoch 205/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 1.0076 - accuracy: 0.2500 - val_loss: 2.8697 - val_accuracy: 0.1562\n",
"Epoch 206/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.9361 - accuracy: 0.4375 - val_loss: 3.5856 - val_accuracy: 0.1250\n",
"Epoch 207/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9452 - accuracy: 0.2812 - val_loss: 2.8267 - val_accuracy: 0.1250\n",
"Epoch 208/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.0514 - accuracy: 0.4375 - val_loss: 3.9112 - val_accuracy: 0.1250\n",
"Epoch 209/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 1.1325 - accuracy: 0.2812 - val_loss: 2.8232 - val_accuracy: 0.1562\n",
"Epoch 210/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.5120 - accuracy: 0.3125 - val_loss: 6.7763 - val_accuracy: 0.0312\n",
"Epoch 211/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 6.5696 - accuracy: 0.0938 - val_loss: 2.2146 - val_accuracy: 0.2188\n",
"Epoch 212/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 7.6359 - accuracy: 0.2188 - val_loss: 4.9682 - val_accuracy: 0.0312\n",
"Epoch 213/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 3.6489 - accuracy: 0.0938 - val_loss: 2.9310 - val_accuracy: 0.1250\n",
"Epoch 214/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.2102 - accuracy: 0.3750 - val_loss: 2.6677 - val_accuracy: 0.1562\n",
"Epoch 215/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9193 - accuracy: 0.4688 - val_loss: 2.7588 - val_accuracy: 0.1562\n",
"Epoch 216/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9719 - accuracy: 0.4688 - val_loss: 2.7088 - val_accuracy: 0.1250\n",
"Epoch 217/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9991 - accuracy: 0.4375 - val_loss: 2.8168 - val_accuracy: 0.1250\n",
"Epoch 218/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8197 - accuracy: 0.5625 - val_loss: 2.7378 - val_accuracy: 0.1250\n",
"Epoch 219/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8754 - accuracy: 0.5000 - val_loss: 2.7498 - val_accuracy: 0.1250\n",
"Epoch 220/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8881 - accuracy: 0.4375 - val_loss: 2.7437 - val_accuracy: 0.1562\n",
"Epoch 221/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8572 - accuracy: 0.5938 - val_loss: 2.7277 - val_accuracy: 0.1562\n",
"Epoch 222/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9340 - accuracy: 0.3750 - val_loss: 2.7713 - val_accuracy: 0.1562\n",
"Epoch 223/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8391 - accuracy: 0.3750 - val_loss: 2.7882 - val_accuracy: 0.1562\n",
"Epoch 224/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9204 - accuracy: 0.4688 - val_loss: 2.7340 - val_accuracy: 0.1562\n",
"Epoch 225/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8915 - accuracy: 0.4688 - val_loss: 2.7711 - val_accuracy: 0.1562\n",
"Epoch 226/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8291 - accuracy: 0.6562 - val_loss: 2.7158 - val_accuracy: 0.1562\n",
"Epoch 227/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9773 - accuracy: 0.5625 - val_loss: 2.7738 - val_accuracy: 0.1562\n",
"Epoch 228/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8741 - accuracy: 0.5938 - val_loss: 2.7073 - val_accuracy: 0.1562\n",
"Epoch 229/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7529 - accuracy: 0.5000 - val_loss: 2.7343 - val_accuracy: 0.1875\n",
"Epoch 230/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8536 - accuracy: 0.5312 - val_loss: 2.8518 - val_accuracy: 0.1562\n",
"Epoch 231/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8572 - accuracy: 0.4062 - val_loss: 2.7837 - val_accuracy: 0.1562\n",
"Epoch 232/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8053 - accuracy: 0.5000 - val_loss: 2.7620 - val_accuracy: 0.1875\n",
"Epoch 233/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.0272 - accuracy: 0.4688 - val_loss: 2.9047 - val_accuracy: 0.1875\n",
"Epoch 234/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8332 - accuracy: 0.5000 - val_loss: 2.7903 - val_accuracy: 0.1875\n",
"Epoch 235/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8818 - accuracy: 0.4688 - val_loss: 2.9873 - val_accuracy: 0.1875\n",
"Epoch 236/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8467 - accuracy: 0.4688 - val_loss: 2.8188 - val_accuracy: 0.1875\n",
"Epoch 237/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8136 - accuracy: 0.5312 - val_loss: 3.0291 - val_accuracy: 0.1875\n",
"Epoch 238/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8497 - accuracy: 0.5625 - val_loss: 2.7530 - val_accuracy: 0.2188\n",
"Epoch 239/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9268 - accuracy: 0.3438 - val_loss: 2.9811 - val_accuracy: 0.1562\n",
"Epoch 240/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.9133 - accuracy: 0.4688 - val_loss: 2.9128 - val_accuracy: 0.1875\n",
"Epoch 241/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8685 - accuracy: 0.4062 - val_loss: 2.8936 - val_accuracy: 0.1875\n",
"Epoch 242/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8557 - accuracy: 0.5000 - val_loss: 2.8656 - val_accuracy: 0.1875\n",
"Epoch 243/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7351 - accuracy: 0.6875 - val_loss: 2.9237 - val_accuracy: 0.2188\n",
"Epoch 244/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8530 - accuracy: 0.5000 - val_loss: 2.9135 - val_accuracy: 0.1875\n",
"Epoch 245/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9440 - accuracy: 0.4688 - val_loss: 2.9821 - val_accuracy: 0.1875\n",
"Epoch 246/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7477 - accuracy: 0.5938 - val_loss: 2.9493 - val_accuracy: 0.1875\n",
"Epoch 247/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8739 - accuracy: 0.4375 - val_loss: 2.9101 - val_accuracy: 0.1875\n",
"Epoch 248/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8581 - accuracy: 0.4688 - val_loss: 2.7897 - val_accuracy: 0.1875\n",
"Epoch 249/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7839 - accuracy: 0.4688 - val_loss: 2.8681 - val_accuracy: 0.1875\n",
"Epoch 250/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8638 - accuracy: 0.5625 - val_loss: 2.9067 - val_accuracy: 0.1562\n",
"Epoch 251/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7953 - accuracy: 0.5938 - val_loss: 2.8702 - val_accuracy: 0.1875\n",
"Epoch 252/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7670 - accuracy: 0.3750 - val_loss: 2.9269 - val_accuracy: 0.1562\n",
"Epoch 253/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7912 - accuracy: 0.4688 - val_loss: 2.9440 - val_accuracy: 0.1562\n",
"Epoch 254/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8828 - accuracy: 0.3125 - val_loss: 2.9966 - val_accuracy: 0.1562\n",
"Epoch 255/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8246 - accuracy: 0.4062 - val_loss: 2.9228 - val_accuracy: 0.1875\n",
"Epoch 256/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9633 - accuracy: 0.4062 - val_loss: 3.0639 - val_accuracy: 0.1875\n",
"Epoch 257/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8218 - accuracy: 0.5000 - val_loss: 2.9195 - val_accuracy: 0.1875\n",
"Epoch 258/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9123 - accuracy: 0.6250 - val_loss: 3.1964 - val_accuracy: 0.1562\n",
"Epoch 259/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8028 - accuracy: 0.5312 - val_loss: 2.9945 - val_accuracy: 0.1875\n",
"Epoch 260/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8144 - accuracy: 0.5625 - val_loss: 3.0649 - val_accuracy: 0.1875\n",
"Epoch 261/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8348 - accuracy: 0.5312 - val_loss: 3.0297 - val_accuracy: 0.1875\n",
"Epoch 262/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8090 - accuracy: 0.5312 - val_loss: 2.9702 - val_accuracy: 0.1875\n",
"Epoch 263/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8542 - accuracy: 0.5312 - val_loss: 2.9837 - val_accuracy: 0.1875\n",
"Epoch 264/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8117 - accuracy: 0.4688 - val_loss: 3.1089 - val_accuracy: 0.1562\n",
"Epoch 265/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8506 - accuracy: 0.5000 - val_loss: 2.9570 - val_accuracy: 0.1875\n",
"Epoch 266/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8459 - accuracy: 0.5312 - val_loss: 3.0291 - val_accuracy: 0.1562\n",
"Epoch 267/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8564 - accuracy: 0.4688 - val_loss: 3.0925 - val_accuracy: 0.1562\n",
"Epoch 268/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9743 - accuracy: 0.4375 - val_loss: 3.2323 - val_accuracy: 0.2188\n",
"Epoch 269/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8080 - accuracy: 0.5625 - val_loss: 3.0975 - val_accuracy: 0.2188\n",
"Epoch 270/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8530 - accuracy: 0.4062 - val_loss: 2.9949 - val_accuracy: 0.1875\n",
"Epoch 271/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7129 - accuracy: 0.5938 - val_loss: 3.0865 - val_accuracy: 0.2188\n",
"Epoch 272/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7631 - accuracy: 0.4375 - val_loss: 3.0217 - val_accuracy: 0.1875\n",
"Epoch 273/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8141 - accuracy: 0.5000 - val_loss: 3.0433 - val_accuracy: 0.1875\n",
"Epoch 274/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8089 - accuracy: 0.4688 - val_loss: 3.0616 - val_accuracy: 0.1875\n",
"Epoch 275/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7835 - accuracy: 0.3438 - val_loss: 3.1714 - val_accuracy: 0.1875\n",
"Epoch 276/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8160 - accuracy: 0.5625 - val_loss: 2.9817 - val_accuracy: 0.2188\n",
"Epoch 277/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9217 - accuracy: 0.4062 - val_loss: 3.2808 - val_accuracy: 0.2188\n",
"Epoch 278/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8463 - accuracy: 0.4375 - val_loss: 2.9499 - val_accuracy: 0.1875\n",
"Epoch 279/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7630 - accuracy: 0.5000 - val_loss: 3.0554 - val_accuracy: 0.1875\n",
"Epoch 280/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7482 - accuracy: 0.5312 - val_loss: 3.0280 - val_accuracy: 0.1875\n",
"Epoch 281/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8581 - accuracy: 0.4062 - val_loss: 3.0792 - val_accuracy: 0.1875\n",
"Epoch 282/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8355 - accuracy: 0.3750 - val_loss: 3.0739 - val_accuracy: 0.1562\n",
"Epoch 283/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8106 - accuracy: 0.5312 - val_loss: 3.1046 - val_accuracy: 0.1875\n",
"Epoch 284/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7149 - accuracy: 0.5312 - val_loss: 3.0673 - val_accuracy: 0.1875\n",
"Epoch 285/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8031 - accuracy: 0.4375 - val_loss: 3.1181 - val_accuracy: 0.1875\n",
"Epoch 286/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8632 - accuracy: 0.4688 - val_loss: 3.0281 - val_accuracy: 0.1562\n",
"Epoch 287/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8084 - accuracy: 0.5312 - val_loss: 3.0647 - val_accuracy: 0.1562\n",
"Epoch 288/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.8207 - accuracy: 0.3438 - val_loss: 3.1292 - val_accuracy: 0.1562\n",
"Epoch 289/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6892 - accuracy: 0.4688 - val_loss: 2.9782 - val_accuracy: 0.1875\n",
"Epoch 290/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8365 - accuracy: 0.5000 - val_loss: 3.0314 - val_accuracy: 0.1562\n",
"Epoch 291/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7832 - accuracy: 0.6250 - val_loss: 2.9869 - val_accuracy: 0.1875\n",
"Epoch 292/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7762 - accuracy: 0.5000 - val_loss: 3.2305 - val_accuracy: 0.1875\n",
"Epoch 293/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7014 - accuracy: 0.6250 - val_loss: 3.0343 - val_accuracy: 0.1875\n",
"Epoch 294/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8334 - accuracy: 0.5000 - val_loss: 3.3007 - val_accuracy: 0.1562\n",
"Epoch 295/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8149 - accuracy: 0.4375 - val_loss: 2.9557 - val_accuracy: 0.1875\n",
"Epoch 296/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8644 - accuracy: 0.4062 - val_loss: 3.2105 - val_accuracy: 0.1875\n",
"Epoch 297/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7960 - accuracy: 0.4688 - val_loss: 3.0304 - val_accuracy: 0.1562\n",
"Epoch 298/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7491 - accuracy: 0.5625 - val_loss: 3.0650 - val_accuracy: 0.1875\n",
"Epoch 299/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8257 - accuracy: 0.4375 - val_loss: 3.0224 - val_accuracy: 0.1562\n",
"Epoch 300/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8271 - accuracy: 0.4688 - val_loss: 3.2148 - val_accuracy: 0.1562\n",
"Epoch 301/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7796 - accuracy: 0.5312 - val_loss: 3.0337 - val_accuracy: 0.1562\n",
"Epoch 302/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7836 - accuracy: 0.5625 - val_loss: 3.2011 - val_accuracy: 0.1875\n",
"Epoch 303/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7248 - accuracy: 0.5625 - val_loss: 2.9793 - val_accuracy: 0.1875\n",
"Epoch 304/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7469 - accuracy: 0.5312 - val_loss: 3.1418 - val_accuracy: 0.1875\n",
"Epoch 305/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6949 - accuracy: 0.5938 - val_loss: 3.0655 - val_accuracy: 0.1875\n",
"Epoch 306/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8157 - accuracy: 0.5312 - val_loss: 3.1809 - val_accuracy: 0.1875\n",
"Epoch 307/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7371 - accuracy: 0.4688 - val_loss: 3.1554 - val_accuracy: 0.1875\n",
"Epoch 308/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6743 - accuracy: 0.6562 - val_loss: 3.0665 - val_accuracy: 0.1875\n",
"Epoch 309/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7665 - accuracy: 0.5625 - val_loss: 3.2245 - val_accuracy: 0.2188\n",
"Epoch 310/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7363 - accuracy: 0.4688 - val_loss: 3.0619 - val_accuracy: 0.1875\n",
"Epoch 311/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7241 - accuracy: 0.5312 - val_loss: 3.1041 - val_accuracy: 0.2188\n",
"Epoch 312/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7185 - accuracy: 0.5000 - val_loss: 3.1858 - val_accuracy: 0.1875\n",
"Epoch 313/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7090 - accuracy: 0.6250 - val_loss: 3.1158 - val_accuracy: 0.1875\n",
"Epoch 314/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7941 - accuracy: 0.5000 - val_loss: 3.4144 - val_accuracy: 0.1562\n",
"Epoch 315/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6463 - accuracy: 0.4062 - val_loss: 3.1167 - val_accuracy: 0.1875\n",
"Epoch 316/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7435 - accuracy: 0.6250 - val_loss: 3.0333 - val_accuracy: 0.2188\n",
"Epoch 317/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8105 - accuracy: 0.4688 - val_loss: 3.0751 - val_accuracy: 0.1875\n",
"Epoch 318/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8479 - accuracy: 0.5938 - val_loss: 3.2475 - val_accuracy: 0.1562\n",
"Epoch 319/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7759 - accuracy: 0.5312 - val_loss: 3.1472 - val_accuracy: 0.1875\n",
"Epoch 320/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8652 - accuracy: 0.4375 - val_loss: 3.0675 - val_accuracy: 0.1875\n",
"Epoch 321/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7126 - accuracy: 0.5000 - val_loss: 3.0934 - val_accuracy: 0.1875\n",
"Epoch 322/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8079 - accuracy: 0.5625 - val_loss: 3.0974 - val_accuracy: 0.1875\n",
"Epoch 323/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.7580 - accuracy: 0.5000 - val_loss: 3.0501 - val_accuracy: 0.1875\n",
"Epoch 324/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7319 - accuracy: 0.5000 - val_loss: 3.1099 - val_accuracy: 0.1875\n",
"Epoch 325/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6849 - accuracy: 0.5000 - val_loss: 3.1542 - val_accuracy: 0.1875\n",
"Epoch 326/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7424 - accuracy: 0.6250 - val_loss: 3.1215 - val_accuracy: 0.1875\n",
"Epoch 327/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6976 - accuracy: 0.4375 - val_loss: 3.3003 - val_accuracy: 0.1875\n",
"Epoch 328/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.9323 - accuracy: 0.3750 - val_loss: 3.1219 - val_accuracy: 0.1875\n",
"Epoch 329/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6796 - accuracy: 0.5625 - val_loss: 3.1639 - val_accuracy: 0.1875\n",
"Epoch 330/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7805 - accuracy: 0.5625 - val_loss: 3.1685 - val_accuracy: 0.1875\n",
"Epoch 331/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7832 - accuracy: 0.5938 - val_loss: 3.0209 - val_accuracy: 0.1875\n",
"Epoch 332/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7674 - accuracy: 0.4375 - val_loss: 3.1684 - val_accuracy: 0.2188\n",
"Epoch 333/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.8237 - accuracy: 0.5312 - val_loss: 3.1292 - val_accuracy: 0.1875\n",
"Epoch 334/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.7838 - accuracy: 0.4375 - val_loss: 3.1535 - val_accuracy: 0.1875\n",
"Epoch 335/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8661 - accuracy: 0.3125 - val_loss: 3.2428 - val_accuracy: 0.2188\n",
"Epoch 336/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7647 - accuracy: 0.5625 - val_loss: 3.0784 - val_accuracy: 0.1875\n",
"Epoch 337/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8966 - accuracy: 0.5000 - val_loss: 3.3253 - val_accuracy: 0.2188\n",
"Epoch 338/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.7431 - accuracy: 0.46 - 0s 172ms/step - loss: 0.7431 - accuracy: 0.4688 - val_loss: 3.0353 - val_accuracy: 0.1875\n",
"Epoch 339/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.9180 - accuracy: 0.4062 - val_loss: 3.3733 - val_accuracy: 0.1875\n",
"Epoch 340/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8311 - accuracy: 0.4688 - val_loss: 3.0865 - val_accuracy: 0.1875\n",
"Epoch 341/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8697 - accuracy: 0.4062 - val_loss: 3.2207 - val_accuracy: 0.2188\n",
"Epoch 342/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.8016 - accuracy: 0.4375 - val_loss: 3.0909 - val_accuracy: 0.1875\n",
"Epoch 343/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.7604 - accuracy: 0.5312 - val_loss: 3.1327 - val_accuracy: 0.1875\n",
"Epoch 344/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8701 - accuracy: 0.4688 - val_loss: 3.1932 - val_accuracy: 0.1875\n",
"Epoch 345/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.7204 - accuracy: 0.5000 - val_loss: 3.1430 - val_accuracy: 0.1875\n",
"Epoch 346/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7402 - accuracy: 0.5938 - val_loss: 3.0923 - val_accuracy: 0.1875\n",
"Epoch 347/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7797 - accuracy: 0.5312 - val_loss: 3.2909 - val_accuracy: 0.2188\n",
"Epoch 348/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8383 - accuracy: 0.5000 - val_loss: 3.0906 - val_accuracy: 0.1875\n",
"Epoch 349/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8690 - accuracy: 0.4062 - val_loss: 3.2112 - val_accuracy: 0.1875\n",
"Epoch 350/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.8434 - accuracy: 0.4062 - val_loss: 3.0351 - val_accuracy: 0.1875\n",
"Epoch 351/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7654 - accuracy: 0.5625 - val_loss: 3.2271 - val_accuracy: 0.1562\n",
"Epoch 352/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8003 - accuracy: 0.5312 - val_loss: 3.0843 - val_accuracy: 0.1875\n",
"Epoch 353/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9093 - accuracy: 0.4062 - val_loss: 3.2012 - val_accuracy: 0.1562\n",
"Epoch 354/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8071 - accuracy: 0.4688 - val_loss: 3.0406 - val_accuracy: 0.1875\n",
"Epoch 355/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.8749 - accuracy: 0.3438 - val_loss: 3.2075 - val_accuracy: 0.1875\n",
"Epoch 356/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7635 - accuracy: 0.5625 - val_loss: 3.0170 - val_accuracy: 0.1875\n",
"Epoch 357/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9295 - accuracy: 0.5000 - val_loss: 3.6057 - val_accuracy: 0.1875\n",
"Epoch 358/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.9764 - accuracy: 0.3125 - val_loss: 3.0101 - val_accuracy: 0.1875\n",
"Epoch 359/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8229 - accuracy: 0.4062 - val_loss: 3.4131 - val_accuracy: 0.1875\n",
"Epoch 360/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.8217 - accuracy: 0.4375 - val_loss: 3.0165 - val_accuracy: 0.1875\n",
"Epoch 361/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.8028 - accuracy: 0.6250 - val_loss: 3.2003 - val_accuracy: 0.1875\n",
"Epoch 362/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7205 - accuracy: 0.5625 - val_loss: 3.2177 - val_accuracy: 0.1562\n",
"Epoch 363/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7848 - accuracy: 0.4688 - val_loss: 3.0874 - val_accuracy: 0.1875\n",
"Epoch 364/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8553 - accuracy: 0.4062 - val_loss: 3.4357 - val_accuracy: 0.1562\n",
"Epoch 365/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8384 - accuracy: 0.5000 - val_loss: 3.0249 - val_accuracy: 0.1875\n",
"Epoch 366/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7580 - accuracy: 0.4688 - val_loss: 3.2081 - val_accuracy: 0.1875\n",
"Epoch 367/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7612 - accuracy: 0.5312 - val_loss: 3.0463 - val_accuracy: 0.1875\n",
"Epoch 368/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9496 - accuracy: 0.4688 - val_loss: 3.3829 - val_accuracy: 0.1562\n",
"Epoch 369/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.1026 - accuracy: 0.5312 - val_loss: 3.8591 - val_accuracy: 0.1250\n",
"Epoch 370/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 3.0467 - accuracy: 0.2188 - val_loss: 12.7798 - val_accuracy: 0.0312\n",
"Epoch 371/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 13.2907 - accuracy: 0.0312 - val_loss: 3.9751 - val_accuracy: 0.0312\n",
"Epoch 372/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 3.2554 - accuracy: 0.0938 - val_loss: 3.1836 - val_accuracy: 0.0312\n",
"Epoch 373/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.7976 - accuracy: 0.0312 - val_loss: 3.1224 - val_accuracy: 0.0312\n",
"Epoch 374/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 3.1635 - accuracy: 0.1250 - val_loss: 2.9970 - val_accuracy: 0.0312\n",
"Epoch 375/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.6443 - accuracy: 0.2188 - val_loss: 2.7542 - val_accuracy: 0.0938\n",
"Epoch 376/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.6456 - accuracy: 0.2188 - val_loss: 2.6852 - val_accuracy: 0.0625\n",
"Epoch 377/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.2898 - accuracy: 0.1562 - val_loss: 2.5133 - val_accuracy: 0.1875\n",
"Epoch 378/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.1791 - accuracy: 0.3438 - val_loss: 2.4064 - val_accuracy: 0.1875\n",
"Epoch 379/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.5301 - accuracy: 0.3438 - val_loss: 2.4779 - val_accuracy: 0.1250\n",
"Epoch 380/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.1330 - accuracy: 0.3125 - val_loss: 2.4160 - val_accuracy: 0.1562\n",
"Epoch 381/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.0245 - accuracy: 0.4688 - val_loss: 2.3596 - val_accuracy: 0.2188\n",
"Epoch 382/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.1686 - accuracy: 0.4688 - val_loss: 2.4929 - val_accuracy: 0.1562\n",
"Epoch 383/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.0379 - accuracy: 0.4062 - val_loss: 2.4331 - val_accuracy: 0.1875\n",
"Epoch 384/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.0902 - accuracy: 0.4688 - val_loss: 2.4884 - val_accuracy: 0.2188\n",
"Epoch 385/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.9604 - accuracy: 0.3125 - val_loss: 2.4833 - val_accuracy: 0.1875\n",
"Epoch 386/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.0534 - accuracy: 0.4062 - val_loss: 2.5417 - val_accuracy: 0.1875\n",
"Epoch 387/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9117 - accuracy: 0.4688 - val_loss: 2.5385 - val_accuracy: 0.1875\n",
"Epoch 388/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9396 - accuracy: 0.4688 - val_loss: 2.5048 - val_accuracy: 0.1875\n",
"Epoch 389/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9839 - accuracy: 0.4062 - val_loss: 2.5922 - val_accuracy: 0.1875\n",
"Epoch 390/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9049 - accuracy: 0.5000 - val_loss: 2.5229 - val_accuracy: 0.1875\n",
"Epoch 391/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9067 - accuracy: 0.5625 - val_loss: 2.6088 - val_accuracy: 0.1875\n",
"Epoch 392/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.9707 - accuracy: 0.5312 - val_loss: 2.6355 - val_accuracy: 0.1875\n",
"Epoch 393/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8115 - accuracy: 0.4688 - val_loss: 2.5689 - val_accuracy: 0.1875\n",
"Epoch 394/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.0600 - accuracy: 0.4688 - val_loss: 2.5928 - val_accuracy: 0.1875\n",
"Epoch 395/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8877 - accuracy: 0.4688 - val_loss: 2.6097 - val_accuracy: 0.1875\n",
"Epoch 396/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.8466 - accuracy: 0.5312 - val_loss: 2.5932 - val_accuracy: 0.1875\n",
"Epoch 397/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9205 - accuracy: 0.5625 - val_loss: 2.6351 - val_accuracy: 0.1875\n",
"Epoch 398/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8453 - accuracy: 0.5625 - val_loss: 2.6269 - val_accuracy: 0.1875\n",
"Epoch 399/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8576 - accuracy: 0.5312 - val_loss: 2.6378 - val_accuracy: 0.1875\n",
"Epoch 400/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.9721 - accuracy: 0.4688 - val_loss: 2.8425 - val_accuracy: 0.1875\n",
"Epoch 401/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9147 - accuracy: 0.4688 - val_loss: 2.6428 - val_accuracy: 0.2188\n",
"Epoch 402/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7939 - accuracy: 0.5938 - val_loss: 2.6912 - val_accuracy: 0.2188\n",
"Epoch 403/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9701 - accuracy: 0.2812 - val_loss: 2.6628 - val_accuracy: 0.2188\n",
"Epoch 404/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.9293 - accuracy: 0.4688 - val_loss: 2.6404 - val_accuracy: 0.2188\n",
"Epoch 405/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8652 - accuracy: 0.3438 - val_loss: 2.7062 - val_accuracy: 0.2188\n",
"Epoch 406/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7897 - accuracy: 0.5312 - val_loss: 2.6943 - val_accuracy: 0.1875\n",
"Epoch 407/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.7695 - accuracy: 0.5938 - val_loss: 2.7192 - val_accuracy: 0.2188\n",
"Epoch 408/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8663 - accuracy: 0.5625 - val_loss: 2.7102 - val_accuracy: 0.2188\n",
"Epoch 409/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.0265 - accuracy: 0.5000 - val_loss: 2.9814 - val_accuracy: 0.1875\n",
"Epoch 410/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7808 - accuracy: 0.5000 - val_loss: 2.8164 - val_accuracy: 0.2188\n",
"Epoch 411/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.8130 - accuracy: 0.5938 - val_loss: 2.7598 - val_accuracy: 0.1875\n",
"Epoch 412/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7833 - accuracy: 0.5312 - val_loss: 2.7942 - val_accuracy: 0.2188\n",
"Epoch 413/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8087 - accuracy: 0.4688 - val_loss: 2.8333 - val_accuracy: 0.2188\n",
"Epoch 414/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8208 - accuracy: 0.6562 - val_loss: 2.7398 - val_accuracy: 0.1875\n",
"Epoch 415/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.9364 - accuracy: 0.4375 - val_loss: 2.8387 - val_accuracy: 0.1875\n",
"Epoch 416/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8441 - accuracy: 0.4375 - val_loss: 2.7440 - val_accuracy: 0.1875\n",
"Epoch 417/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8307 - accuracy: 0.5312 - val_loss: 2.7780 - val_accuracy: 0.2188\n",
"Epoch 418/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7801 - accuracy: 0.5625 - val_loss: 2.8109 - val_accuracy: 0.2188\n",
"Epoch 419/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8642 - accuracy: 0.5625 - val_loss: 2.9301 - val_accuracy: 0.2188\n",
"Epoch 420/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8377 - accuracy: 0.3750 - val_loss: 2.8203 - val_accuracy: 0.1875\n",
"Epoch 421/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.8019 - accuracy: 0.5312 - val_loss: 2.8410 - val_accuracy: 0.2188\n",
"Epoch 422/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.8008 - accuracy: 0.4375 - val_loss: 2.7600 - val_accuracy: 0.1875\n",
"Epoch 423/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.7486 - accuracy: 0.5938 - val_loss: 2.8587 - val_accuracy: 0.1875\n",
"Epoch 424/5000\n",
"1/1 [==============================] - 0s 222ms/step - loss: 0.8493 - accuracy: 0.5312 - val_loss: 2.8231 - val_accuracy: 0.1875\n",
"Epoch 425/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.8529 - accuracy: 0.6562 - val_loss: 2.8279 - val_accuracy: 0.1875\n",
"Epoch 426/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7397 - accuracy: 0.5312 - val_loss: 2.8907 - val_accuracy: 0.1875\n",
"Epoch 427/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7284 - accuracy: 0.5312 - val_loss: 2.7972 - val_accuracy: 0.1875\n",
"Epoch 428/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7409 - accuracy: 0.5938 - val_loss: 2.9089 - val_accuracy: 0.1875\n",
"Epoch 429/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.8599 - accuracy: 0.6250 - val_loss: 2.8684 - val_accuracy: 0.1875\n",
"Epoch 430/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.8573 - accuracy: 0.5312 - val_loss: 2.9737 - val_accuracy: 0.1875\n",
"Epoch 431/5000\n",
"1/1 [==============================] - 0s 209ms/step - loss: 0.7460 - accuracy: 0.4688 - val_loss: 2.7807 - val_accuracy: 0.1875\n",
"Epoch 432/5000\n",
"1/1 [==============================] - 0s 213ms/step - loss: 0.8380 - accuracy: 0.5000 - val_loss: 2.8762 - val_accuracy: 0.1875\n",
"Epoch 433/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8266 - accuracy: 0.4062 - val_loss: 2.8902 - val_accuracy: 0.1562\n",
"Epoch 434/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7668 - accuracy: 0.4688 - val_loss: 2.7883 - val_accuracy: 0.1875\n",
"Epoch 435/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.7879 - accuracy: 0.5312 - val_loss: 2.9130 - val_accuracy: 0.1562\n",
"Epoch 436/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7468 - accuracy: 0.5000 - val_loss: 2.8201 - val_accuracy: 0.1875\n",
"Epoch 437/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7407 - accuracy: 0.4688 - val_loss: 2.8628 - val_accuracy: 0.1562\n",
"Epoch 438/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8020 - accuracy: 0.6250 - val_loss: 2.8759 - val_accuracy: 0.1562\n",
"Epoch 439/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.8091 - accuracy: 0.5312 - val_loss: 2.8989 - val_accuracy: 0.1875\n",
"Epoch 440/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7758 - accuracy: 0.5000 - val_loss: 2.8627 - val_accuracy: 0.1562\n",
"Epoch 441/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.7217 - accuracy: 0.5938 - val_loss: 2.8858 - val_accuracy: 0.1562\n",
"Epoch 442/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.7053 - accuracy: 0.5312 - val_loss: 2.8398 - val_accuracy: 0.1875\n",
"Epoch 443/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7670 - accuracy: 0.5625 - val_loss: 2.8939 - val_accuracy: 0.1562\n",
"Epoch 444/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6677 - accuracy: 0.5938 - val_loss: 2.9184 - val_accuracy: 0.1875\n",
"Epoch 445/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8183 - accuracy: 0.5000 - val_loss: 2.9112 - val_accuracy: 0.1562\n",
"Epoch 446/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9349 - accuracy: 0.4375 - val_loss: 2.9035 - val_accuracy: 0.1875\n",
"Epoch 447/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8547 - accuracy: 0.5625 - val_loss: 2.9341 - val_accuracy: 0.1562\n",
"Epoch 448/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8077 - accuracy: 0.4688 - val_loss: 2.8792 - val_accuracy: 0.1562\n",
"Epoch 449/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7069 - accuracy: 0.4375 - val_loss: 2.8698 - val_accuracy: 0.1875\n",
"Epoch 450/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7932 - accuracy: 0.5000 - val_loss: 2.9526 - val_accuracy: 0.1562\n",
"Epoch 451/5000\n",
"1/1 [==============================] - 0s 210ms/step - loss: 0.8112 - accuracy: 0.5625 - val_loss: 2.9404 - val_accuracy: 0.1562\n",
"Epoch 452/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.8458 - accuracy: 0.4375 - val_loss: 2.9407 - val_accuracy: 0.1562\n",
"Epoch 453/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.7616 - accuracy: 0.5000 - val_loss: 2.8874 - val_accuracy: 0.1875\n",
"Epoch 454/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7453 - accuracy: 0.5625 - val_loss: 2.9603 - val_accuracy: 0.1875\n",
"Epoch 455/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6461 - accuracy: 0.6250 - val_loss: 2.9333 - val_accuracy: 0.1875\n",
"Epoch 456/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7832 - accuracy: 0.5312 - val_loss: 3.0343 - val_accuracy: 0.1875\n",
"Epoch 457/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.0626 - accuracy: 0.5625 - val_loss: 2.9109 - val_accuracy: 0.1875\n",
"Epoch 458/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.8919 - accuracy: 0.4375 - val_loss: 3.1499 - val_accuracy: 0.1875\n",
"Epoch 459/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9427 - accuracy: 0.5312 - val_loss: 2.8291 - val_accuracy: 0.1875\n",
"Epoch 460/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7391 - accuracy: 0.4688 - val_loss: 3.0388 - val_accuracy: 0.2188\n",
"Epoch 461/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7720 - accuracy: 0.5000 - val_loss: 3.0748 - val_accuracy: 0.1562\n",
"Epoch 462/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8190 - accuracy: 0.4375 - val_loss: 2.9768 - val_accuracy: 0.1875\n",
"Epoch 463/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7603 - accuracy: 0.5312 - val_loss: 3.0211 - val_accuracy: 0.1562\n",
"Epoch 464/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8214 - accuracy: 0.5625 - val_loss: 3.1334 - val_accuracy: 0.1875\n",
"Epoch 465/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8029 - accuracy: 0.4375 - val_loss: 2.9107 - val_accuracy: 0.1875\n",
"Epoch 466/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7770 - accuracy: 0.5312 - val_loss: 3.1395 - val_accuracy: 0.1875\n",
"Epoch 467/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8337 - accuracy: 0.5625 - val_loss: 3.0494 - val_accuracy: 0.1562\n",
"Epoch 468/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8496 - accuracy: 0.5000 - val_loss: 3.1025 - val_accuracy: 0.1562\n",
"Epoch 469/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8040 - accuracy: 0.3750 - val_loss: 3.0093 - val_accuracy: 0.1875\n",
"Epoch 470/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7163 - accuracy: 0.6250 - val_loss: 2.9578 - val_accuracy: 0.1562\n",
"Epoch 471/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7441 - accuracy: 0.5312 - val_loss: 3.0571 - val_accuracy: 0.1562\n",
"Epoch 472/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8632 - accuracy: 0.4062 - val_loss: 3.1050 - val_accuracy: 0.1562\n",
"Epoch 473/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6791 - accuracy: 0.5938 - val_loss: 2.9250 - val_accuracy: 0.1875\n",
"Epoch 474/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6670 - accuracy: 0.5625 - val_loss: 3.0249 - val_accuracy: 0.1562\n",
"Epoch 475/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8717 - accuracy: 0.4062 - val_loss: 3.0410 - val_accuracy: 0.1562\n",
"Epoch 476/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8075 - accuracy: 0.5000 - val_loss: 3.0540 - val_accuracy: 0.1562\n",
"Epoch 477/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7068 - accuracy: 0.5000 - val_loss: 2.9948 - val_accuracy: 0.1875\n",
"Epoch 478/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8221 - accuracy: 0.5000 - val_loss: 3.0494 - val_accuracy: 0.1875\n",
"Epoch 479/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6551 - accuracy: 0.6875 - val_loss: 3.0897 - val_accuracy: 0.1875\n",
"Epoch 480/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7773 - accuracy: 0.6562 - val_loss: 2.9752 - val_accuracy: 0.1875\n",
"Epoch 481/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7664 - accuracy: 0.5312 - val_loss: 3.0105 - val_accuracy: 0.1875\n",
"Epoch 482/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8601 - accuracy: 0.4688 - val_loss: 2.9470 - val_accuracy: 0.1875\n",
"Epoch 483/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7633 - accuracy: 0.5312 - val_loss: 3.1279 - val_accuracy: 0.1875\n",
"Epoch 484/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6996 - accuracy: 0.5312 - val_loss: 2.8926 - val_accuracy: 0.1875\n",
"Epoch 485/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7431 - accuracy: 0.4688 - val_loss: 3.0723 - val_accuracy: 0.1875\n",
"Epoch 486/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6452 - accuracy: 0.5938 - val_loss: 2.9129 - val_accuracy: 0.1875\n",
"Epoch 487/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7136 - accuracy: 0.5000 - val_loss: 2.9845 - val_accuracy: 0.1875\n",
"Epoch 488/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7752 - accuracy: 0.6562 - val_loss: 2.9833 - val_accuracy: 0.1875\n",
"Epoch 489/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.2116 - accuracy: 0.4688 - val_loss: 3.2164 - val_accuracy: 0.2188\n",
"Epoch 490/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.3109 - accuracy: 0.4062 - val_loss: 2.8865 - val_accuracy: 0.1562\n",
"Epoch 491/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.3682 - accuracy: 0.3125 - val_loss: 3.3678 - val_accuracy: 0.1250\n",
"Epoch 492/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.9578 - accuracy: 0.3438 - val_loss: 2.9422 - val_accuracy: 0.2188\n",
"Epoch 493/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7519 - accuracy: 0.5625 - val_loss: 3.0523 - val_accuracy: 0.1875\n",
"Epoch 494/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7581 - accuracy: 0.4688 - val_loss: 3.1483 - val_accuracy: 0.2188\n",
"Epoch 495/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7813 - accuracy: 0.5312 - val_loss: 3.0326 - val_accuracy: 0.1875\n",
"Epoch 496/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7664 - accuracy: 0.5312 - val_loss: 3.1391 - val_accuracy: 0.1875\n",
"Epoch 497/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7988 - accuracy: 0.5000 - val_loss: 3.0012 - val_accuracy: 0.1875\n",
"Epoch 498/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7712 - accuracy: 0.5312 - val_loss: 3.2270 - val_accuracy: 0.2188\n",
"Epoch 499/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8336 - accuracy: 0.4062 - val_loss: 2.9638 - val_accuracy: 0.2188\n",
"Epoch 500/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7213 - accuracy: 0.5625 - val_loss: 3.1732 - val_accuracy: 0.1875\n",
"Epoch 501/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7911 - accuracy: 0.5625 - val_loss: 2.9434 - val_accuracy: 0.2188\n",
"Epoch 502/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8604 - accuracy: 0.4375 - val_loss: 3.1414 - val_accuracy: 0.2500\n",
"Epoch 503/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7641 - accuracy: 0.5625 - val_loss: 2.9744 - val_accuracy: 0.2188\n",
"Epoch 504/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8518 - accuracy: 0.4375 - val_loss: 3.2012 - val_accuracy: 0.1875\n",
"Epoch 505/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8740 - accuracy: 0.5312 - val_loss: 2.9763 - val_accuracy: 0.1875\n",
"Epoch 506/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7702 - accuracy: 0.5000 - val_loss: 3.0265 - val_accuracy: 0.1875\n",
"Epoch 507/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7026 - accuracy: 0.6562 - val_loss: 3.0445 - val_accuracy: 0.1875\n",
"Epoch 508/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7454 - accuracy: 0.4688 - val_loss: 2.9955 - val_accuracy: 0.1875\n",
"Epoch 509/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7959 - accuracy: 0.5625 - val_loss: 3.0276 - val_accuracy: 0.1875\n",
"Epoch 510/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6677 - accuracy: 0.5625 - val_loss: 3.1141 - val_accuracy: 0.1875\n",
"Epoch 511/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7133 - accuracy: 0.6250 - val_loss: 3.0856 - val_accuracy: 0.1562\n",
"Epoch 512/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6529 - accuracy: 0.6875 - val_loss: 3.1255 - val_accuracy: 0.1875\n",
"Epoch 513/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9784 - accuracy: 0.3750 - val_loss: 3.0122 - val_accuracy: 0.1875\n",
"Epoch 514/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7853 - accuracy: 0.5625 - val_loss: 3.1978 - val_accuracy: 0.1562\n",
"Epoch 515/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7994 - accuracy: 0.5000 - val_loss: 3.0522 - val_accuracy: 0.1562\n",
"Epoch 516/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7987 - accuracy: 0.4375 - val_loss: 3.0741 - val_accuracy: 0.1875\n",
"Epoch 517/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8203 - accuracy: 0.4688 - val_loss: 3.1168 - val_accuracy: 0.1562\n",
"Epoch 518/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7936 - accuracy: 0.4375 - val_loss: 3.2558 - val_accuracy: 0.1562\n",
"Epoch 519/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.7437 - accuracy: 0.4688 - val_loss: 2.9616 - val_accuracy: 0.1875\n",
"Epoch 520/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7562 - accuracy: 0.5938 - val_loss: 3.1688 - val_accuracy: 0.2188\n",
"Epoch 521/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.7724 - accuracy: 0.5000 - val_loss: 3.0773 - val_accuracy: 0.1562\n",
"Epoch 522/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.7518 - accuracy: 0.5312 - val_loss: 3.1356 - val_accuracy: 0.1562\n",
"Epoch 523/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8309 - accuracy: 0.5938 - val_loss: 3.0924 - val_accuracy: 0.1562\n",
"Epoch 524/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7000 - accuracy: 0.6250 - val_loss: 3.1635 - val_accuracy: 0.1562\n",
"Epoch 525/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.7701 - accuracy: 0.4375 - val_loss: 3.0955 - val_accuracy: 0.1562\n",
"Epoch 526/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.8042 - accuracy: 0.4688 - val_loss: 3.0395 - val_accuracy: 0.1562\n",
"Epoch 527/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6816 - accuracy: 0.5625 - val_loss: 3.1019 - val_accuracy: 0.1562\n",
"Epoch 528/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7530 - accuracy: 0.5625 - val_loss: 3.1066 - val_accuracy: 0.1562\n",
"Epoch 529/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7912 - accuracy: 0.5312 - val_loss: 3.1411 - val_accuracy: 0.1562\n",
"Epoch 530/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7679 - accuracy: 0.5312 - val_loss: 3.0282 - val_accuracy: 0.1562\n",
"Epoch 531/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7755 - accuracy: 0.4375 - val_loss: 3.0992 - val_accuracy: 0.1562\n",
"Epoch 532/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7121 - accuracy: 0.5625 - val_loss: 3.0315 - val_accuracy: 0.1562\n",
"Epoch 533/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7010 - accuracy: 0.4688 - val_loss: 3.0944 - val_accuracy: 0.1562\n",
"Epoch 534/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8625 - accuracy: 0.5000 - val_loss: 3.1968 - val_accuracy: 0.1562\n",
"Epoch 535/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7140 - accuracy: 0.5625 - val_loss: 3.1548 - val_accuracy: 0.1875\n",
"Epoch 536/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8274 - accuracy: 0.4375 - val_loss: 3.1893 - val_accuracy: 0.1562\n",
"Epoch 537/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7821 - accuracy: 0.5000 - val_loss: 3.1346 - val_accuracy: 0.1875\n",
"Epoch 538/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7817 - accuracy: 0.5938 - val_loss: 3.1135 - val_accuracy: 0.1875\n",
"Epoch 539/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7698 - accuracy: 0.5000 - val_loss: 3.2230 - val_accuracy: 0.1562\n",
"Epoch 540/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7817 - accuracy: 0.4375 - val_loss: 3.1338 - val_accuracy: 0.1562\n",
"Epoch 541/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7662 - accuracy: 0.5312 - val_loss: 3.1287 - val_accuracy: 0.1562\n",
"Epoch 542/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8009 - accuracy: 0.4688 - val_loss: 3.1866 - val_accuracy: 0.1562\n",
"Epoch 543/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6854 - accuracy: 0.6250 - val_loss: 3.1880 - val_accuracy: 0.2188\n",
"Epoch 544/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7581 - accuracy: 0.5625 - val_loss: 3.1111 - val_accuracy: 0.1875\n",
"Epoch 545/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7071 - accuracy: 0.5000 - val_loss: 3.0582 - val_accuracy: 0.1875\n",
"Epoch 546/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8223 - accuracy: 0.5000 - val_loss: 3.3934 - val_accuracy: 0.1875\n",
"Epoch 547/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8045 - accuracy: 0.5312 - val_loss: 3.0369 - val_accuracy: 0.1875\n",
"Epoch 548/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7611 - accuracy: 0.4688 - val_loss: 3.2348 - val_accuracy: 0.1562\n",
"Epoch 549/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.8459 - accuracy: 0.5000 - val_loss: 3.0325 - val_accuracy: 0.1875\n",
"Epoch 550/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8441 - accuracy: 0.4062 - val_loss: 3.3053 - val_accuracy: 0.1562\n",
"Epoch 551/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8834 - accuracy: 0.4375 - val_loss: 2.9936 - val_accuracy: 0.1562\n",
"Epoch 552/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7347 - accuracy: 0.5938 - val_loss: 3.2369 - val_accuracy: 0.1875\n",
"Epoch 553/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7430 - accuracy: 0.5625 - val_loss: 3.1495 - val_accuracy: 0.1562\n",
"Epoch 554/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7716 - accuracy: 0.5000 - val_loss: 3.1785 - val_accuracy: 0.1562\n",
"Epoch 555/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7442 - accuracy: 0.5938 - val_loss: 3.1827 - val_accuracy: 0.1562\n",
"Epoch 556/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8067 - accuracy: 0.5312 - val_loss: 3.2855 - val_accuracy: 0.1875\n",
"Epoch 557/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7649 - accuracy: 0.5000 - val_loss: 3.0984 - val_accuracy: 0.1875\n",
"Epoch 558/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8261 - accuracy: 0.4688 - val_loss: 3.3631 - val_accuracy: 0.1875\n",
"Epoch 559/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8213 - accuracy: 0.4062 - val_loss: 3.0162 - val_accuracy: 0.1562\n",
"Epoch 560/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9361 - accuracy: 0.4375 - val_loss: 3.4148 - val_accuracy: 0.1562\n",
"Epoch 561/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8222 - accuracy: 0.4375 - val_loss: 3.0827 - val_accuracy: 0.1562\n",
"Epoch 562/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6827 - accuracy: 0.6875 - val_loss: 3.2159 - val_accuracy: 0.1562\n",
"Epoch 563/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8311 - accuracy: 0.4688 - val_loss: 3.0741 - val_accuracy: 0.1562\n",
"Epoch 564/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6035 - accuracy: 0.5938 - val_loss: 3.1703 - val_accuracy: 0.1562\n",
"Epoch 565/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7643 - accuracy: 0.5000 - val_loss: 3.2275 - val_accuracy: 0.1875\n",
"Epoch 566/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6845 - accuracy: 0.5938 - val_loss: 3.1617 - val_accuracy: 0.1562\n",
"Epoch 567/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5890 - accuracy: 0.6562 - val_loss: 3.1215 - val_accuracy: 0.1562\n",
"Epoch 568/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6632 - accuracy: 0.5312 - val_loss: 3.2063 - val_accuracy: 0.1875\n",
"Epoch 569/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6944 - accuracy: 0.6562 - val_loss: 3.2283 - val_accuracy: 0.1562\n",
"Epoch 570/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7932 - accuracy: 0.5000 - val_loss: 3.1633 - val_accuracy: 0.1875\n",
"Epoch 571/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7325 - accuracy: 0.5625 - val_loss: 3.2451 - val_accuracy: 0.1562\n",
"Epoch 572/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7295 - accuracy: 0.5312 - val_loss: 3.1546 - val_accuracy: 0.1562\n",
"Epoch 573/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7656 - accuracy: 0.5938 - val_loss: 3.3815 - val_accuracy: 0.1562\n",
"Epoch 574/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7112 - accuracy: 0.5625 - val_loss: 3.1840 - val_accuracy: 0.1562\n",
"Epoch 575/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7149 - accuracy: 0.5000 - val_loss: 3.1654 - val_accuracy: 0.1562\n",
"Epoch 576/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7338 - accuracy: 0.5312 - val_loss: 3.2478 - val_accuracy: 0.1562\n",
"Epoch 577/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7646 - accuracy: 0.4375 - val_loss: 3.2866 - val_accuracy: 0.1562\n",
"Epoch 578/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8513 - accuracy: 0.5312 - val_loss: 3.1654 - val_accuracy: 0.1562\n",
"Epoch 579/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7208 - accuracy: 0.6250 - val_loss: 3.2970 - val_accuracy: 0.1562\n",
"Epoch 580/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6896 - accuracy: 0.5000 - val_loss: 3.1330 - val_accuracy: 0.1562\n",
"Epoch 581/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9534 - accuracy: 0.5625 - val_loss: 3.1944 - val_accuracy: 0.1562\n",
"Epoch 582/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7859 - accuracy: 0.4375 - val_loss: 3.3016 - val_accuracy: 0.1562\n",
"Epoch 583/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7131 - accuracy: 0.5938 - val_loss: 3.1424 - val_accuracy: 0.1562\n",
"Epoch 584/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7437 - accuracy: 0.5625 - val_loss: 3.3841 - val_accuracy: 0.1562\n",
"Epoch 585/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.8049 - accuracy: 0.4375 - val_loss: 3.0870 - val_accuracy: 0.1562\n",
"Epoch 586/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7375 - accuracy: 0.5312 - val_loss: 3.3386 - val_accuracy: 0.1250\n",
"Epoch 587/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8042 - accuracy: 0.5625 - val_loss: 3.1355 - val_accuracy: 0.1562\n",
"Epoch 588/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8263 - accuracy: 0.4688 - val_loss: 3.2055 - val_accuracy: 0.1562\n",
"Epoch 589/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8191 - accuracy: 0.5312 - val_loss: 3.0689 - val_accuracy: 0.1562\n",
"Epoch 590/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7676 - accuracy: 0.5000 - val_loss: 3.3358 - val_accuracy: 0.1562\n",
"Epoch 591/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8458 - accuracy: 0.5000 - val_loss: 3.0349 - val_accuracy: 0.1562\n",
"Epoch 592/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7562 - accuracy: 0.3750 - val_loss: 3.2764 - val_accuracy: 0.1562\n",
"Epoch 593/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6706 - accuracy: 0.5312 - val_loss: 3.0879 - val_accuracy: 0.1562\n",
"Epoch 594/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7085 - accuracy: 0.4062 - val_loss: 3.2504 - val_accuracy: 0.1562\n",
"Epoch 595/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7042 - accuracy: 0.5312 - val_loss: 3.1483 - val_accuracy: 0.1562\n",
"Epoch 596/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7621 - accuracy: 0.5000 - val_loss: 3.1720 - val_accuracy: 0.1562\n",
"Epoch 597/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7675 - accuracy: 0.5000 - val_loss: 3.2203 - val_accuracy: 0.1562\n",
"Epoch 598/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7122 - accuracy: 0.5625 - val_loss: 3.1380 - val_accuracy: 0.1562\n",
"Epoch 599/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7087 - accuracy: 0.5000 - val_loss: 3.1609 - val_accuracy: 0.1562\n",
"Epoch 600/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7784 - accuracy: 0.5312 - val_loss: 3.2676 - val_accuracy: 0.1562\n",
"Epoch 601/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8509 - accuracy: 0.5000 - val_loss: 3.1990 - val_accuracy: 0.1562\n",
"Epoch 602/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6993 - accuracy: 0.5938 - val_loss: 3.2363 - val_accuracy: 0.1562\n",
"Epoch 603/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8656 - accuracy: 0.4375 - val_loss: 3.1208 - val_accuracy: 0.1562\n",
"Epoch 604/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8742 - accuracy: 0.4688 - val_loss: 3.1985 - val_accuracy: 0.1562\n",
"Epoch 605/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7390 - accuracy: 0.5312 - val_loss: 3.1318 - val_accuracy: 0.1562\n",
"Epoch 606/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6645 - accuracy: 0.5312 - val_loss: 3.1673 - val_accuracy: 0.1562\n",
"Epoch 607/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7309 - accuracy: 0.4375 - val_loss: 3.1713 - val_accuracy: 0.1562\n",
"Epoch 608/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6901 - accuracy: 0.5312 - val_loss: 3.1004 - val_accuracy: 0.1562\n",
"Epoch 609/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8425 - accuracy: 0.4688 - val_loss: 3.3473 - val_accuracy: 0.1562\n",
"Epoch 610/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7140 - accuracy: 0.4062 - val_loss: 3.0920 - val_accuracy: 0.1562\n",
"Epoch 611/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7814 - accuracy: 0.4688 - val_loss: 3.2659 - val_accuracy: 0.1875\n",
"Epoch 612/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7899 - accuracy: 0.5625 - val_loss: 3.1379 - val_accuracy: 0.1562\n",
"Epoch 613/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.9011 - accuracy: 0.4375 - val_loss: 3.2479 - val_accuracy: 0.1562\n",
"Epoch 614/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7266 - accuracy: 0.5625 - val_loss: 3.1179 - val_accuracy: 0.1875\n",
"Epoch 615/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6251 - accuracy: 0.6250 - val_loss: 3.3071 - val_accuracy: 0.1562\n",
"Epoch 616/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7249 - accuracy: 0.5938 - val_loss: 3.1725 - val_accuracy: 0.1562\n",
"Epoch 617/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8452 - accuracy: 0.4062 - val_loss: 3.1950 - val_accuracy: 0.1562\n",
"Epoch 618/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7642 - accuracy: 0.5625 - val_loss: 3.2174 - val_accuracy: 0.1562\n",
"Epoch 619/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7419 - accuracy: 0.5938 - val_loss: 3.2184 - val_accuracy: 0.1562\n",
"Epoch 620/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8089 - accuracy: 0.4375 - val_loss: 3.1452 - val_accuracy: 0.1562\n",
"Epoch 621/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7968 - accuracy: 0.6250 - val_loss: 3.3391 - val_accuracy: 0.1562\n",
"Epoch 622/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7164 - accuracy: 0.5312 - val_loss: 3.1263 - val_accuracy: 0.1562\n",
"Epoch 623/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8118 - accuracy: 0.4062 - val_loss: 3.1662 - val_accuracy: 0.1562\n",
"Epoch 624/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7514 - accuracy: 0.5938 - val_loss: 3.1433 - val_accuracy: 0.1562\n",
"Epoch 625/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8515 - accuracy: 0.4688 - val_loss: 3.2667 - val_accuracy: 0.1562\n",
"Epoch 626/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.8079 - accuracy: 0.5312 - val_loss: 3.1250 - val_accuracy: 0.1562\n",
"Epoch 627/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7155 - accuracy: 0.4688 - val_loss: 3.2162 - val_accuracy: 0.1875\n",
"Epoch 628/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7698 - accuracy: 0.4688 - val_loss: 3.2289 - val_accuracy: 0.1562\n",
"Epoch 629/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8629 - accuracy: 0.5938 - val_loss: 3.2329 - val_accuracy: 0.1562\n",
"Epoch 630/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8310 - accuracy: 0.4375 - val_loss: 3.2531 - val_accuracy: 0.1562\n",
"Epoch 631/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7376 - accuracy: 0.4688 - val_loss: 3.3018 - val_accuracy: 0.1562\n",
"Epoch 632/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6739 - accuracy: 0.6250 - val_loss: 3.2062 - val_accuracy: 0.1562\n",
"Epoch 633/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9313 - accuracy: 0.4375 - val_loss: 3.1957 - val_accuracy: 0.1562\n",
"Epoch 634/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7550 - accuracy: 0.5938 - val_loss: 3.1526 - val_accuracy: 0.1562\n",
"Epoch 635/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7592 - accuracy: 0.5938 - val_loss: 3.0905 - val_accuracy: 0.1562\n",
"Epoch 636/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8498 - accuracy: 0.4375 - val_loss: 3.6139 - val_accuracy: 0.1875\n",
"Epoch 637/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8118 - accuracy: 0.4688 - val_loss: 2.8639 - val_accuracy: 0.1562\n",
"Epoch 638/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.9484 - accuracy: 0.5000 - val_loss: 3.3502 - val_accuracy: 0.1562\n",
"Epoch 639/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8909 - accuracy: 0.3750 - val_loss: 3.0726 - val_accuracy: 0.1875\n",
"Epoch 640/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7087 - accuracy: 0.5938 - val_loss: 3.1408 - val_accuracy: 0.1875\n",
"Epoch 641/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8077 - accuracy: 0.5625 - val_loss: 3.2496 - val_accuracy: 0.1562\n",
"Epoch 642/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7096 - accuracy: 0.5625 - val_loss: 3.1985 - val_accuracy: 0.1562\n",
"Epoch 643/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7014 - accuracy: 0.5312 - val_loss: 3.2632 - val_accuracy: 0.1562\n",
"Epoch 644/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7425 - accuracy: 0.5312 - val_loss: 3.1489 - val_accuracy: 0.1562\n",
"Epoch 645/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6949 - accuracy: 0.5000 - val_loss: 3.2449 - val_accuracy: 0.1562\n",
"Epoch 646/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6858 - accuracy: 0.5312 - val_loss: 3.1289 - val_accuracy: 0.1875\n",
"Epoch 647/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6682 - accuracy: 0.5938 - val_loss: 3.2196 - val_accuracy: 0.1562\n",
"Epoch 648/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7974 - accuracy: 0.4062 - val_loss: 3.1730 - val_accuracy: 0.1562\n",
"Epoch 649/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7500 - accuracy: 0.5938 - val_loss: 3.2340 - val_accuracy: 0.1562\n",
"Epoch 650/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.7807 - accuracy: 0.4688 - val_loss: 3.1050 - val_accuracy: 0.1875\n",
"Epoch 651/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7671 - accuracy: 0.4375 - val_loss: 3.2873 - val_accuracy: 0.1562\n",
"Epoch 652/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7503 - accuracy: 0.5000 - val_loss: 3.0883 - val_accuracy: 0.1875\n",
"Epoch 653/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7272 - accuracy: 0.4688 - val_loss: 3.3747 - val_accuracy: 0.1562\n",
"Epoch 654/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8123 - accuracy: 0.5312 - val_loss: 3.0237 - val_accuracy: 0.1875\n",
"Epoch 655/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8031 - accuracy: 0.5625 - val_loss: 3.4031 - val_accuracy: 0.1562\n",
"Epoch 656/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7047 - accuracy: 0.4688 - val_loss: 3.1444 - val_accuracy: 0.1562\n",
"Epoch 657/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7658 - accuracy: 0.5312 - val_loss: 3.3508 - val_accuracy: 0.1562\n",
"Epoch 658/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7996 - accuracy: 0.4375 - val_loss: 3.0937 - val_accuracy: 0.1562\n",
"Epoch 659/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6786 - accuracy: 0.5938 - val_loss: 3.2747 - val_accuracy: 0.1562\n",
"Epoch 660/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7861 - accuracy: 0.5000 - val_loss: 3.2134 - val_accuracy: 0.1562\n",
"Epoch 661/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7691 - accuracy: 0.5312 - val_loss: 3.1391 - val_accuracy: 0.1562\n",
"Epoch 662/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7358 - accuracy: 0.4688 - val_loss: 3.3235 - val_accuracy: 0.1875\n",
"Epoch 663/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7239 - accuracy: 0.5312 - val_loss: 3.0490 - val_accuracy: 0.2188\n",
"Epoch 664/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.1267 - accuracy: 0.5000 - val_loss: 5.2977 - val_accuracy: 0.0312\n",
"Epoch 665/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 3.7838 - accuracy: 0.1562 - val_loss: 6.0151 - val_accuracy: 0.1562\n",
"Epoch 666/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 16.7141 - accuracy: 0.1562 - val_loss: 7.3040 - val_accuracy: 0.0312\n",
"Epoch 667/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 8.2424 - accuracy: 0.0938 - val_loss: 2.9554 - val_accuracy: 0.0312\n",
"Epoch 668/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 3.7586 - accuracy: 0.1562 - val_loss: 2.8403 - val_accuracy: 0.0312\n",
"Epoch 669/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 3.1064 - accuracy: 0.0625 - val_loss: 2.6737 - val_accuracy: 0.0312\n",
"Epoch 670/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 3.0810 - accuracy: 0.1875 - val_loss: 2.6947 - val_accuracy: 0.0312\n",
"Epoch 671/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.8868 - accuracy: 0.1875 - val_loss: 2.7173 - val_accuracy: 0.0312\n",
"Epoch 672/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 3.1225 - accuracy: 0.0938 - val_loss: 2.7885 - val_accuracy: 0.0312\n",
"Epoch 673/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 2.7741 - accuracy: 0.1875 - val_loss: 2.7995 - val_accuracy: 0.0312\n",
"Epoch 674/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.8871 - accuracy: 0.0938 - val_loss: 2.7313 - val_accuracy: 0.0312\n",
"Epoch 675/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.7409 - accuracy: 0.0625 - val_loss: 2.6378 - val_accuracy: 0.0625\n",
"Epoch 676/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 2.5736 - accuracy: 0.1875 - val_loss: 2.6405 - val_accuracy: 0.0312\n",
"Epoch 677/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.5561 - accuracy: 0.1250 - val_loss: 2.6111 - val_accuracy: 0.0625\n",
"Epoch 678/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.4954 - accuracy: 0.1250 - val_loss: 2.5584 - val_accuracy: 0.1250\n",
"Epoch 679/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.8955 - accuracy: 0.1250 - val_loss: 2.5931 - val_accuracy: 0.0938\n",
"Epoch 680/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.5878 - accuracy: 0.1250 - val_loss: 2.5853 - val_accuracy: 0.0625\n",
"Epoch 681/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.5062 - accuracy: 0.1562 - val_loss: 2.5706 - val_accuracy: 0.0625\n",
"Epoch 682/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.3220 - accuracy: 0.1250 - val_loss: 2.6013 - val_accuracy: 0.0000e+00\n",
"Epoch 683/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.5485 - accuracy: 0.1250 - val_loss: 2.6481 - val_accuracy: 0.0000e+00\n",
"Epoch 684/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.3578 - accuracy: 0.1250 - val_loss: 2.6871 - val_accuracy: 0.0000e+00\n",
"Epoch 685/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.1371 - accuracy: 0.0938 - val_loss: 2.7213 - val_accuracy: 0.0000e+00\n",
"Epoch 686/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.2910 - accuracy: 0.1562 - val_loss: 2.7794 - val_accuracy: 0.0000e+00\n",
"Epoch 687/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.0855 - accuracy: 0.1562 - val_loss: 2.8317 - val_accuracy: 0.0312\n",
"Epoch 688/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.1110 - accuracy: 0.0938 - val_loss: 2.7321 - val_accuracy: 0.0312\n",
"Epoch 689/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.5415 - accuracy: 0.1875 - val_loss: 2.9405 - val_accuracy: 0.0000e+00\n",
"Epoch 690/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.1640 - accuracy: 0.0625 - val_loss: 2.8237 - val_accuracy: 0.0000e+00\n",
"Epoch 691/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.1561 - accuracy: 0.2188 - val_loss: 2.8732 - val_accuracy: 0.0312\n",
"Epoch 692/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.0471 - accuracy: 0.1875 - val_loss: 2.8195 - val_accuracy: 0.0312\n",
"Epoch 693/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.2818 - accuracy: 0.0938 - val_loss: 2.8956 - val_accuracy: 0.0312\n",
"Epoch 694/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.1426 - accuracy: 0.0938 - val_loss: 2.8629 - val_accuracy: 0.0000e+00\n",
"Epoch 695/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 2.0064 - accuracy: 0.1250 - val_loss: 2.7485 - val_accuracy: 0.0312\n",
"Epoch 696/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.0135 - accuracy: 0.1250 - val_loss: 2.6997 - val_accuracy: 0.0000e+00\n",
"Epoch 697/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.3754 - accuracy: 0.0938 - val_loss: 2.6961 - val_accuracy: 0.0625\n",
"Epoch 698/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.1364 - accuracy: 0.2188 - val_loss: 2.7951 - val_accuracy: 0.0312\n",
"Epoch 699/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.0893 - accuracy: 0.1562 - val_loss: 2.9172 - val_accuracy: 0.0312\n",
"Epoch 700/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.2596 - accuracy: 0.1250 - val_loss: 2.7888 - val_accuracy: 0.0312\n",
"Epoch 701/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.2298 - accuracy: 0.1250 - val_loss: 2.8276 - val_accuracy: 0.0312\n",
"Epoch 702/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.9874 - accuracy: 0.0938 - val_loss: 2.8505 - val_accuracy: 0.0312\n",
"Epoch 703/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.1602 - accuracy: 0.1250 - val_loss: 2.9595 - val_accuracy: 0.0312\n",
"Epoch 704/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.4412 - accuracy: 0.1250 - val_loss: 2.9082 - val_accuracy: 0.0312\n",
"Epoch 705/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.8515 - accuracy: 0.2188 - val_loss: 2.7848 - val_accuracy: 0.0625\n",
"Epoch 706/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 2.1339 - accuracy: 0.1875 - val_loss: 2.8286 - val_accuracy: 0.0625\n",
"Epoch 707/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.8249 - accuracy: 0.1562 - val_loss: 2.8553 - val_accuracy: 0.0625\n",
"Epoch 708/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 2.3005 - accuracy: 0.1875 - val_loss: 2.8743 - val_accuracy: 0.0312\n",
"Epoch 709/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.8713 - accuracy: 0.2500 - val_loss: 2.8436 - val_accuracy: 0.0625\n",
"Epoch 710/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.4277 - accuracy: 0.1250 - val_loss: 2.8938 - val_accuracy: 0.0000e+00\n",
"Epoch 711/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.9746 - accuracy: 0.1875 - val_loss: 2.6574 - val_accuracy: 0.0312\n",
"Epoch 712/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.2214 - accuracy: 0.1250 - val_loss: 3.0030 - val_accuracy: 0.0312\n",
"Epoch 713/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.1528 - accuracy: 0.0938 - val_loss: 2.8762 - val_accuracy: 0.0000e+00\n",
"Epoch 714/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.1999 - accuracy: 0.1875 - val_loss: 2.9020 - val_accuracy: 0.0312\n",
"Epoch 715/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.7081 - accuracy: 0.1875 - val_loss: 2.8379 - val_accuracy: 0.0625\n",
"Epoch 716/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.8406 - accuracy: 0.2188 - val_loss: 2.9301 - val_accuracy: 0.0625\n",
"Epoch 717/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.7786 - accuracy: 0.1250 - val_loss: 3.0356 - val_accuracy: 0.0625\n",
"Epoch 718/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.0579 - accuracy: 0.1562 - val_loss: 2.9098 - val_accuracy: 0.0625\n",
"Epoch 719/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.8181 - accuracy: 0.1250 - val_loss: 2.7975 - val_accuracy: 0.0625\n",
"Epoch 720/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.5328 - accuracy: 0.1562 - val_loss: 2.8324 - val_accuracy: 0.0312\n",
"Epoch 721/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.7565 - accuracy: 0.0938 - val_loss: 2.7240 - val_accuracy: 0.0938\n",
"Epoch 722/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.8872 - accuracy: 0.1875 - val_loss: 2.8646 - val_accuracy: 0.0312\n",
"Epoch 723/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.8602 - accuracy: 0.1562 - val_loss: 2.5900 - val_accuracy: 0.0625\n",
"Epoch 724/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.0677 - accuracy: 0.1875 - val_loss: 3.3616 - val_accuracy: 0.0000e+00\n",
"Epoch 725/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.8253 - accuracy: 0.0938 - val_loss: 2.8655 - val_accuracy: 0.0625\n",
"Epoch 726/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.3612 - accuracy: 0.2500 - val_loss: 2.8141 - val_accuracy: 0.0625\n",
"Epoch 727/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.4551 - accuracy: 0.2188 - val_loss: 2.7454 - val_accuracy: 0.0625\n",
"Epoch 728/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.5502 - accuracy: 0.1562 - val_loss: 2.6686 - val_accuracy: 0.0625\n",
"Epoch 729/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3497 - accuracy: 0.1562 - val_loss: 2.6102 - val_accuracy: 0.0625\n",
"Epoch 730/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.0372 - accuracy: 0.2188 - val_loss: 3.2733 - val_accuracy: 0.0312\n",
"Epoch 731/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.9435 - accuracy: 0.2188 - val_loss: 2.8481 - val_accuracy: 0.0625\n",
"Epoch 732/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.5459 - accuracy: 0.2500 - val_loss: 2.9365 - val_accuracy: 0.0938\n",
"Epoch 733/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.1662 - accuracy: 0.2188 - val_loss: 3.2901 - val_accuracy: 0.0625\n",
"Epoch 734/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.7933 - accuracy: 0.2500 - val_loss: 2.8524 - val_accuracy: 0.0938\n",
"Epoch 735/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.5265 - accuracy: 0.2188 - val_loss: 2.6598 - val_accuracy: 0.1250\n",
"Epoch 736/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.4522 - accuracy: 0.2500 - val_loss: 2.6029 - val_accuracy: 0.1250\n",
"Epoch 737/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.4752 - accuracy: 0.1562 - val_loss: 2.6846 - val_accuracy: 0.0938\n",
"Epoch 738/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.0169 - accuracy: 0.1875 - val_loss: 2.8863 - val_accuracy: 0.0938\n",
"Epoch 739/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.6695 - accuracy: 0.1562 - val_loss: 2.9390 - val_accuracy: 0.0938\n",
"Epoch 740/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.6425 - accuracy: 0.1875 - val_loss: 2.8913 - val_accuracy: 0.0625\n",
"Epoch 741/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 1.6878 - accuracy: 0.2188 - val_loss: 2.8395 - val_accuracy: 0.0625\n",
"Epoch 742/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.3465 - accuracy: 0.1250 - val_loss: 2.9419 - val_accuracy: 0.0625\n",
"Epoch 743/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.9033 - accuracy: 0.2188 - val_loss: 3.0160 - val_accuracy: 0.0625\n",
"Epoch 744/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.2867 - accuracy: 0.2188 - val_loss: 2.7983 - val_accuracy: 0.0938\n",
"Epoch 745/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.4563 - accuracy: 0.2188 - val_loss: 2.7232 - val_accuracy: 0.0625\n",
"Epoch 746/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.4761 - accuracy: 0.2812 - val_loss: 2.8602 - val_accuracy: 0.0938\n",
"Epoch 747/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.6555 - accuracy: 0.2188 - val_loss: 2.8278 - val_accuracy: 0.0625\n",
"Epoch 748/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.5646 - accuracy: 0.2188 - val_loss: 2.6344 - val_accuracy: 0.0938\n",
"Epoch 749/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.4037 - accuracy: 0.3125 - val_loss: 2.7893 - val_accuracy: 0.0938\n",
"Epoch 750/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.4132 - accuracy: 0.2188 - val_loss: 2.7567 - val_accuracy: 0.0625\n",
"Epoch 751/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.4187 - accuracy: 0.2500 - val_loss: 2.9225 - val_accuracy: 0.0625\n",
"Epoch 752/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.3607 - accuracy: 0.1875 - val_loss: 2.6916 - val_accuracy: 0.0938\n",
"Epoch 753/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.2322 - accuracy: 0.2188 - val_loss: 2.8036 - val_accuracy: 0.1250\n",
"Epoch 754/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3661 - accuracy: 0.3438 - val_loss: 2.6682 - val_accuracy: 0.1562\n",
"Epoch 755/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3367 - accuracy: 0.2812 - val_loss: 3.0521 - val_accuracy: 0.0938\n",
"Epoch 756/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.3338 - accuracy: 0.2812 - val_loss: 2.8018 - val_accuracy: 0.1562\n",
"Epoch 757/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.3512 - accuracy: 0.2500 - val_loss: 2.7185 - val_accuracy: 0.1562\n",
"Epoch 758/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3663 - accuracy: 0.2812 - val_loss: 3.0989 - val_accuracy: 0.1250\n",
"Epoch 759/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.4241 - accuracy: 0.2812 - val_loss: 2.7062 - val_accuracy: 0.0938\n",
"Epoch 760/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.1121 - accuracy: 0.3125 - val_loss: 2.8190 - val_accuracy: 0.1250\n",
"Epoch 761/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.2429 - accuracy: 0.4688 - val_loss: 2.6335 - val_accuracy: 0.1562\n",
"Epoch 762/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.1055 - accuracy: 0.3438 - val_loss: 2.6523 - val_accuracy: 0.1250\n",
"Epoch 763/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9795 - accuracy: 0.3750 - val_loss: 2.8054 - val_accuracy: 0.0938\n",
"Epoch 764/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.1929 - accuracy: 0.3438 - val_loss: 2.6525 - val_accuracy: 0.1250\n",
"Epoch 765/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.0475 - accuracy: 0.4375 - val_loss: 2.7396 - val_accuracy: 0.1562\n",
"Epoch 766/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.0114 - accuracy: 0.2812 - val_loss: 2.8076 - val_accuracy: 0.1250\n",
"Epoch 767/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.1264 - accuracy: 0.1875 - val_loss: 2.7412 - val_accuracy: 0.1562\n",
"Epoch 768/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.0408 - accuracy: 0.4062 - val_loss: 2.8088 - val_accuracy: 0.1562\n",
"Epoch 769/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.0898 - accuracy: 0.2812 - val_loss: 2.7399 - val_accuracy: 0.1562\n",
"Epoch 770/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9827 - accuracy: 0.4688 - val_loss: 2.8534 - val_accuracy: 0.1562\n",
"Epoch 771/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.0109 - accuracy: 0.4375 - val_loss: 2.8132 - val_accuracy: 0.1250\n",
"Epoch 772/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.1318 - accuracy: 0.3750 - val_loss: 3.0118 - val_accuracy: 0.1250\n",
"Epoch 773/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9393 - accuracy: 0.3750 - val_loss: 3.0565 - val_accuracy: 0.1250\n",
"Epoch 774/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9404 - accuracy: 0.3750 - val_loss: 3.0012 - val_accuracy: 0.1250\n",
"Epoch 775/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.0983 - accuracy: 0.3750 - val_loss: 2.8457 - val_accuracy: 0.1562\n",
"Epoch 776/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8182 - accuracy: 0.5312 - val_loss: 2.8953 - val_accuracy: 0.1562\n",
"Epoch 777/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8976 - accuracy: 0.3438 - val_loss: 2.9758 - val_accuracy: 0.1250\n",
"Epoch 778/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.9404 - accuracy: 0.4688 - val_loss: 2.8964 - val_accuracy: 0.1250\n",
"Epoch 779/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8198 - accuracy: 0.5000 - val_loss: 2.9074 - val_accuracy: 0.1562\n",
"Epoch 780/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8614 - accuracy: 0.4688 - val_loss: 2.8732 - val_accuracy: 0.1562\n",
"Epoch 781/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.1076 - accuracy: 0.4375 - val_loss: 3.0178 - val_accuracy: 0.1250\n",
"Epoch 782/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8839 - accuracy: 0.4375 - val_loss: 2.9091 - val_accuracy: 0.1562\n",
"Epoch 783/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.8615 - accuracy: 0.4375 - val_loss: 2.8380 - val_accuracy: 0.1562\n",
"Epoch 784/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8845 - accuracy: 0.5312 - val_loss: 2.8992 - val_accuracy: 0.1562\n",
"Epoch 785/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8343 - accuracy: 0.5000 - val_loss: 2.8985 - val_accuracy: 0.1562\n",
"Epoch 786/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8230 - accuracy: 0.4688 - val_loss: 2.8020 - val_accuracy: 0.1562\n",
"Epoch 787/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7711 - accuracy: 0.5625 - val_loss: 2.8984 - val_accuracy: 0.1562\n",
"Epoch 788/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9706 - accuracy: 0.5312 - val_loss: 2.7818 - val_accuracy: 0.1875\n",
"Epoch 789/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.0425 - accuracy: 0.4375 - val_loss: 3.1461 - val_accuracy: 0.1562\n",
"Epoch 790/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.9130 - accuracy: 0.4688 - val_loss: 2.9374 - val_accuracy: 0.1562\n",
"Epoch 791/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7942 - accuracy: 0.5938 - val_loss: 2.8489 - val_accuracy: 0.1562\n",
"Epoch 792/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8804 - accuracy: 0.3750 - val_loss: 2.8770 - val_accuracy: 0.1562\n",
"Epoch 793/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.1562 - accuracy: 0.5312 - val_loss: 2.7855 - val_accuracy: 0.1562\n",
"Epoch 794/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8290 - accuracy: 0.5312 - val_loss: 2.9744 - val_accuracy: 0.1250\n",
"Epoch 795/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8148 - accuracy: 0.5000 - val_loss: 2.8382 - val_accuracy: 0.1562\n",
"Epoch 796/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8024 - accuracy: 0.4688 - val_loss: 2.8394 - val_accuracy: 0.1562\n",
"Epoch 797/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8596 - accuracy: 0.3438 - val_loss: 2.9270 - val_accuracy: 0.1562\n",
"Epoch 798/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7750 - accuracy: 0.4688 - val_loss: 2.9869 - val_accuracy: 0.1250\n",
"Epoch 799/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7571 - accuracy: 0.5312 - val_loss: 2.8990 - val_accuracy: 0.1562\n",
"Epoch 800/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8130 - accuracy: 0.5938 - val_loss: 2.9753 - val_accuracy: 0.1562\n",
"Epoch 801/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8421 - accuracy: 0.3750 - val_loss: 2.7781 - val_accuracy: 0.1875\n",
"Epoch 802/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7885 - accuracy: 0.5000 - val_loss: 2.9333 - val_accuracy: 0.1250\n",
"Epoch 803/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8957 - accuracy: 0.5000 - val_loss: 2.9483 - val_accuracy: 0.1562\n",
"Epoch 804/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7731 - accuracy: 0.5625 - val_loss: 2.9269 - val_accuracy: 0.1875\n",
"Epoch 805/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7620 - accuracy: 0.5625 - val_loss: 3.1274 - val_accuracy: 0.1250\n",
"Epoch 806/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8663 - accuracy: 0.4062 - val_loss: 2.9959 - val_accuracy: 0.1875\n",
"Epoch 807/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7899 - accuracy: 0.5312 - val_loss: 2.9886 - val_accuracy: 0.1875\n",
"Epoch 808/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8801 - accuracy: 0.3750 - val_loss: 3.0072 - val_accuracy: 0.1562\n",
"Epoch 809/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9040 - accuracy: 0.4062 - val_loss: 3.0952 - val_accuracy: 0.1562\n",
"Epoch 810/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7843 - accuracy: 0.5000 - val_loss: 2.9762 - val_accuracy: 0.1562\n",
"Epoch 811/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7359 - accuracy: 0.5938 - val_loss: 3.0529 - val_accuracy: 0.1250\n",
"Epoch 812/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9236 - accuracy: 0.5312 - val_loss: 3.0109 - val_accuracy: 0.1562\n",
"Epoch 813/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8669 - accuracy: 0.4688 - val_loss: 3.0887 - val_accuracy: 0.1562\n",
"Epoch 814/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8416 - accuracy: 0.4062 - val_loss: 3.0022 - val_accuracy: 0.1562\n",
"Epoch 815/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8673 - accuracy: 0.5938 - val_loss: 3.0091 - val_accuracy: 0.1562\n",
"Epoch 816/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8200 - accuracy: 0.5312 - val_loss: 3.1814 - val_accuracy: 0.1562\n",
"Epoch 817/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8783 - accuracy: 0.4062 - val_loss: 2.9681 - val_accuracy: 0.1875\n",
"Epoch 818/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8417 - accuracy: 0.5000 - val_loss: 2.9494 - val_accuracy: 0.1875\n",
"Epoch 819/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7825 - accuracy: 0.5625 - val_loss: 2.9721 - val_accuracy: 0.1562\n",
"Epoch 820/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8487 - accuracy: 0.5625 - val_loss: 3.1418 - val_accuracy: 0.1562\n",
"Epoch 821/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8068 - accuracy: 0.5938 - val_loss: 2.9819 - val_accuracy: 0.1875\n",
"Epoch 822/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8366 - accuracy: 0.5312 - val_loss: 3.0862 - val_accuracy: 0.1562\n",
"Epoch 823/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8198 - accuracy: 0.4688 - val_loss: 3.0033 - val_accuracy: 0.1562\n",
"Epoch 824/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7261 - accuracy: 0.5312 - val_loss: 3.0152 - val_accuracy: 0.1875\n",
"Epoch 825/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7902 - accuracy: 0.6250 - val_loss: 3.0421 - val_accuracy: 0.1562\n",
"Epoch 826/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7897 - accuracy: 0.4375 - val_loss: 3.0315 - val_accuracy: 0.1875\n",
"Epoch 827/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8635 - accuracy: 0.4375 - val_loss: 3.0461 - val_accuracy: 0.1562\n",
"Epoch 828/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.9140 - accuracy: 0.4375 - val_loss: 3.2285 - val_accuracy: 0.2188\n",
"Epoch 829/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7432 - accuracy: 0.5000 - val_loss: 3.0411 - val_accuracy: 0.1875\n",
"Epoch 830/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8817 - accuracy: 0.4062 - val_loss: 3.0624 - val_accuracy: 0.1875\n",
"Epoch 831/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8123 - accuracy: 0.6250 - val_loss: 3.0545 - val_accuracy: 0.1875\n",
"Epoch 832/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6710 - accuracy: 0.7188 - val_loss: 3.1130 - val_accuracy: 0.1875\n",
"Epoch 833/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7541 - accuracy: 0.5312 - val_loss: 3.0349 - val_accuracy: 0.1875\n",
"Epoch 834/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8151 - accuracy: 0.4688 - val_loss: 3.1335 - val_accuracy: 0.1875\n",
"Epoch 835/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7954 - accuracy: 0.5625 - val_loss: 3.1315 - val_accuracy: 0.1875\n",
"Epoch 836/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8167 - accuracy: 0.5312 - val_loss: 3.1444 - val_accuracy: 0.1875\n",
"Epoch 837/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8249 - accuracy: 0.5938 - val_loss: 3.1004 - val_accuracy: 0.1875\n",
"Epoch 838/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7866 - accuracy: 0.4375 - val_loss: 3.1109 - val_accuracy: 0.1875\n",
"Epoch 839/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9673 - accuracy: 0.5625 - val_loss: 2.9645 - val_accuracy: 0.1875\n",
"Epoch 840/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8949 - accuracy: 0.3750 - val_loss: 3.3008 - val_accuracy: 0.1562\n",
"Epoch 841/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7371 - accuracy: 0.5938 - val_loss: 2.9697 - val_accuracy: 0.1875\n",
"Epoch 842/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8571 - accuracy: 0.5312 - val_loss: 2.9883 - val_accuracy: 0.1875\n",
"Epoch 843/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7261 - accuracy: 0.5938 - val_loss: 3.0326 - val_accuracy: 0.1875\n",
"Epoch 844/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7481 - accuracy: 0.5938 - val_loss: 3.0799 - val_accuracy: 0.1875\n",
"Epoch 845/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.0310 - accuracy: 0.4062 - val_loss: 3.3962 - val_accuracy: 0.1562\n",
"Epoch 846/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8305 - accuracy: 0.4062 - val_loss: 2.9467 - val_accuracy: 0.1875\n",
"Epoch 847/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7416 - accuracy: 0.5938 - val_loss: 3.2946 - val_accuracy: 0.1875\n",
"Epoch 848/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7644 - accuracy: 0.5625 - val_loss: 3.2133 - val_accuracy: 0.1562\n",
"Epoch 849/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8092 - accuracy: 0.4688 - val_loss: 3.1471 - val_accuracy: 0.1875\n",
"Epoch 850/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0997 - accuracy: 0.4688 - val_loss: 3.4578 - val_accuracy: 0.1562\n",
"Epoch 851/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8481 - accuracy: 0.5312 - val_loss: 3.1102 - val_accuracy: 0.1875\n",
"Epoch 852/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8048 - accuracy: 0.5312 - val_loss: 3.2090 - val_accuracy: 0.1562\n",
"Epoch 853/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7345 - accuracy: 0.5938 - val_loss: 3.2273 - val_accuracy: 0.1562\n",
"Epoch 854/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8452 - accuracy: 0.5312 - val_loss: 3.2703 - val_accuracy: 0.1562\n",
"Epoch 855/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7268 - accuracy: 0.5625 - val_loss: 3.2717 - val_accuracy: 0.1562\n",
"Epoch 856/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6427 - accuracy: 0.5938 - val_loss: 3.1381 - val_accuracy: 0.1562\n",
"Epoch 857/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6582 - accuracy: 0.4375 - val_loss: 3.2294 - val_accuracy: 0.1562\n",
"Epoch 858/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6450 - accuracy: 0.6875 - val_loss: 3.2372 - val_accuracy: 0.1562\n",
"Epoch 859/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7368 - accuracy: 0.4375 - val_loss: 3.2057 - val_accuracy: 0.1562\n",
"Epoch 860/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8022 - accuracy: 0.4688 - val_loss: 3.1854 - val_accuracy: 0.1562\n",
"Epoch 861/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8559 - accuracy: 0.4375 - val_loss: 3.1702 - val_accuracy: 0.1562\n",
"Epoch 862/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8272 - accuracy: 0.5625 - val_loss: 3.1666 - val_accuracy: 0.1562\n",
"Epoch 863/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7995 - accuracy: 0.5312 - val_loss: 3.2459 - val_accuracy: 0.1562\n",
"Epoch 864/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7869 - accuracy: 0.5312 - val_loss: 3.0067 - val_accuracy: 0.1875\n",
"Epoch 865/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8975 - accuracy: 0.5000 - val_loss: 3.4244 - val_accuracy: 0.1562\n",
"Epoch 866/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7692 - accuracy: 0.5312 - val_loss: 3.1141 - val_accuracy: 0.1875\n",
"Epoch 867/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9137 - accuracy: 0.4375 - val_loss: 3.5703 - val_accuracy: 0.2188\n",
"Epoch 868/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7723 - accuracy: 0.5625 - val_loss: 3.1556 - val_accuracy: 0.2188\n",
"Epoch 869/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7098 - accuracy: 0.5000 - val_loss: 3.2587 - val_accuracy: 0.1875\n",
"Epoch 870/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7817 - accuracy: 0.5312 - val_loss: 3.3255 - val_accuracy: 0.1875\n",
"Epoch 871/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8481 - accuracy: 0.4062 - val_loss: 3.2157 - val_accuracy: 0.1875\n",
"Epoch 872/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8122 - accuracy: 0.3750 - val_loss: 3.2395 - val_accuracy: 0.1875\n",
"Epoch 873/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7825 - accuracy: 0.5000 - val_loss: 3.1774 - val_accuracy: 0.1875\n",
"Epoch 874/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8023 - accuracy: 0.5000 - val_loss: 3.1983 - val_accuracy: 0.1875\n",
"Epoch 875/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7858 - accuracy: 0.5625 - val_loss: 3.2192 - val_accuracy: 0.1875\n",
"Epoch 876/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7188 - accuracy: 0.4375 - val_loss: 3.1612 - val_accuracy: 0.1875\n",
"Epoch 877/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7341 - accuracy: 0.4688 - val_loss: 3.2751 - val_accuracy: 0.1562\n",
"Epoch 878/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7944 - accuracy: 0.5312 - val_loss: 3.1625 - val_accuracy: 0.1875\n",
"Epoch 879/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6915 - accuracy: 0.5312 - val_loss: 3.2465 - val_accuracy: 0.1562\n",
"Epoch 880/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8185 - accuracy: 0.5000 - val_loss: 3.3324 - val_accuracy: 0.1562\n",
"Epoch 881/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7569 - accuracy: 0.5625 - val_loss: 3.1722 - val_accuracy: 0.1562\n",
"Epoch 882/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7737 - accuracy: 0.4062 - val_loss: 3.2073 - val_accuracy: 0.1875\n",
"Epoch 883/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7645 - accuracy: 0.5312 - val_loss: 3.2255 - val_accuracy: 0.1875\n",
"Epoch 884/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8677 - accuracy: 0.5312 - val_loss: 3.4675 - val_accuracy: 0.1562\n",
"Epoch 885/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7902 - accuracy: 0.6250 - val_loss: 3.1615 - val_accuracy: 0.1875\n",
"Epoch 886/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7807 - accuracy: 0.5312 - val_loss: 3.2553 - val_accuracy: 0.1562\n",
"Epoch 887/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.8139 - accuracy: 0.5312 - val_loss: 3.2621 - val_accuracy: 0.1562\n",
"Epoch 888/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7690 - accuracy: 0.5312 - val_loss: 3.2142 - val_accuracy: 0.1562\n",
"Epoch 889/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7897 - accuracy: 0.5625 - val_loss: 3.3216 - val_accuracy: 0.1562\n",
"Epoch 890/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6592 - accuracy: 0.5312 - val_loss: 3.1876 - val_accuracy: 0.1875\n",
"Epoch 891/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7009 - accuracy: 0.5000 - val_loss: 3.2789 - val_accuracy: 0.1562\n",
"Epoch 892/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7971 - accuracy: 0.3438 - val_loss: 3.3427 - val_accuracy: 0.1875\n",
"Epoch 893/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7541 - accuracy: 0.4688 - val_loss: 3.0746 - val_accuracy: 0.1875\n",
"Epoch 894/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8146 - accuracy: 0.4688 - val_loss: 3.5398 - val_accuracy: 0.1562\n",
"Epoch 895/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7545 - accuracy: 0.3750 - val_loss: 2.9660 - val_accuracy: 0.1875\n",
"Epoch 896/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8303 - accuracy: 0.5312 - val_loss: 3.4601 - val_accuracy: 0.1562\n",
"Epoch 897/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8129 - accuracy: 0.5312 - val_loss: 3.1818 - val_accuracy: 0.1875\n",
"Epoch 898/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6566 - accuracy: 0.5938 - val_loss: 3.3151 - val_accuracy: 0.1875\n",
"Epoch 899/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7456 - accuracy: 0.4688 - val_loss: 3.1670 - val_accuracy: 0.1875\n",
"Epoch 900/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7832 - accuracy: 0.5000 - val_loss: 3.3606 - val_accuracy: 0.1875\n",
"Epoch 901/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5661 - accuracy: 0.6562 - val_loss: 3.1785 - val_accuracy: 0.1875\n",
"Epoch 902/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6661 - accuracy: 0.6562 - val_loss: 3.1629 - val_accuracy: 0.1875\n",
"Epoch 903/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8342 - accuracy: 0.4688 - val_loss: 3.2786 - val_accuracy: 0.1875\n",
"Epoch 904/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7644 - accuracy: 0.4688 - val_loss: 3.2044 - val_accuracy: 0.1875\n",
"Epoch 905/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7714 - accuracy: 0.5625 - val_loss: 3.1646 - val_accuracy: 0.2188\n",
"Epoch 906/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7045 - accuracy: 0.5625 - val_loss: 3.3455 - val_accuracy: 0.1875\n",
"Epoch 907/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6624 - accuracy: 0.6250 - val_loss: 3.1684 - val_accuracy: 0.2188\n",
"Epoch 908/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7426 - accuracy: 0.5312 - val_loss: 3.4008 - val_accuracy: 0.1875\n",
"Epoch 909/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6484 - accuracy: 0.5312 - val_loss: 3.2258 - val_accuracy: 0.2188\n",
"Epoch 910/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6878 - accuracy: 0.5625 - val_loss: 3.3062 - val_accuracy: 0.1875\n",
"Epoch 911/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8517 - accuracy: 0.5938 - val_loss: 3.2412 - val_accuracy: 0.1875\n",
"Epoch 912/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7249 - accuracy: 0.5000 - val_loss: 3.2881 - val_accuracy: 0.1875\n",
"Epoch 913/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8250 - accuracy: 0.4688 - val_loss: 3.2749 - val_accuracy: 0.1875\n",
"Epoch 914/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8578 - accuracy: 0.5312 - val_loss: 3.2517 - val_accuracy: 0.1875\n",
"Epoch 915/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6833 - accuracy: 0.5312 - val_loss: 3.1682 - val_accuracy: 0.1875\n",
"Epoch 916/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7103 - accuracy: 0.6250 - val_loss: 3.2350 - val_accuracy: 0.1875\n",
"Epoch 917/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8034 - accuracy: 0.5625 - val_loss: 3.2201 - val_accuracy: 0.1875\n",
"Epoch 918/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8257 - accuracy: 0.5000 - val_loss: 3.3320 - val_accuracy: 0.1875\n",
"Epoch 919/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7129 - accuracy: 0.5625 - val_loss: 3.1019 - val_accuracy: 0.2188\n",
"Epoch 920/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7193 - accuracy: 0.5312 - val_loss: 3.2462 - val_accuracy: 0.1562\n",
"Epoch 921/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7227 - accuracy: 0.5312 - val_loss: 3.1576 - val_accuracy: 0.1875\n",
"Epoch 922/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7732 - accuracy: 0.5312 - val_loss: 3.2869 - val_accuracy: 0.1875\n",
"Epoch 923/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7695 - accuracy: 0.5000 - val_loss: 3.1276 - val_accuracy: 0.1875\n",
"Epoch 924/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7760 - accuracy: 0.6250 - val_loss: 3.4888 - val_accuracy: 0.1562\n",
"Epoch 925/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8599 - accuracy: 0.3438 - val_loss: 3.0104 - val_accuracy: 0.1875\n",
"Epoch 926/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6823 - accuracy: 0.5000 - val_loss: 3.2303 - val_accuracy: 0.1875\n",
"Epoch 927/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6038 - accuracy: 0.6250 - val_loss: 3.1410 - val_accuracy: 0.1875\n",
"Epoch 928/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.8193 - accuracy: 0.4688 - val_loss: 3.3460 - val_accuracy: 0.1562\n",
"Epoch 929/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7420 - accuracy: 0.4688 - val_loss: 3.1600 - val_accuracy: 0.1875\n",
"Epoch 930/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7364 - accuracy: 0.5000 - val_loss: 3.2424 - val_accuracy: 0.1875\n",
"Epoch 931/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7254 - accuracy: 0.5938 - val_loss: 3.2324 - val_accuracy: 0.1875\n",
"Epoch 932/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7181 - accuracy: 0.4688 - val_loss: 3.1798 - val_accuracy: 0.1875\n",
"Epoch 933/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7478 - accuracy: 0.5000 - val_loss: 3.3343 - val_accuracy: 0.2188\n",
"Epoch 934/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7495 - accuracy: 0.5312 - val_loss: 3.1514 - val_accuracy: 0.1875\n",
"Epoch 935/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7669 - accuracy: 0.5000 - val_loss: 3.2764 - val_accuracy: 0.2188\n",
"Epoch 936/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7510 - accuracy: 0.4688 - val_loss: 3.2655 - val_accuracy: 0.1875\n",
"Epoch 937/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7205 - accuracy: 0.5312 - val_loss: 3.3386 - val_accuracy: 0.1562\n",
"Epoch 938/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6598 - accuracy: 0.6250 - val_loss: 3.2104 - val_accuracy: 0.1875\n",
"Epoch 939/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6739 - accuracy: 0.4688 - val_loss: 3.1878 - val_accuracy: 0.1875\n",
"Epoch 940/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.6924 - accuracy: 0.5938 - val_loss: 3.3064 - val_accuracy: 0.1562\n",
"Epoch 941/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7460 - accuracy: 0.5938 - val_loss: 3.2651 - val_accuracy: 0.1875\n",
"Epoch 942/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7617 - accuracy: 0.5000 - val_loss: 3.1856 - val_accuracy: 0.1875\n",
"Epoch 943/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.8325 - accuracy: 0.5312 - val_loss: 3.2670 - val_accuracy: 0.1875\n",
"Epoch 944/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6975 - accuracy: 0.4375 - val_loss: 3.3171 - val_accuracy: 0.1875\n",
"Epoch 945/5000\n",
"1/1 [==============================] - 0s 215ms/step - loss: 0.7544 - accuracy: 0.5312 - val_loss: 3.2190 - val_accuracy: 0.1875\n",
"Epoch 946/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.8171 - accuracy: 0.4375 - val_loss: 3.2559 - val_accuracy: 0.1875\n",
"Epoch 947/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.6632 - accuracy: 0.5312 - val_loss: 3.0873 - val_accuracy: 0.2188\n",
"Epoch 948/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7324 - accuracy: 0.6562 - val_loss: 3.3124 - val_accuracy: 0.1875\n",
"Epoch 949/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7797 - accuracy: 0.4688 - val_loss: 3.0070 - val_accuracy: 0.2188\n",
"Epoch 950/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.7036 - accuracy: 0.5938 - val_loss: 3.2256 - val_accuracy: 0.1562\n",
"Epoch 951/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.1268 - accuracy: 0.5000 - val_loss: 3.2649 - val_accuracy: 0.1562\n",
"Epoch 952/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.1010 - accuracy: 0.4062 - val_loss: 3.7777 - val_accuracy: 0.1562\n",
"Epoch 953/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.0427 - accuracy: 0.3750 - val_loss: 3.0936 - val_accuracy: 0.1875\n",
"Epoch 954/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8830 - accuracy: 0.3750 - val_loss: 3.5476 - val_accuracy: 0.1875\n",
"Epoch 955/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7624 - accuracy: 0.5000 - val_loss: 3.1613 - val_accuracy: 0.1875\n",
"Epoch 956/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7948 - accuracy: 0.4375 - val_loss: 3.3964 - val_accuracy: 0.1875\n",
"Epoch 957/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7225 - accuracy: 0.5312 - val_loss: 3.2440 - val_accuracy: 0.1875\n",
"Epoch 958/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7823 - accuracy: 0.5625 - val_loss: 3.3277 - val_accuracy: 0.1562\n",
"Epoch 959/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.7434 - accuracy: 0.5312 - val_loss: 3.2400 - val_accuracy: 0.1562\n",
"Epoch 960/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7084 - accuracy: 0.6250 - val_loss: 3.3604 - val_accuracy: 0.1562\n",
"Epoch 961/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7195 - accuracy: 0.5312 - val_loss: 3.1895 - val_accuracy: 0.1562\n",
"Epoch 962/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 1.0160 - accuracy: 0.3750 - val_loss: 3.2714 - val_accuracy: 0.1875\n",
"Epoch 963/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6387 - accuracy: 0.6250 - val_loss: 3.4668 - val_accuracy: 0.2188\n",
"Epoch 964/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6212 - accuracy: 0.5312 - val_loss: 3.2806 - val_accuracy: 0.1875\n",
"Epoch 965/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7069 - accuracy: 0.5938 - val_loss: 3.3096 - val_accuracy: 0.1875\n",
"Epoch 966/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7409 - accuracy: 0.5312 - val_loss: 3.1953 - val_accuracy: 0.1875\n",
"Epoch 967/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7163 - accuracy: 0.7188 - val_loss: 3.2388 - val_accuracy: 0.1875\n",
"Epoch 968/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7712 - accuracy: 0.5000 - val_loss: 3.3590 - val_accuracy: 0.1562\n",
"Epoch 969/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8510 - accuracy: 0.4688 - val_loss: 3.3379 - val_accuracy: 0.1875\n",
"Epoch 970/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7469 - accuracy: 0.5625 - val_loss: 3.2258 - val_accuracy: 0.1875\n",
"Epoch 971/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7926 - accuracy: 0.5312 - val_loss: 3.3112 - val_accuracy: 0.1875\n",
"Epoch 972/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7787 - accuracy: 0.5625 - val_loss: 3.4804 - val_accuracy: 0.2500\n",
"Epoch 973/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7186 - accuracy: 0.5938 - val_loss: 3.2125 - val_accuracy: 0.1875\n",
"Epoch 974/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7547 - accuracy: 0.5625 - val_loss: 3.4173 - val_accuracy: 0.2188\n",
"Epoch 975/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7160 - accuracy: 0.5938 - val_loss: 3.2907 - val_accuracy: 0.1875\n",
"Epoch 976/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.8093 - accuracy: 0.5000 - val_loss: 3.3487 - val_accuracy: 0.2188\n",
"Epoch 977/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.7708 - accuracy: 0.4688 - val_loss: 3.2482 - val_accuracy: 0.2188\n",
"Epoch 978/5000\n",
"1/1 [==============================] - 0s 213ms/step - loss: 0.6800 - accuracy: 0.5625 - val_loss: 3.2492 - val_accuracy: 0.1875\n",
"Epoch 979/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6666 - accuracy: 0.6562 - val_loss: 3.2747 - val_accuracy: 0.1875\n",
"Epoch 980/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7984 - accuracy: 0.5625 - val_loss: 3.4088 - val_accuracy: 0.1875\n",
"Epoch 981/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.8122 - accuracy: 0.5000 - val_loss: 3.4046 - val_accuracy: 0.1875\n",
"Epoch 982/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.7097 - accuracy: 0.5312 - val_loss: 3.3738 - val_accuracy: 0.1875\n",
"Epoch 983/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.7445 - accuracy: 0.6250 - val_loss: 3.3268 - val_accuracy: 0.1875\n",
"Epoch 984/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.8159 - accuracy: 0.5000 - val_loss: 3.4009 - val_accuracy: 0.1875\n",
"Epoch 985/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6504 - accuracy: 0.6250 - val_loss: 3.4593 - val_accuracy: 0.1875\n",
"Epoch 986/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7276 - accuracy: 0.6875 - val_loss: 3.2048 - val_accuracy: 0.2188\n",
"Epoch 987/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8798 - accuracy: 0.4062 - val_loss: 3.7516 - val_accuracy: 0.1562\n",
"Epoch 988/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8580 - accuracy: 0.4688 - val_loss: 3.1108 - val_accuracy: 0.1875\n",
"Epoch 989/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8875 - accuracy: 0.3438 - val_loss: 3.6263 - val_accuracy: 0.1562\n",
"Epoch 990/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8146 - accuracy: 0.4375 - val_loss: 3.3311 - val_accuracy: 0.1562\n",
"Epoch 991/5000\n",
"1/1 [==============================] - 0s 368ms/step - loss: 0.6742 - accuracy: 0.6250 - val_loss: 3.2703 - val_accuracy: 0.1875\n",
"Epoch 992/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7031 - accuracy: 0.6562 - val_loss: 3.3578 - val_accuracy: 0.1562\n",
"Epoch 993/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8470 - accuracy: 0.5312 - val_loss: 3.3431 - val_accuracy: 0.1562\n",
"Epoch 994/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7067 - accuracy: 0.5938 - val_loss: 3.3637 - val_accuracy: 0.1562\n",
"Epoch 995/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7288 - accuracy: 0.5938 - val_loss: 3.2358 - val_accuracy: 0.1875\n",
"Epoch 996/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7927 - accuracy: 0.5312 - val_loss: 3.4235 - val_accuracy: 0.1562\n",
"Epoch 997/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6376 - accuracy: 0.6562 - val_loss: 3.3455 - val_accuracy: 0.1562\n",
"Epoch 998/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.7883 - accuracy: 0.4688 - val_loss: 3.4118 - val_accuracy: 0.1562\n",
"Epoch 999/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8562 - accuracy: 0.5000 - val_loss: 3.1290 - val_accuracy: 0.1562\n",
"Epoch 1000/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8684 - accuracy: 0.3750 - val_loss: 3.5574 - val_accuracy: 0.1875\n",
"Epoch 1001/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7522 - accuracy: 0.5000 - val_loss: 3.2262 - val_accuracy: 0.1875\n",
"Epoch 1002/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7124 - accuracy: 0.4688 - val_loss: 3.3818 - val_accuracy: 0.1562\n",
"Epoch 1003/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6662 - accuracy: 0.5312 - val_loss: 3.3668 - val_accuracy: 0.1562\n",
"Epoch 1004/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7350 - accuracy: 0.5312 - val_loss: 3.3257 - val_accuracy: 0.1562\n",
"Epoch 1005/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6685 - accuracy: 0.4688 - val_loss: 3.2362 - val_accuracy: 0.1562\n",
"Epoch 1006/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7852 - accuracy: 0.5938 - val_loss: 4.1765 - val_accuracy: 0.1562\n",
"Epoch 1007/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8263 - accuracy: 0.5000 - val_loss: 3.1923 - val_accuracy: 0.1875\n",
"Epoch 1008/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7909 - accuracy: 0.5312 - val_loss: 3.5744 - val_accuracy: 0.1562\n",
"Epoch 1009/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7409 - accuracy: 0.5000 - val_loss: 3.2415 - val_accuracy: 0.1875\n",
"Epoch 1010/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9561 - accuracy: 0.3750 - val_loss: 3.8100 - val_accuracy: 0.1562\n",
"Epoch 1011/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9312 - accuracy: 0.3750 - val_loss: 3.0881 - val_accuracy: 0.2188\n",
"Epoch 1012/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7911 - accuracy: 0.5312 - val_loss: 3.4816 - val_accuracy: 0.1562\n",
"Epoch 1013/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7007 - accuracy: 0.5000 - val_loss: 3.3593 - val_accuracy: 0.1875\n",
"Epoch 1014/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6523 - accuracy: 0.5938 - val_loss: 3.3273 - val_accuracy: 0.1875\n",
"Epoch 1015/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7964 - accuracy: 0.5312 - val_loss: 3.8315 - val_accuracy: 0.1562\n",
"Epoch 1016/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7366 - accuracy: 0.5312 - val_loss: 3.1510 - val_accuracy: 0.2188\n",
"Epoch 1017/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8478 - accuracy: 0.5625 - val_loss: 3.7197 - val_accuracy: 0.0938\n",
"Epoch 1018/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7652 - accuracy: 0.5312 - val_loss: 3.1157 - val_accuracy: 0.1875\n",
"Epoch 1019/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8445 - accuracy: 0.5000 - val_loss: 3.5870 - val_accuracy: 0.1875\n",
"Epoch 1020/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7444 - accuracy: 0.5000 - val_loss: 3.2822 - val_accuracy: 0.1562\n",
"Epoch 1021/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5840 - accuracy: 0.5625 - val_loss: 3.4280 - val_accuracy: 0.1562\n",
"Epoch 1022/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8324 - accuracy: 0.5000 - val_loss: 3.4493 - val_accuracy: 0.1562\n",
"Epoch 1023/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7890 - accuracy: 0.5625 - val_loss: 3.2354 - val_accuracy: 0.1875\n",
"Epoch 1024/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6845 - accuracy: 0.6250 - val_loss: 3.4040 - val_accuracy: 0.1562\n",
"Epoch 1025/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7349 - accuracy: 0.5312 - val_loss: 3.5417 - val_accuracy: 0.1562\n",
"Epoch 1026/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6264 - accuracy: 0.5938 - val_loss: 3.3942 - val_accuracy: 0.1875\n",
"Epoch 1027/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7037 - accuracy: 0.6250 - val_loss: 3.3109 - val_accuracy: 0.1562\n",
"Epoch 1028/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7322 - accuracy: 0.6250 - val_loss: 3.7607 - val_accuracy: 0.1250\n",
"Epoch 1029/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7977 - accuracy: 0.5312 - val_loss: 3.2110 - val_accuracy: 0.1875\n",
"Epoch 1030/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8484 - accuracy: 0.4688 - val_loss: 3.4843 - val_accuracy: 0.1562\n",
"Epoch 1031/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7766 - accuracy: 0.4375 - val_loss: 3.3506 - val_accuracy: 0.1875\n",
"Epoch 1032/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7742 - accuracy: 0.5625 - val_loss: 3.2945 - val_accuracy: 0.1875\n",
"Epoch 1033/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7140 - accuracy: 0.6250 - val_loss: 3.5177 - val_accuracy: 0.1562\n",
"Epoch 1034/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8429 - accuracy: 0.5312 - val_loss: 3.2629 - val_accuracy: 0.1875\n",
"Epoch 1035/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7895 - accuracy: 0.5625 - val_loss: 3.5533 - val_accuracy: 0.1562\n",
"Epoch 1036/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7576 - accuracy: 0.5000 - val_loss: 3.2612 - val_accuracy: 0.1875\n",
"Epoch 1037/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8108 - accuracy: 0.4062 - val_loss: 3.4564 - val_accuracy: 0.1562\n",
"Epoch 1038/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.8026 - accuracy: 0.5625 - val_loss: 3.3207 - val_accuracy: 0.1875\n",
"Epoch 1039/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7644 - accuracy: 0.5625 - val_loss: 3.4760 - val_accuracy: 0.1562\n",
"Epoch 1040/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7641 - accuracy: 0.4062 - val_loss: 3.3670 - val_accuracy: 0.2188\n",
"Epoch 1041/5000\n",
"1/1 [==============================] - 0s 230ms/step - loss: 0.9107 - accuracy: 0.4688 - val_loss: 3.5589 - val_accuracy: 0.1562\n",
"Epoch 1042/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.8395 - accuracy: 0.4062 - val_loss: 3.3290 - val_accuracy: 0.1875\n",
"Epoch 1043/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8203 - accuracy: 0.4062 - val_loss: 3.3130 - val_accuracy: 0.1562\n",
"Epoch 1044/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6786 - accuracy: 0.5312 - val_loss: 3.4013 - val_accuracy: 0.1562\n",
"Epoch 1045/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.7565 - accuracy: 0.4688 - val_loss: 3.3539 - val_accuracy: 0.1562\n",
"Epoch 1046/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7518 - accuracy: 0.5312 - val_loss: 3.4322 - val_accuracy: 0.1562\n",
"Epoch 1047/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6942 - accuracy: 0.4688 - val_loss: 3.3734 - val_accuracy: 0.1562\n",
"Epoch 1048/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8536 - accuracy: 0.4688 - val_loss: 3.5029 - val_accuracy: 0.1562\n",
"Epoch 1049/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7036 - accuracy: 0.5312 - val_loss: 3.2455 - val_accuracy: 0.1875\n",
"Epoch 1050/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8241 - accuracy: 0.5625 - val_loss: 3.5927 - val_accuracy: 0.1562\n",
"Epoch 1051/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7220 - accuracy: 0.5938 - val_loss: 3.2976 - val_accuracy: 0.1875\n",
"Epoch 1052/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6606 - accuracy: 0.5625 - val_loss: 3.5514 - val_accuracy: 0.1562\n",
"Epoch 1053/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7392 - accuracy: 0.5938 - val_loss: 3.2097 - val_accuracy: 0.1875\n",
"Epoch 1054/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8585 - accuracy: 0.4688 - val_loss: 3.3668 - val_accuracy: 0.1562\n",
"Epoch 1055/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7671 - accuracy: 0.5625 - val_loss: 3.8467 - val_accuracy: 0.1562\n",
"Epoch 1056/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9210 - accuracy: 0.4062 - val_loss: 2.9927 - val_accuracy: 0.1562\n",
"Epoch 1057/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.0087 - accuracy: 0.3438 - val_loss: 4.2250 - val_accuracy: 0.0938\n",
"Epoch 1058/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.7788 - accuracy: 0.3125 - val_loss: 10.8302 - val_accuracy: 0.0938\n",
"Epoch 1059/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 16.5579 - accuracy: 0.0312 - val_loss: 9.8761 - val_accuracy: 0.0312\n",
"Epoch 1060/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 12.4522 - accuracy: 0.0938 - val_loss: 2.3764 - val_accuracy: 0.2812\n",
"Epoch 1061/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.0665 - accuracy: 0.4062 - val_loss: 3.1263 - val_accuracy: 0.1875\n",
"Epoch 1062/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.2799 - accuracy: 0.3125 - val_loss: 2.7976 - val_accuracy: 0.1250\n",
"Epoch 1063/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0867 - accuracy: 0.4062 - val_loss: 2.7931 - val_accuracy: 0.1250\n",
"Epoch 1064/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.0679 - accuracy: 0.3750 - val_loss: 2.7642 - val_accuracy: 0.0938\n",
"Epoch 1065/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9621 - accuracy: 0.6250 - val_loss: 2.7291 - val_accuracy: 0.1250\n",
"Epoch 1066/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.9902 - accuracy: 0.5312 - val_loss: 2.7349 - val_accuracy: 0.1250\n",
"Epoch 1067/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9700 - accuracy: 0.4062 - val_loss: 2.7648 - val_accuracy: 0.1250\n",
"Epoch 1068/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.0974 - accuracy: 0.4688 - val_loss: 2.7438 - val_accuracy: 0.0938\n",
"Epoch 1069/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9846 - accuracy: 0.4375 - val_loss: 2.7676 - val_accuracy: 0.1250\n",
"Epoch 1070/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.9861 - accuracy: 0.4062 - val_loss: 2.7424 - val_accuracy: 0.1250\n",
"Epoch 1071/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.9604 - accuracy: 0.4688 - val_loss: 2.7561 - val_accuracy: 0.1875\n",
"Epoch 1072/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 1.1603 - accuracy: 0.4688 - val_loss: 2.8383 - val_accuracy: 0.1562\n",
"Epoch 1073/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.8991 - accuracy: 0.5312 - val_loss: 2.7247 - val_accuracy: 0.1250\n",
"Epoch 1074/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9560 - accuracy: 0.4688 - val_loss: 2.8007 - val_accuracy: 0.1562\n",
"Epoch 1075/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8882 - accuracy: 0.4688 - val_loss: 2.7655 - val_accuracy: 0.1875\n",
"Epoch 1076/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8660 - accuracy: 0.5312 - val_loss: 2.7752 - val_accuracy: 0.1562\n",
"Epoch 1077/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.0955 - accuracy: 0.4688 - val_loss: 2.8200 - val_accuracy: 0.1875\n",
"Epoch 1078/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.9407 - accuracy: 0.5625 - val_loss: 2.8576 - val_accuracy: 0.1562\n",
"Epoch 1079/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8906 - accuracy: 0.5938 - val_loss: 2.8172 - val_accuracy: 0.1562\n",
"Epoch 1080/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8078 - accuracy: 0.5625 - val_loss: 2.7692 - val_accuracy: 0.1562\n",
"Epoch 1081/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8360 - accuracy: 0.5312 - val_loss: 2.8245 - val_accuracy: 0.1562\n",
"Epoch 1082/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8757 - accuracy: 0.4688 - val_loss: 2.7673 - val_accuracy: 0.1562\n",
"Epoch 1083/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8580 - accuracy: 0.5312 - val_loss: 2.7713 - val_accuracy: 0.1562\n",
"Epoch 1084/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8875 - accuracy: 0.5000 - val_loss: 2.8167 - val_accuracy: 0.1562\n",
"Epoch 1085/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8983 - accuracy: 0.5625 - val_loss: 2.8345 - val_accuracy: 0.1562\n",
"Epoch 1086/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7744 - accuracy: 0.5625 - val_loss: 2.8413 - val_accuracy: 0.1562\n",
"Epoch 1087/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9417 - accuracy: 0.4062 - val_loss: 2.8362 - val_accuracy: 0.1562\n",
"Epoch 1088/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9206 - accuracy: 0.5000 - val_loss: 2.8174 - val_accuracy: 0.1562\n",
"Epoch 1089/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8345 - accuracy: 0.6250 - val_loss: 2.8482 - val_accuracy: 0.1562\n",
"Epoch 1090/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7730 - accuracy: 0.5312 - val_loss: 2.8133 - val_accuracy: 0.1562\n",
"Epoch 1091/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8033 - accuracy: 0.6562 - val_loss: 2.8213 - val_accuracy: 0.1875\n",
"Epoch 1092/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9439 - accuracy: 0.4688 - val_loss: 2.8099 - val_accuracy: 0.1562\n",
"Epoch 1093/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8988 - accuracy: 0.4688 - val_loss: 2.8340 - val_accuracy: 0.1562\n",
"Epoch 1094/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8948 - accuracy: 0.4375 - val_loss: 2.9162 - val_accuracy: 0.1875\n",
"Epoch 1095/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8894 - accuracy: 0.5312 - val_loss: 2.8169 - val_accuracy: 0.1250\n",
"Epoch 1096/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8686 - accuracy: 0.5625 - val_loss: 2.8936 - val_accuracy: 0.1562\n",
"Epoch 1097/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8865 - accuracy: 0.4688 - val_loss: 2.8255 - val_accuracy: 0.1562\n",
"Epoch 1098/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8351 - accuracy: 0.4688 - val_loss: 2.8219 - val_accuracy: 0.1875\n",
"Epoch 1099/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9030 - accuracy: 0.4375 - val_loss: 2.8529 - val_accuracy: 0.1562\n",
"Epoch 1100/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8814 - accuracy: 0.5938 - val_loss: 2.9743 - val_accuracy: 0.1562\n",
"Epoch 1101/5000\n",
"1/1 [==============================] - 0s 150ms/step - loss: 0.8322 - accuracy: 0.5938 - val_loss: 3.0090 - val_accuracy: 0.1875\n",
"Epoch 1102/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8745 - accuracy: 0.5938 - val_loss: 2.8859 - val_accuracy: 0.1562\n",
"Epoch 1103/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7803 - accuracy: 0.5938 - val_loss: 2.8622 - val_accuracy: 0.1562\n",
"Epoch 1104/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7453 - accuracy: 0.5938 - val_loss: 2.8805 - val_accuracy: 0.1875\n",
"Epoch 1105/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8105 - accuracy: 0.5000 - val_loss: 2.9161 - val_accuracy: 0.1875\n",
"Epoch 1106/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7819 - accuracy: 0.5938 - val_loss: 2.9816 - val_accuracy: 0.1875\n",
"Epoch 1107/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8186 - accuracy: 0.5312 - val_loss: 2.9195 - val_accuracy: 0.1562\n",
"Epoch 1108/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8647 - accuracy: 0.5312 - val_loss: 2.9765 - val_accuracy: 0.1875\n",
"Epoch 1109/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8669 - accuracy: 0.5000 - val_loss: 2.9745 - val_accuracy: 0.1562\n",
"Epoch 1110/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8215 - accuracy: 0.5000 - val_loss: 3.0035 - val_accuracy: 0.1562\n",
"Epoch 1111/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8711 - accuracy: 0.5000 - val_loss: 2.9197 - val_accuracy: 0.1562\n",
"Epoch 1112/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8420 - accuracy: 0.4688 - val_loss: 2.9999 - val_accuracy: 0.1875\n",
"Epoch 1113/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.9239 - accuracy: 0.4688 - val_loss: 2.9391 - val_accuracy: 0.1875\n",
"Epoch 1114/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8461 - accuracy: 0.5312 - val_loss: 2.9078 - val_accuracy: 0.1562\n",
"Epoch 1115/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7953 - accuracy: 0.5312 - val_loss: 2.9344 - val_accuracy: 0.1562\n",
"Epoch 1116/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8992 - accuracy: 0.5000 - val_loss: 2.9023 - val_accuracy: 0.1562\n",
"Epoch 1117/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7565 - accuracy: 0.5312 - val_loss: 3.0018 - val_accuracy: 0.1562\n",
"Epoch 1118/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7386 - accuracy: 0.5938 - val_loss: 3.0137 - val_accuracy: 0.1562\n",
"Epoch 1119/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7928 - accuracy: 0.5312 - val_loss: 2.9702 - val_accuracy: 0.1562\n",
"Epoch 1120/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8043 - accuracy: 0.5000 - val_loss: 3.0800 - val_accuracy: 0.1875\n",
"Epoch 1121/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8281 - accuracy: 0.4375 - val_loss: 2.9577 - val_accuracy: 0.1875\n",
"Epoch 1122/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8737 - accuracy: 0.4688 - val_loss: 2.9939 - val_accuracy: 0.1562\n",
"Epoch 1123/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7391 - accuracy: 0.5625 - val_loss: 3.0064 - val_accuracy: 0.1875\n",
"Epoch 1124/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6595 - accuracy: 0.6250 - val_loss: 2.9180 - val_accuracy: 0.1562\n",
"Epoch 1125/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7816 - accuracy: 0.4688 - val_loss: 2.9862 - val_accuracy: 0.1875\n",
"Epoch 1126/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7634 - accuracy: 0.5625 - val_loss: 2.9871 - val_accuracy: 0.1875\n",
"Epoch 1127/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7760 - accuracy: 0.5312 - val_loss: 2.9520 - val_accuracy: 0.1562\n",
"Epoch 1128/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6542 - accuracy: 0.6250 - val_loss: 3.0087 - val_accuracy: 0.1875\n",
"Epoch 1129/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7049 - accuracy: 0.5625 - val_loss: 3.0822 - val_accuracy: 0.1875\n",
"Epoch 1130/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6976 - accuracy: 0.5938 - val_loss: 3.0109 - val_accuracy: 0.1562\n",
"Epoch 1131/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7079 - accuracy: 0.5938 - val_loss: 2.9670 - val_accuracy: 0.1562\n",
"Epoch 1132/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7693 - accuracy: 0.5000 - val_loss: 3.1104 - val_accuracy: 0.1875\n",
"Epoch 1133/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7214 - accuracy: 0.5625 - val_loss: 3.0650 - val_accuracy: 0.1875\n",
"Epoch 1134/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6887 - accuracy: 0.6562 - val_loss: 3.0626 - val_accuracy: 0.1875\n",
"Epoch 1135/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7393 - accuracy: 0.5000 - val_loss: 3.0545 - val_accuracy: 0.1562\n",
"Epoch 1136/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7753 - accuracy: 0.5938 - val_loss: 3.0438 - val_accuracy: 0.1562\n",
"Epoch 1137/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7575 - accuracy: 0.5938 - val_loss: 3.0751 - val_accuracy: 0.1562\n",
"Epoch 1138/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7336 - accuracy: 0.6250 - val_loss: 3.1349 - val_accuracy: 0.1875\n",
"Epoch 1139/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7812 - accuracy: 0.6250 - val_loss: 3.0897 - val_accuracy: 0.1875\n",
"Epoch 1140/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7493 - accuracy: 0.4375 - val_loss: 3.1535 - val_accuracy: 0.2188\n",
"Epoch 1141/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7857 - accuracy: 0.4375 - val_loss: 3.0870 - val_accuracy: 0.1875\n",
"Epoch 1142/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8543 - accuracy: 0.5000 - val_loss: 3.1855 - val_accuracy: 0.2188\n",
"Epoch 1143/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7064 - accuracy: 0.6562 - val_loss: 3.1186 - val_accuracy: 0.2188\n",
"Epoch 1144/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6899 - accuracy: 0.6562 - val_loss: 3.0439 - val_accuracy: 0.2188\n",
"Epoch 1145/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8507 - accuracy: 0.4375 - val_loss: 3.1647 - val_accuracy: 0.2188\n",
"Epoch 1146/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7507 - accuracy: 0.5312 - val_loss: 3.1076 - val_accuracy: 0.1875\n",
"Epoch 1147/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7766 - accuracy: 0.4375 - val_loss: 3.1048 - val_accuracy: 0.1875\n",
"Epoch 1148/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7742 - accuracy: 0.5625 - val_loss: 3.1432 - val_accuracy: 0.1875\n",
"Epoch 1149/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7507 - accuracy: 0.4688 - val_loss: 3.1059 - val_accuracy: 0.1875\n",
"Epoch 1150/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7501 - accuracy: 0.4688 - val_loss: 3.1078 - val_accuracy: 0.1875\n",
"Epoch 1151/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7659 - accuracy: 0.5312 - val_loss: 3.0360 - val_accuracy: 0.1875\n",
"Epoch 1152/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7779 - accuracy: 0.5625 - val_loss: 3.1490 - val_accuracy: 0.1875\n",
"Epoch 1153/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8275 - accuracy: 0.4688 - val_loss: 3.0624 - val_accuracy: 0.1875\n",
"Epoch 1154/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7662 - accuracy: 0.5625 - val_loss: 3.1276 - val_accuracy: 0.1875\n",
"Epoch 1155/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7393 - accuracy: 0.6875 - val_loss: 3.0740 - val_accuracy: 0.1875\n",
"Epoch 1156/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8445 - accuracy: 0.4375 - val_loss: 3.1803 - val_accuracy: 0.1875\n",
"Epoch 1157/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8093 - accuracy: 0.5312 - val_loss: 3.1203 - val_accuracy: 0.1875\n",
"Epoch 1158/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.9005 - accuracy: 0.4375 - val_loss: 3.1570 - val_accuracy: 0.1875\n",
"Epoch 1159/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6392 - accuracy: 0.5625 - val_loss: 3.1781 - val_accuracy: 0.1875\n",
"Epoch 1160/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6924 - accuracy: 0.5938 - val_loss: 3.0905 - val_accuracy: 0.1875\n",
"Epoch 1161/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7184 - accuracy: 0.5000 - val_loss: 3.1972 - val_accuracy: 0.2188\n",
"Epoch 1162/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6796 - accuracy: 0.5625 - val_loss: 3.0440 - val_accuracy: 0.1875\n",
"Epoch 1163/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6698 - accuracy: 0.6250 - val_loss: 3.1650 - val_accuracy: 0.1875\n",
"Epoch 1164/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7189 - accuracy: 0.7188 - val_loss: 3.1724 - val_accuracy: 0.1875\n",
"Epoch 1165/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6753 - accuracy: 0.5625 - val_loss: 3.0848 - val_accuracy: 0.1875\n",
"Epoch 1166/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.7448 - accuracy: 0.5000 - val_loss: 3.1092 - val_accuracy: 0.1875\n",
"Epoch 1167/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6665 - accuracy: 0.5312 - val_loss: 3.1264 - val_accuracy: 0.1875\n",
"Epoch 1168/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8067 - accuracy: 0.5312 - val_loss: 3.1300 - val_accuracy: 0.1562\n",
"Epoch 1169/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7451 - accuracy: 0.5938 - val_loss: 3.1275 - val_accuracy: 0.1875\n",
"Epoch 1170/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7746 - accuracy: 0.4688 - val_loss: 3.0862 - val_accuracy: 0.1875\n",
"Epoch 1171/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8190 - accuracy: 0.4375 - val_loss: 3.1351 - val_accuracy: 0.1875\n",
"Epoch 1172/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.8266 - accuracy: 0.6250 - val_loss: 3.4076 - val_accuracy: 0.1875\n",
"Epoch 1173/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7975 - accuracy: 0.4688 - val_loss: 3.0815 - val_accuracy: 0.2188\n",
"Epoch 1174/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7285 - accuracy: 0.6250 - val_loss: 3.2071 - val_accuracy: 0.1562\n",
"Epoch 1175/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7258 - accuracy: 0.5625 - val_loss: 3.0660 - val_accuracy: 0.2188\n",
"Epoch 1176/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8168 - accuracy: 0.4688 - val_loss: 3.1855 - val_accuracy: 0.1875\n",
"Epoch 1177/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7423 - accuracy: 0.6250 - val_loss: 3.1833 - val_accuracy: 0.1875\n",
"Epoch 1178/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7534 - accuracy: 0.4688 - val_loss: 3.1689 - val_accuracy: 0.1875\n",
"Epoch 1179/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6208 - accuracy: 0.6875 - val_loss: 3.1674 - val_accuracy: 0.1875\n",
"Epoch 1180/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6975 - accuracy: 0.6562 - val_loss: 3.1478 - val_accuracy: 0.1875\n",
"Epoch 1181/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6921 - accuracy: 0.5625 - val_loss: 3.1530 - val_accuracy: 0.1875\n",
"Epoch 1182/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6904 - accuracy: 0.5938 - val_loss: 3.1352 - val_accuracy: 0.1875\n",
"Epoch 1183/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8194 - accuracy: 0.3750 - val_loss: 3.0896 - val_accuracy: 0.1875\n",
"Epoch 1184/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7762 - accuracy: 0.5000 - val_loss: 3.1412 - val_accuracy: 0.1875\n",
"Epoch 1185/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7666 - accuracy: 0.5312 - val_loss: 3.2438 - val_accuracy: 0.1875\n",
"Epoch 1186/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7382 - accuracy: 0.5000 - val_loss: 3.1735 - val_accuracy: 0.1875\n",
"Epoch 1187/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8136 - accuracy: 0.5000 - val_loss: 3.2883 - val_accuracy: 0.1875\n",
"Epoch 1188/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6719 - accuracy: 0.7188 - val_loss: 3.2322 - val_accuracy: 0.1875\n",
"Epoch 1189/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.8150 - accuracy: 0.5938 - val_loss: 3.1159 - val_accuracy: 0.1875\n",
"Epoch 1190/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8129 - accuracy: 0.3438 - val_loss: 3.3493 - val_accuracy: 0.1562\n",
"Epoch 1191/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6683 - accuracy: 0.5625 - val_loss: 3.2151 - val_accuracy: 0.1875\n",
"Epoch 1192/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7197 - accuracy: 0.5625 - val_loss: 3.1798 - val_accuracy: 0.1875\n",
"Epoch 1193/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8263 - accuracy: 0.5312 - val_loss: 3.2063 - val_accuracy: 0.1562\n",
"Epoch 1194/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7504 - accuracy: 0.4688 - val_loss: 3.1471 - val_accuracy: 0.1562\n",
"Epoch 1195/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6726 - accuracy: 0.4688 - val_loss: 3.2228 - val_accuracy: 0.1562\n",
"Epoch 1196/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8635 - accuracy: 0.5312 - val_loss: 3.1471 - val_accuracy: 0.1875\n",
"Epoch 1197/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6356 - accuracy: 0.5625 - val_loss: 3.2943 - val_accuracy: 0.1562\n",
"Epoch 1198/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6311 - accuracy: 0.5625 - val_loss: 3.0834 - val_accuracy: 0.1875\n",
"Epoch 1199/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6724 - accuracy: 0.6250 - val_loss: 3.2524 - val_accuracy: 0.1875\n",
"Epoch 1200/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7091 - accuracy: 0.5938 - val_loss: 3.1759 - val_accuracy: 0.1875\n",
"Epoch 1201/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6811 - accuracy: 0.5000 - val_loss: 3.2644 - val_accuracy: 0.1562\n",
"Epoch 1202/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6931 - accuracy: 0.5312 - val_loss: 3.1751 - val_accuracy: 0.1875\n",
"Epoch 1203/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.7321 - accuracy: 0.5000 - val_loss: 3.4423 - val_accuracy: 0.2188\n",
"Epoch 1204/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6534 - accuracy: 0.6250 - val_loss: 3.2371 - val_accuracy: 0.2188\n",
"Epoch 1205/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7018 - accuracy: 0.4688 - val_loss: 3.2692 - val_accuracy: 0.2188\n",
"Epoch 1206/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6130 - accuracy: 0.5938 - val_loss: 3.2221 - val_accuracy: 0.1875\n",
"Epoch 1207/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6522 - accuracy: 0.5312 - val_loss: 3.3368 - val_accuracy: 0.2188\n",
"Epoch 1208/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7773 - accuracy: 0.5000 - val_loss: 3.1636 - val_accuracy: 0.2188\n",
"Epoch 1209/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7340 - accuracy: 0.5625 - val_loss: 3.3126 - val_accuracy: 0.1562\n",
"Epoch 1210/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6874 - accuracy: 0.6250 - val_loss: 3.1723 - val_accuracy: 0.1875\n",
"Epoch 1211/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6524 - accuracy: 0.6562 - val_loss: 3.3389 - val_accuracy: 0.2188\n",
"Epoch 1212/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7221 - accuracy: 0.5312 - val_loss: 3.1083 - val_accuracy: 0.1875\n",
"Epoch 1213/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6922 - accuracy: 0.5312 - val_loss: 3.2807 - val_accuracy: 0.1562\n",
"Epoch 1214/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7733 - accuracy: 0.5312 - val_loss: 3.3351 - val_accuracy: 0.1562\n",
"Epoch 1215/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6408 - accuracy: 0.6562 - val_loss: 3.2225 - val_accuracy: 0.1875\n",
"Epoch 1216/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8222 - accuracy: 0.5312 - val_loss: 3.3115 - val_accuracy: 0.1875\n",
"Epoch 1217/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7286 - accuracy: 0.6562 - val_loss: 3.2368 - val_accuracy: 0.2188\n",
"Epoch 1218/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7088 - accuracy: 0.5312 - val_loss: 3.3223 - val_accuracy: 0.2188\n",
"Epoch 1219/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7758 - accuracy: 0.5312 - val_loss: 3.2640 - val_accuracy: 0.1875\n",
"Epoch 1220/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6456 - accuracy: 0.6562 - val_loss: 3.2719 - val_accuracy: 0.1562\n",
"Epoch 1221/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7414 - accuracy: 0.5000 - val_loss: 3.2223 - val_accuracy: 0.1875\n",
"Epoch 1222/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7200 - accuracy: 0.5312 - val_loss: 3.3269 - val_accuracy: 0.1562\n",
"Epoch 1223/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6915 - accuracy: 0.5000 - val_loss: 3.2264 - val_accuracy: 0.1875\n",
"Epoch 1224/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6491 - accuracy: 0.6562 - val_loss: 3.2808 - val_accuracy: 0.2188\n",
"Epoch 1225/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8056 - accuracy: 0.5625 - val_loss: 3.1885 - val_accuracy: 0.1875\n",
"Epoch 1226/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6730 - accuracy: 0.5938 - val_loss: 3.3122 - val_accuracy: 0.2188\n",
"Epoch 1227/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7315 - accuracy: 0.5000 - val_loss: 3.3270 - val_accuracy: 0.1875\n",
"Epoch 1228/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7604 - accuracy: 0.5625 - val_loss: 3.2670 - val_accuracy: 0.1875\n",
"Epoch 1229/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8402 - accuracy: 0.4688 - val_loss: 3.3475 - val_accuracy: 0.1562\n",
"Epoch 1230/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8082 - accuracy: 0.5000 - val_loss: 3.2441 - val_accuracy: 0.2188\n",
"Epoch 1231/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7172 - accuracy: 0.4688 - val_loss: 3.6883 - val_accuracy: 0.2188\n",
"Epoch 1232/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8285 - accuracy: 0.4375 - val_loss: 3.1708 - val_accuracy: 0.2188\n",
"Epoch 1233/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6788 - accuracy: 0.6875 - val_loss: 3.5147 - val_accuracy: 0.2188\n",
"Epoch 1234/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6645 - accuracy: 0.5312 - val_loss: 3.2097 - val_accuracy: 0.2188\n",
"Epoch 1235/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.7314 - accuracy: 0.56 - 0s 177ms/step - loss: 0.7314 - accuracy: 0.5625 - val_loss: 3.4988 - val_accuracy: 0.1875\n",
"Epoch 1236/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7050 - accuracy: 0.5312 - val_loss: 3.3632 - val_accuracy: 0.2188\n",
"Epoch 1237/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6466 - accuracy: 0.6250 - val_loss: 3.2225 - val_accuracy: 0.2188\n",
"Epoch 1238/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7366 - accuracy: 0.5312 - val_loss: 3.2332 - val_accuracy: 0.2188\n",
"Epoch 1239/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6753 - accuracy: 0.6562 - val_loss: 3.4533 - val_accuracy: 0.2188\n",
"Epoch 1240/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7891 - accuracy: 0.5312 - val_loss: 3.2078 - val_accuracy: 0.2188\n",
"Epoch 1241/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8785 - accuracy: 0.4688 - val_loss: 3.4735 - val_accuracy: 0.2188\n",
"Epoch 1242/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8444 - accuracy: 0.5000 - val_loss: 3.1060 - val_accuracy: 0.2188\n",
"Epoch 1243/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8352 - accuracy: 0.4688 - val_loss: 3.5638 - val_accuracy: 0.1875\n",
"Epoch 1244/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6334 - accuracy: 0.5625 - val_loss: 3.1863 - val_accuracy: 0.2188\n",
"Epoch 1245/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7557 - accuracy: 0.3750 - val_loss: 3.4836 - val_accuracy: 0.1875\n",
"Epoch 1246/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7670 - accuracy: 0.4688 - val_loss: 3.1178 - val_accuracy: 0.1875\n",
"Epoch 1247/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6899 - accuracy: 0.5625 - val_loss: 3.3215 - val_accuracy: 0.1875\n",
"Epoch 1248/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7683 - accuracy: 0.5312 - val_loss: 3.3484 - val_accuracy: 0.1875\n",
"Epoch 1249/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6987 - accuracy: 0.5000 - val_loss: 3.3067 - val_accuracy: 0.1875\n",
"Epoch 1250/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8058 - accuracy: 0.5625 - val_loss: 3.1715 - val_accuracy: 0.2188\n",
"Epoch 1251/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7516 - accuracy: 0.5312 - val_loss: 3.5188 - val_accuracy: 0.1875\n",
"Epoch 1252/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6939 - accuracy: 0.5625 - val_loss: 3.2317 - val_accuracy: 0.1875\n",
"Epoch 1253/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6748 - accuracy: 0.5000 - val_loss: 3.3003 - val_accuracy: 0.1562\n",
"Epoch 1254/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8802 - accuracy: 0.4062 - val_loss: 3.4453 - val_accuracy: 0.1562\n",
"Epoch 1255/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6789 - accuracy: 0.5312 - val_loss: 3.2806 - val_accuracy: 0.1562\n",
"Epoch 1256/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6699 - accuracy: 0.5312 - val_loss: 3.2055 - val_accuracy: 0.1562\n",
"Epoch 1257/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8867 - accuracy: 0.4062 - val_loss: 3.4853 - val_accuracy: 0.2500\n",
"Epoch 1258/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.1783 - accuracy: 0.5000 - val_loss: 3.6309 - val_accuracy: 0.2188\n",
"Epoch 1259/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7931 - accuracy: 0.5938 - val_loss: 3.6441 - val_accuracy: 0.2188\n",
"Epoch 1260/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6542 - accuracy: 0.5625 - val_loss: 3.2106 - val_accuracy: 0.2500\n",
"Epoch 1261/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7075 - accuracy: 0.6875 - val_loss: 3.5383 - val_accuracy: 0.1875\n",
"Epoch 1262/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7127 - accuracy: 0.5938 - val_loss: 3.3170 - val_accuracy: 0.2188\n",
"Epoch 1263/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6053 - accuracy: 0.7500 - val_loss: 3.3186 - val_accuracy: 0.2188\n",
"Epoch 1264/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7023 - accuracy: 0.5000 - val_loss: 3.4014 - val_accuracy: 0.1875\n",
"Epoch 1265/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6838 - accuracy: 0.6562 - val_loss: 3.3288 - val_accuracy: 0.2188\n",
"Epoch 1266/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6936 - accuracy: 0.5625 - val_loss: 3.2643 - val_accuracy: 0.2188\n",
"Epoch 1267/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8130 - accuracy: 0.5312 - val_loss: 3.3073 - val_accuracy: 0.2188\n",
"Epoch 1268/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7561 - accuracy: 0.5625 - val_loss: 3.4430 - val_accuracy: 0.1875\n",
"Epoch 1269/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6248 - accuracy: 0.6875 - val_loss: 3.2527 - val_accuracy: 0.2188\n",
"Epoch 1270/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6138 - accuracy: 0.5938 - val_loss: 3.4963 - val_accuracy: 0.1875\n",
"Epoch 1271/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5793 - accuracy: 0.6562 - val_loss: 3.3526 - val_accuracy: 0.2188\n",
"Epoch 1272/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6882 - accuracy: 0.5312 - val_loss: 3.2394 - val_accuracy: 0.2188\n",
"Epoch 1273/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7849 - accuracy: 0.5938 - val_loss: 3.4838 - val_accuracy: 0.1875\n",
"Epoch 1274/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8470 - accuracy: 0.5000 - val_loss: 3.2386 - val_accuracy: 0.2188\n",
"Epoch 1275/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7179 - accuracy: 0.5625 - val_loss: 3.7040 - val_accuracy: 0.1562\n",
"Epoch 1276/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7686 - accuracy: 0.5000 - val_loss: 3.3516 - val_accuracy: 0.2500\n",
"Epoch 1277/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7108 - accuracy: 0.5938 - val_loss: 3.5710 - val_accuracy: 0.2188\n",
"Epoch 1278/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7467 - accuracy: 0.4688 - val_loss: 3.3544 - val_accuracy: 0.2188\n",
"Epoch 1279/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7250 - accuracy: 0.4688 - val_loss: 3.5105 - val_accuracy: 0.2500\n",
"Epoch 1280/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7929 - accuracy: 0.5938 - val_loss: 3.3800 - val_accuracy: 0.2188\n",
"Epoch 1281/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7241 - accuracy: 0.5312 - val_loss: 3.4601 - val_accuracy: 0.2188\n",
"Epoch 1282/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7500 - accuracy: 0.5000 - val_loss: 3.3453 - val_accuracy: 0.2188\n",
"Epoch 1283/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6281 - accuracy: 0.5625 - val_loss: 3.3280 - val_accuracy: 0.2188\n",
"Epoch 1284/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7258 - accuracy: 0.5312 - val_loss: 3.3440 - val_accuracy: 0.1875\n",
"Epoch 1285/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6462 - accuracy: 0.5938 - val_loss: 3.3452 - val_accuracy: 0.2188\n",
"Epoch 1286/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7413 - accuracy: 0.5312 - val_loss: 3.4258 - val_accuracy: 0.2188\n",
"Epoch 1287/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7326 - accuracy: 0.4688 - val_loss: 3.4694 - val_accuracy: 0.2188\n",
"Epoch 1288/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7803 - accuracy: 0.4375 - val_loss: 3.3968 - val_accuracy: 0.2188\n",
"Epoch 1289/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8879 - accuracy: 0.4375 - val_loss: 3.3805 - val_accuracy: 0.2188\n",
"Epoch 1290/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7126 - accuracy: 0.5938 - val_loss: 3.3407 - val_accuracy: 0.2188\n",
"Epoch 1291/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6526 - accuracy: 0.5625 - val_loss: 3.3959 - val_accuracy: 0.1562\n",
"Epoch 1292/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6640 - accuracy: 0.5312 - val_loss: 3.3517 - val_accuracy: 0.1875\n",
"Epoch 1293/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5683 - accuracy: 0.6875 - val_loss: 3.3585 - val_accuracy: 0.1875\n",
"Epoch 1294/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6242 - accuracy: 0.6250 - val_loss: 3.4423 - val_accuracy: 0.1562\n",
"Epoch 1295/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8107 - accuracy: 0.4688 - val_loss: 3.3061 - val_accuracy: 0.2188\n",
"Epoch 1296/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.7333 - accuracy: 0.5312 - val_loss: 3.3638 - val_accuracy: 0.2188\n",
"Epoch 1297/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7691 - accuracy: 0.6250 - val_loss: 3.3142 - val_accuracy: 0.2188\n",
"Epoch 1298/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6918 - accuracy: 0.6250 - val_loss: 3.4105 - val_accuracy: 0.1875\n",
"Epoch 1299/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6894 - accuracy: 0.5938 - val_loss: 3.4082 - val_accuracy: 0.1875\n",
"Epoch 1300/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5804 - accuracy: 0.5938 - val_loss: 3.3095 - val_accuracy: 0.2188\n",
"Epoch 1301/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6486 - accuracy: 0.6562 - val_loss: 3.4326 - val_accuracy: 0.2188\n",
"Epoch 1302/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6951 - accuracy: 0.4688 - val_loss: 3.3452 - val_accuracy: 0.2188\n",
"Epoch 1303/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6703 - accuracy: 0.6250 - val_loss: 3.4306 - val_accuracy: 0.2188\n",
"Epoch 1304/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6587 - accuracy: 0.5938 - val_loss: 3.3297 - val_accuracy: 0.2188\n",
"Epoch 1305/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7742 - accuracy: 0.5625 - val_loss: 3.3706 - val_accuracy: 0.2188\n",
"Epoch 1306/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8014 - accuracy: 0.5938 - val_loss: 3.6363 - val_accuracy: 0.2188\n",
"Epoch 1307/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8574 - accuracy: 0.5000 - val_loss: 3.0257 - val_accuracy: 0.2188\n",
"Epoch 1308/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.0303 - accuracy: 0.4375 - val_loss: 3.6281 - val_accuracy: 0.1875\n",
"Epoch 1309/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7751 - accuracy: 0.5312 - val_loss: 3.1910 - val_accuracy: 0.1875\n",
"Epoch 1310/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7345 - accuracy: 0.3750 - val_loss: 3.3998 - val_accuracy: 0.1875\n",
"Epoch 1311/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6894 - accuracy: 0.5938 - val_loss: 3.1794 - val_accuracy: 0.1875\n",
"Epoch 1312/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6819 - accuracy: 0.6562 - val_loss: 3.4059 - val_accuracy: 0.1875\n",
"Epoch 1313/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6333 - accuracy: 0.5312 - val_loss: 3.2693 - val_accuracy: 0.1875\n",
"Epoch 1314/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7316 - accuracy: 0.5312 - val_loss: 3.3913 - val_accuracy: 0.2188\n",
"Epoch 1315/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7679 - accuracy: 0.4688 - val_loss: 3.2277 - val_accuracy: 0.2188\n",
"Epoch 1316/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7286 - accuracy: 0.4375 - val_loss: 3.4166 - val_accuracy: 0.1875\n",
"Epoch 1317/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7120 - accuracy: 0.5625 - val_loss: 3.2979 - val_accuracy: 0.1875\n",
"Epoch 1318/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7010 - accuracy: 0.6250 - val_loss: 3.3837 - val_accuracy: 0.1875\n",
"Epoch 1319/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6449 - accuracy: 0.5312 - val_loss: 3.4151 - val_accuracy: 0.1875\n",
"Epoch 1320/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7684 - accuracy: 0.5938 - val_loss: 3.3633 - val_accuracy: 0.1875\n",
"Epoch 1321/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7085 - accuracy: 0.5625 - val_loss: 3.5006 - val_accuracy: 0.1562\n",
"Epoch 1322/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6683 - accuracy: 0.5000 - val_loss: 3.2566 - val_accuracy: 0.1562\n",
"Epoch 1323/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8717 - accuracy: 0.4062 - val_loss: 3.5399 - val_accuracy: 0.1562\n",
"Epoch 1324/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6850 - accuracy: 0.5312 - val_loss: 3.2298 - val_accuracy: 0.1562\n",
"Epoch 1325/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7691 - accuracy: 0.4688 - val_loss: 3.4848 - val_accuracy: 0.2188\n",
"Epoch 1326/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6825 - accuracy: 0.6875 - val_loss: 3.2932 - val_accuracy: 0.1562\n",
"Epoch 1327/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7288 - accuracy: 0.5625 - val_loss: 3.8005 - val_accuracy: 0.1875\n",
"Epoch 1328/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8336 - accuracy: 0.5000 - val_loss: 2.9954 - val_accuracy: 0.2188\n",
"Epoch 1329/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.2393 - accuracy: 0.4688 - val_loss: 6.1566 - val_accuracy: 0.0312\n",
"Epoch 1330/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 4.3150 - accuracy: 0.0625 - val_loss: 3.7517 - val_accuracy: 0.2188\n",
"Epoch 1331/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 8.8761 - accuracy: 0.1875 - val_loss: 3.6992 - val_accuracy: 0.0625\n",
"Epoch 1332/5000\n",
"1/1 [==============================] - 0s 204ms/step - loss: 3.2737 - accuracy: 0.1250 - val_loss: 3.3195 - val_accuracy: 0.0625\n",
"Epoch 1333/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 3.5355 - accuracy: 0.1250 - val_loss: 3.0663 - val_accuracy: 0.0938\n",
"Epoch 1334/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 2.7891 - accuracy: 0.1875 - val_loss: 3.1617 - val_accuracy: 0.1250\n",
"Epoch 1335/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.2430 - accuracy: 0.2188 - val_loss: 3.3470 - val_accuracy: 0.0938\n",
"Epoch 1336/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.1508 - accuracy: 0.3125 - val_loss: 3.1022 - val_accuracy: 0.0938\n",
"Epoch 1337/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.9032 - accuracy: 0.3438 - val_loss: 2.9771 - val_accuracy: 0.1250\n",
"Epoch 1338/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8544 - accuracy: 0.4375 - val_loss: 2.9541 - val_accuracy: 0.0625\n",
"Epoch 1339/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9952 - accuracy: 0.4062 - val_loss: 2.9577 - val_accuracy: 0.1250\n",
"Epoch 1340/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8869 - accuracy: 0.4062 - val_loss: 2.9506 - val_accuracy: 0.1562\n",
"Epoch 1341/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.8413 - accuracy: 0.5625 - val_loss: 2.9467 - val_accuracy: 0.1250\n",
"Epoch 1342/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7943 - accuracy: 0.5938 - val_loss: 2.9203 - val_accuracy: 0.1250\n",
"Epoch 1343/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8338 - accuracy: 0.5000 - val_loss: 3.0394 - val_accuracy: 0.1562\n",
"Epoch 1344/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7968 - accuracy: 0.6250 - val_loss: 3.0380 - val_accuracy: 0.1562\n",
"Epoch 1345/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7648 - accuracy: 0.5312 - val_loss: 3.0000 - val_accuracy: 0.1562\n",
"Epoch 1346/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7853 - accuracy: 0.5312 - val_loss: 2.9599 - val_accuracy: 0.1562\n",
"Epoch 1347/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9018 - accuracy: 0.3750 - val_loss: 2.9743 - val_accuracy: 0.1562\n",
"Epoch 1348/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.7482 - accuracy: 0.5938 - val_loss: 2.9404 - val_accuracy: 0.1562\n",
"Epoch 1349/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8784 - accuracy: 0.5000 - val_loss: 3.0104 - val_accuracy: 0.1562\n",
"Epoch 1350/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7614 - accuracy: 0.5312 - val_loss: 3.0383 - val_accuracy: 0.1562\n",
"Epoch 1351/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8184 - accuracy: 0.4688 - val_loss: 3.0361 - val_accuracy: 0.1562\n",
"Epoch 1352/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8059 - accuracy: 0.5938 - val_loss: 3.1224 - val_accuracy: 0.1562\n",
"Epoch 1353/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7752 - accuracy: 0.6250 - val_loss: 3.0829 - val_accuracy: 0.1562\n",
"Epoch 1354/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7411 - accuracy: 0.6250 - val_loss: 3.0003 - val_accuracy: 0.1562\n",
"Epoch 1355/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7094 - accuracy: 0.5938 - val_loss: 3.0468 - val_accuracy: 0.1562\n",
"Epoch 1356/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7421 - accuracy: 0.5312 - val_loss: 3.0624 - val_accuracy: 0.1562\n",
"Epoch 1357/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7828 - accuracy: 0.6562 - val_loss: 3.0984 - val_accuracy: 0.1562\n",
"Epoch 1358/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7812 - accuracy: 0.5000 - val_loss: 3.0783 - val_accuracy: 0.1562\n",
"Epoch 1359/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7203 - accuracy: 0.5625 - val_loss: 3.0712 - val_accuracy: 0.1562\n",
"Epoch 1360/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7565 - accuracy: 0.6250 - val_loss: 3.1448 - val_accuracy: 0.1562\n",
"Epoch 1361/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7822 - accuracy: 0.5625 - val_loss: 3.0970 - val_accuracy: 0.1562\n",
"Epoch 1362/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7156 - accuracy: 0.5312 - val_loss: 3.1037 - val_accuracy: 0.1562\n",
"Epoch 1363/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.8016 - accuracy: 0.5312 - val_loss: 3.0614 - val_accuracy: 0.1562\n",
"Epoch 1364/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7865 - accuracy: 0.5625 - val_loss: 3.0556 - val_accuracy: 0.1562\n",
"Epoch 1365/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.8328 - accuracy: 0.5312 - val_loss: 3.1160 - val_accuracy: 0.1562\n",
"Epoch 1366/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6794 - accuracy: 0.5000 - val_loss: 3.1335 - val_accuracy: 0.1562\n",
"Epoch 1367/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7655 - accuracy: 0.6562 - val_loss: 2.9858 - val_accuracy: 0.1562\n",
"Epoch 1368/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7303 - accuracy: 0.5625 - val_loss: 3.0927 - val_accuracy: 0.1562\n",
"Epoch 1369/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6738 - accuracy: 0.5000 - val_loss: 3.0976 - val_accuracy: 0.1562\n",
"Epoch 1370/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6542 - accuracy: 0.7188 - val_loss: 3.0565 - val_accuracy: 0.1562\n",
"Epoch 1371/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6762 - accuracy: 0.5312 - val_loss: 3.1169 - val_accuracy: 0.1562\n",
"Epoch 1372/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7078 - accuracy: 0.4688 - val_loss: 3.1445 - val_accuracy: 0.1562\n",
"Epoch 1373/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7682 - accuracy: 0.5000 - val_loss: 3.1535 - val_accuracy: 0.1562\n",
"Epoch 1374/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6846 - accuracy: 0.6250 - val_loss: 3.1177 - val_accuracy: 0.1562\n",
"Epoch 1375/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7854 - accuracy: 0.5000 - val_loss: 3.1544 - val_accuracy: 0.1562\n",
"Epoch 1376/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7513 - accuracy: 0.4688 - val_loss: 3.1242 - val_accuracy: 0.1562\n",
"Epoch 1377/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7987 - accuracy: 0.5000 - val_loss: 3.2089 - val_accuracy: 0.1562\n",
"Epoch 1378/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6848 - accuracy: 0.5000 - val_loss: 3.2723 - val_accuracy: 0.1562\n",
"Epoch 1379/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8053 - accuracy: 0.4062 - val_loss: 3.1551 - val_accuracy: 0.1562\n",
"Epoch 1380/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8418 - accuracy: 0.5000 - val_loss: 3.2015 - val_accuracy: 0.1562\n",
"Epoch 1381/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7630 - accuracy: 0.5625 - val_loss: 3.0986 - val_accuracy: 0.1562\n",
"Epoch 1382/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7516 - accuracy: 0.5625 - val_loss: 3.2012 - val_accuracy: 0.1562\n",
"Epoch 1383/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5989 - accuracy: 0.5625 - val_loss: 3.1230 - val_accuracy: 0.1562\n",
"Epoch 1384/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6606 - accuracy: 0.5938 - val_loss: 3.1384 - val_accuracy: 0.1562\n",
"Epoch 1385/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6801 - accuracy: 0.6250 - val_loss: 3.2168 - val_accuracy: 0.1562\n",
"Epoch 1386/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6585 - accuracy: 0.5938 - val_loss: 3.1608 - val_accuracy: 0.1562\n",
"Epoch 1387/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7981 - accuracy: 0.5312 - val_loss: 3.2285 - val_accuracy: 0.1875\n",
"Epoch 1388/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7340 - accuracy: 0.4688 - val_loss: 3.2246 - val_accuracy: 0.1875\n",
"Epoch 1389/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7394 - accuracy: 0.5312 - val_loss: 3.1817 - val_accuracy: 0.1875\n",
"Epoch 1390/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6434 - accuracy: 0.5625 - val_loss: 3.1326 - val_accuracy: 0.1875\n",
"Epoch 1391/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7096 - accuracy: 0.5000 - val_loss: 3.2329 - val_accuracy: 0.1875\n",
"Epoch 1392/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7330 - accuracy: 0.6250 - val_loss: 3.2275 - val_accuracy: 0.1562\n",
"Epoch 1393/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7692 - accuracy: 0.5625 - val_loss: 3.2183 - val_accuracy: 0.1875\n",
"Epoch 1394/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7785 - accuracy: 0.5000 - val_loss: 3.1510 - val_accuracy: 0.1562\n",
"Epoch 1395/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7748 - accuracy: 0.5000 - val_loss: 3.3118 - val_accuracy: 0.1875\n",
"Epoch 1396/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6375 - accuracy: 0.6250 - val_loss: 3.2677 - val_accuracy: 0.1875\n",
"Epoch 1397/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7036 - accuracy: 0.5625 - val_loss: 3.1888 - val_accuracy: 0.1562\n",
"Epoch 1398/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.7506 - accuracy: 0.59 - 0s 170ms/step - loss: 0.7506 - accuracy: 0.5938 - val_loss: 3.4759 - val_accuracy: 0.1875\n",
"Epoch 1399/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7325 - accuracy: 0.5625 - val_loss: 3.1642 - val_accuracy: 0.1875\n",
"Epoch 1400/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7086 - accuracy: 0.6875 - val_loss: 3.3702 - val_accuracy: 0.1875\n",
"Epoch 1401/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8057 - accuracy: 0.4688 - val_loss: 3.2144 - val_accuracy: 0.1875\n",
"Epoch 1402/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6836 - accuracy: 0.6250 - val_loss: 3.1821 - val_accuracy: 0.1562\n",
"Epoch 1403/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6992 - accuracy: 0.5625 - val_loss: 3.3082 - val_accuracy: 0.1875\n",
"Epoch 1404/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6719 - accuracy: 0.5625 - val_loss: 3.2246 - val_accuracy: 0.1562\n",
"Epoch 1405/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6618 - accuracy: 0.6250 - val_loss: 3.3929 - val_accuracy: 0.1875\n",
"Epoch 1406/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8026 - accuracy: 0.5000 - val_loss: 3.1416 - val_accuracy: 0.1562\n",
"Epoch 1407/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6579 - accuracy: 0.5938 - val_loss: 3.2931 - val_accuracy: 0.1875\n",
"Epoch 1408/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6512 - accuracy: 0.5625 - val_loss: 3.1955 - val_accuracy: 0.1875\n",
"Epoch 1409/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6819 - accuracy: 0.4688 - val_loss: 3.3519 - val_accuracy: 0.1875\n",
"Epoch 1410/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6924 - accuracy: 0.5312 - val_loss: 3.2808 - val_accuracy: 0.1875\n",
"Epoch 1411/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6448 - accuracy: 0.5000 - val_loss: 3.2181 - val_accuracy: 0.1875\n",
"Epoch 1412/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7037 - accuracy: 0.5000 - val_loss: 3.2853 - val_accuracy: 0.1875\n",
"Epoch 1413/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7051 - accuracy: 0.5312 - val_loss: 3.3652 - val_accuracy: 0.1875\n",
"Epoch 1414/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6155 - accuracy: 0.6562 - val_loss: 3.2152 - val_accuracy: 0.2188\n",
"Epoch 1415/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7371 - accuracy: 0.5312 - val_loss: 3.3330 - val_accuracy: 0.1875\n",
"Epoch 1416/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7521 - accuracy: 0.5625 - val_loss: 3.2387 - val_accuracy: 0.1875\n",
"Epoch 1417/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6468 - accuracy: 0.5312 - val_loss: 3.2773 - val_accuracy: 0.1875\n",
"Epoch 1418/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7083 - accuracy: 0.5312 - val_loss: 3.2610 - val_accuracy: 0.1875\n",
"Epoch 1419/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7178 - accuracy: 0.5000 - val_loss: 3.3271 - val_accuracy: 0.1875\n",
"Epoch 1420/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8045 - accuracy: 0.4062 - val_loss: 3.3751 - val_accuracy: 0.1875\n",
"Epoch 1421/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7057 - accuracy: 0.5312 - val_loss: 3.2447 - val_accuracy: 0.1875\n",
"Epoch 1422/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7999 - accuracy: 0.5000 - val_loss: 3.2644 - val_accuracy: 0.1562\n",
"Epoch 1423/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7861 - accuracy: 0.5312 - val_loss: 3.2732 - val_accuracy: 0.1562\n",
"Epoch 1424/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7935 - accuracy: 0.5000 - val_loss: 3.4822 - val_accuracy: 0.1562\n",
"Epoch 1425/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6944 - accuracy: 0.5312 - val_loss: 3.2744 - val_accuracy: 0.1562\n",
"Epoch 1426/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6345 - accuracy: 0.5938 - val_loss: 3.1514 - val_accuracy: 0.1562\n",
"Epoch 1427/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7593 - accuracy: 0.6562 - val_loss: 3.4929 - val_accuracy: 0.1562\n",
"Epoch 1428/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8354 - accuracy: 0.5625 - val_loss: 3.1262 - val_accuracy: 0.1875\n",
"Epoch 1429/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6342 - accuracy: 0.5938 - val_loss: 3.3140 - val_accuracy: 0.1562\n",
"Epoch 1430/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7881 - accuracy: 0.5938 - val_loss: 3.3644 - val_accuracy: 0.2188\n",
"Epoch 1431/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7692 - accuracy: 0.5312 - val_loss: 3.3420 - val_accuracy: 0.2188\n",
"Epoch 1432/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7746 - accuracy: 0.5000 - val_loss: 3.3004 - val_accuracy: 0.2188\n",
"Epoch 1433/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6922 - accuracy: 0.5000 - val_loss: 3.3967 - val_accuracy: 0.2188\n",
"Epoch 1434/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7402 - accuracy: 0.7188 - val_loss: 3.2298 - val_accuracy: 0.2188\n",
"Epoch 1435/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8787 - accuracy: 0.4688 - val_loss: 3.5273 - val_accuracy: 0.1562\n",
"Epoch 1436/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7604 - accuracy: 0.5000 - val_loss: 3.2087 - val_accuracy: 0.2188\n",
"Epoch 1437/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.6650 - accuracy: 0.5938 - val_loss: 3.3040 - val_accuracy: 0.1562\n",
"Epoch 1438/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6984 - accuracy: 0.5938 - val_loss: 3.3465 - val_accuracy: 0.1562\n",
"Epoch 1439/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7805 - accuracy: 0.4688 - val_loss: 3.3403 - val_accuracy: 0.1562\n",
"Epoch 1440/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.8122 - accuracy: 0.5312 - val_loss: 3.4685 - val_accuracy: 0.1562\n",
"Epoch 1441/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6359 - accuracy: 0.4688 - val_loss: 3.2841 - val_accuracy: 0.2188\n",
"Epoch 1442/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8217 - accuracy: 0.4375 - val_loss: 3.4998 - val_accuracy: 0.1562\n",
"Epoch 1443/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7584 - accuracy: 0.5000 - val_loss: 3.2727 - val_accuracy: 0.2188\n",
"Epoch 1444/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6514 - accuracy: 0.6875 - val_loss: 3.3210 - val_accuracy: 0.1562\n",
"Epoch 1445/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7780 - accuracy: 0.5625 - val_loss: 3.4368 - val_accuracy: 0.1875\n",
"Epoch 1446/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7270 - accuracy: 0.6875 - val_loss: 3.6148 - val_accuracy: 0.1562\n",
"Epoch 1447/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7111 - accuracy: 0.5938 - val_loss: 3.2869 - val_accuracy: 0.2188\n",
"Epoch 1448/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7304 - accuracy: 0.5000 - val_loss: 3.4242 - val_accuracy: 0.1562\n",
"Epoch 1449/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6823 - accuracy: 0.6250 - val_loss: 3.4117 - val_accuracy: 0.1875\n",
"Epoch 1450/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6418 - accuracy: 0.5938 - val_loss: 3.5312 - val_accuracy: 0.1875\n",
"Epoch 1451/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8109 - accuracy: 0.5312 - val_loss: 3.2817 - val_accuracy: 0.1875\n",
"Epoch 1452/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5825 - accuracy: 0.6875 - val_loss: 3.2821 - val_accuracy: 0.1875\n",
"Epoch 1453/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7114 - accuracy: 0.5000 - val_loss: 3.4847 - val_accuracy: 0.1875\n",
"Epoch 1454/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6744 - accuracy: 0.4375 - val_loss: 3.3730 - val_accuracy: 0.1562\n",
"Epoch 1455/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6233 - accuracy: 0.6875 - val_loss: 3.4286 - val_accuracy: 0.1875\n",
"Epoch 1456/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8754 - accuracy: 0.5000 - val_loss: 3.4488 - val_accuracy: 0.1875\n",
"Epoch 1457/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6529 - accuracy: 0.5625 - val_loss: 3.3779 - val_accuracy: 0.2188\n",
"Epoch 1458/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7259 - accuracy: 0.5625 - val_loss: 3.4536 - val_accuracy: 0.2188\n",
"Epoch 1459/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7929 - accuracy: 0.4375 - val_loss: 3.3825 - val_accuracy: 0.1875\n",
"Epoch 1460/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.8016 - accuracy: 0.3750 - val_loss: 3.4576 - val_accuracy: 0.1562\n",
"Epoch 1461/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6421 - accuracy: 0.5000 - val_loss: 3.3712 - val_accuracy: 0.1562\n",
"Epoch 1462/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6325 - accuracy: 0.5312 - val_loss: 3.4688 - val_accuracy: 0.1562\n",
"Epoch 1463/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6395 - accuracy: 0.5625 - val_loss: 3.4268 - val_accuracy: 0.1562\n",
"Epoch 1464/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7098 - accuracy: 0.6250 - val_loss: 3.5275 - val_accuracy: 0.1562\n",
"Epoch 1465/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8259 - accuracy: 0.4688 - val_loss: 3.2336 - val_accuracy: 0.1562\n",
"Epoch 1466/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7284 - accuracy: 0.5938 - val_loss: 3.2603 - val_accuracy: 0.1875\n",
"Epoch 1467/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7292 - accuracy: 0.5312 - val_loss: 3.5052 - val_accuracy: 0.1562\n",
"Epoch 1468/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6565 - accuracy: 0.5938 - val_loss: 3.2039 - val_accuracy: 0.2188\n",
"Epoch 1469/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7183 - accuracy: 0.4375 - val_loss: 3.7110 - val_accuracy: 0.1562\n",
"Epoch 1470/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6686 - accuracy: 0.6250 - val_loss: 3.1782 - val_accuracy: 0.2188\n",
"Epoch 1471/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6820 - accuracy: 0.6250 - val_loss: 3.5259 - val_accuracy: 0.1250\n",
"Epoch 1472/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6468 - accuracy: 0.5625 - val_loss: 3.2692 - val_accuracy: 0.1875\n",
"Epoch 1473/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6869 - accuracy: 0.5312 - val_loss: 3.4239 - val_accuracy: 0.1562\n",
"Epoch 1474/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6273 - accuracy: 0.5312 - val_loss: 3.3495 - val_accuracy: 0.1875\n",
"Epoch 1475/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7897 - accuracy: 0.4688 - val_loss: 3.3515 - val_accuracy: 0.2188\n",
"Epoch 1476/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7295 - accuracy: 0.5625 - val_loss: 3.3805 - val_accuracy: 0.1875\n",
"Epoch 1477/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6249 - accuracy: 0.5938 - val_loss: 3.3648 - val_accuracy: 0.1562\n",
"Epoch 1478/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6315 - accuracy: 0.6250 - val_loss: 3.4547 - val_accuracy: 0.1562\n",
"Epoch 1479/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6638 - accuracy: 0.6875 - val_loss: 3.3509 - val_accuracy: 0.1562\n",
"Epoch 1480/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8396 - accuracy: 0.5625 - val_loss: 3.6246 - val_accuracy: 0.1875\n",
"Epoch 1481/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6465 - accuracy: 0.5938 - val_loss: 3.3711 - val_accuracy: 0.1562\n",
"Epoch 1482/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6709 - accuracy: 0.6250 - val_loss: 3.2714 - val_accuracy: 0.1875\n",
"Epoch 1483/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7798 - accuracy: 0.5625 - val_loss: 3.5911 - val_accuracy: 0.1562\n",
"Epoch 1484/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6774 - accuracy: 0.4062 - val_loss: 3.3513 - val_accuracy: 0.1875\n",
"Epoch 1485/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5920 - accuracy: 0.6250 - val_loss: 3.3268 - val_accuracy: 0.1875\n",
"Epoch 1486/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7216 - accuracy: 0.5312 - val_loss: 3.5310 - val_accuracy: 0.1875\n",
"Epoch 1487/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6806 - accuracy: 0.5312 - val_loss: 3.3744 - val_accuracy: 0.1562\n",
"Epoch 1488/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6944 - accuracy: 0.5625 - val_loss: 3.4392 - val_accuracy: 0.1562\n",
"Epoch 1489/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6756 - accuracy: 0.5938 - val_loss: 3.3542 - val_accuracy: 0.1562\n",
"Epoch 1490/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.7305 - accuracy: 0.5625 - val_loss: 3.3758 - val_accuracy: 0.1562\n",
"Epoch 1491/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5993 - accuracy: 0.6250 - val_loss: 3.5321 - val_accuracy: 0.1875\n",
"Epoch 1492/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7061 - accuracy: 0.4688 - val_loss: 3.3690 - val_accuracy: 0.1875\n",
"Epoch 1493/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7916 - accuracy: 0.4688 - val_loss: 3.3570 - val_accuracy: 0.1875\n",
"Epoch 1494/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6774 - accuracy: 0.5625 - val_loss: 3.3876 - val_accuracy: 0.1875\n",
"Epoch 1495/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.7396 - accuracy: 0.5312 - val_loss: 3.2613 - val_accuracy: 0.1875\n",
"Epoch 1496/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6819 - accuracy: 0.5938 - val_loss: 3.3733 - val_accuracy: 0.1875\n",
"Epoch 1497/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6094 - accuracy: 0.6562 - val_loss: 3.4777 - val_accuracy: 0.1562\n",
"Epoch 1498/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7294 - accuracy: 0.5312 - val_loss: 3.2829 - val_accuracy: 0.1562\n",
"Epoch 1499/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5824 - accuracy: 0.6250 - val_loss: 3.3556 - val_accuracy: 0.1562\n",
"Epoch 1500/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6363 - accuracy: 0.4688 - val_loss: 3.4301 - val_accuracy: 0.1562\n",
"Epoch 1501/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6445 - accuracy: 0.50 - 0s 160ms/step - loss: 0.6445 - accuracy: 0.5000 - val_loss: 3.3022 - val_accuracy: 0.1875\n",
"Epoch 1502/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6978 - accuracy: 0.4688 - val_loss: 3.4449 - val_accuracy: 0.2188\n",
"Epoch 1503/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7106 - accuracy: 0.6250 - val_loss: 3.4757 - val_accuracy: 0.1562\n",
"Epoch 1504/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6613 - accuracy: 0.6562 - val_loss: 3.5218 - val_accuracy: 0.1562\n",
"Epoch 1505/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7127 - accuracy: 0.5312 - val_loss: 3.2920 - val_accuracy: 0.1562\n",
"Epoch 1506/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6272 - accuracy: 0.6562 - val_loss: 3.5549 - val_accuracy: 0.1875\n",
"Epoch 1507/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8413 - accuracy: 0.4375 - val_loss: 3.2553 - val_accuracy: 0.2188\n",
"Epoch 1508/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5956 - accuracy: 0.6250 - val_loss: 3.5678 - val_accuracy: 0.1875\n",
"Epoch 1509/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7047 - accuracy: 0.4688 - val_loss: 3.4768 - val_accuracy: 0.1875\n",
"Epoch 1510/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6248 - accuracy: 0.5625 - val_loss: 3.4673 - val_accuracy: 0.1875\n",
"Epoch 1511/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6505 - accuracy: 0.6875 - val_loss: 3.4110 - val_accuracy: 0.1875\n",
"Epoch 1512/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5918 - accuracy: 0.6250 - val_loss: 3.4083 - val_accuracy: 0.2188\n",
"Epoch 1513/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6731 - accuracy: 0.5625 - val_loss: 3.4736 - val_accuracy: 0.1875\n",
"Epoch 1514/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6171 - accuracy: 0.5312 - val_loss: 3.4610 - val_accuracy: 0.1562\n",
"Epoch 1515/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6790 - accuracy: 0.5000 - val_loss: 3.3537 - val_accuracy: 0.2188\n",
"Epoch 1516/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6286 - accuracy: 0.6250 - val_loss: 3.5501 - val_accuracy: 0.1875\n",
"Epoch 1517/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7250 - accuracy: 0.5938 - val_loss: 3.2846 - val_accuracy: 0.2188\n",
"Epoch 1518/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8283 - accuracy: 0.5000 - val_loss: 3.7289 - val_accuracy: 0.2188\n",
"Epoch 1519/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7172 - accuracy: 0.5625 - val_loss: 3.2247 - val_accuracy: 0.2188\n",
"Epoch 1520/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7084 - accuracy: 0.5000 - val_loss: 3.5527 - val_accuracy: 0.2188\n",
"Epoch 1521/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7589 - accuracy: 0.5625 - val_loss: 3.3395 - val_accuracy: 0.1875\n",
"Epoch 1522/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6480 - accuracy: 0.5938 - val_loss: 3.4828 - val_accuracy: 0.1875\n",
"Epoch 1523/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7489 - accuracy: 0.5625 - val_loss: 3.5863 - val_accuracy: 0.1875\n",
"Epoch 1524/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6937 - accuracy: 0.5312 - val_loss: 3.4229 - val_accuracy: 0.1875\n",
"Epoch 1525/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6592 - accuracy: 0.5312 - val_loss: 3.5291 - val_accuracy: 0.1875\n",
"Epoch 1526/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7695 - accuracy: 0.4688 - val_loss: 3.5079 - val_accuracy: 0.1875\n",
"Epoch 1527/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5912 - accuracy: 0.6875 - val_loss: 3.4839 - val_accuracy: 0.1875\n",
"Epoch 1528/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6594 - accuracy: 0.5000 - val_loss: 3.5090 - val_accuracy: 0.1875\n",
"Epoch 1529/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7054 - accuracy: 0.5000 - val_loss: 3.4474 - val_accuracy: 0.2188\n",
"Epoch 1530/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.5357 - accuracy: 0.6562 - val_loss: 3.4773 - val_accuracy: 0.2188\n",
"Epoch 1531/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6573 - accuracy: 0.5312 - val_loss: 3.4596 - val_accuracy: 0.2188\n",
"Epoch 1532/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6952 - accuracy: 0.5938 - val_loss: 3.4894 - val_accuracy: 0.2188\n",
"Epoch 1533/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7126 - accuracy: 0.5000 - val_loss: 3.4947 - val_accuracy: 0.2188\n",
"Epoch 1534/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6488 - accuracy: 0.5000 - val_loss: 3.5522 - val_accuracy: 0.2188\n",
"Epoch 1535/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6596 - accuracy: 0.5938 - val_loss: 3.5873 - val_accuracy: 0.2188\n",
"Epoch 1536/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7535 - accuracy: 0.3750 - val_loss: 3.4444 - val_accuracy: 0.2188\n",
"Epoch 1537/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7216 - accuracy: 0.4375 - val_loss: 3.5270 - val_accuracy: 0.2188\n",
"Epoch 1538/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9132 - accuracy: 0.3125 - val_loss: 3.5030 - val_accuracy: 0.2188\n",
"Epoch 1539/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6082 - accuracy: 0.5312 - val_loss: 3.4860 - val_accuracy: 0.2188\n",
"Epoch 1540/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5932 - accuracy: 0.7188 - val_loss: 3.5101 - val_accuracy: 0.2188\n",
"Epoch 1541/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6169 - accuracy: 0.5625 - val_loss: 3.4932 - val_accuracy: 0.2188\n",
"Epoch 1542/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6859 - accuracy: 0.6562 - val_loss: 3.5138 - val_accuracy: 0.2188\n",
"Epoch 1543/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7327 - accuracy: 0.5000 - val_loss: 3.7012 - val_accuracy: 0.1875\n",
"Epoch 1544/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6741 - accuracy: 0.5938 - val_loss: 3.3553 - val_accuracy: 0.2188\n",
"Epoch 1545/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7307 - accuracy: 0.4688 - val_loss: 3.4923 - val_accuracy: 0.1562\n",
"Epoch 1546/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5763 - accuracy: 0.5938 - val_loss: 3.3620 - val_accuracy: 0.1875\n",
"Epoch 1547/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6102 - accuracy: 0.6250 - val_loss: 3.5397 - val_accuracy: 0.1875\n",
"Epoch 1548/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6857 - accuracy: 0.6562 - val_loss: 3.4714 - val_accuracy: 0.2188\n",
"Epoch 1549/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7059 - accuracy: 0.5312 - val_loss: 3.6570 - val_accuracy: 0.1875\n",
"Epoch 1550/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6218 - accuracy: 0.5312 - val_loss: 3.6576 - val_accuracy: 0.1875\n",
"Epoch 1551/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6813 - accuracy: 0.6562 - val_loss: 3.3573 - val_accuracy: 0.2188\n",
"Epoch 1552/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7422 - accuracy: 0.5312 - val_loss: 3.7817 - val_accuracy: 0.1562\n",
"Epoch 1553/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8177 - accuracy: 0.3438 - val_loss: 3.2667 - val_accuracy: 0.2188\n",
"Epoch 1554/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6354 - accuracy: 0.5938 - val_loss: 3.6374 - val_accuracy: 0.2500\n",
"Epoch 1555/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7174 - accuracy: 0.6250 - val_loss: 3.3359 - val_accuracy: 0.1875\n",
"Epoch 1556/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7546 - accuracy: 0.5000 - val_loss: 3.6420 - val_accuracy: 0.1875\n",
"Epoch 1557/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.6647 - accuracy: 0.5000 - val_loss: 3.3252 - val_accuracy: 0.2188\n",
"Epoch 1558/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6879 - accuracy: 0.6562 - val_loss: 3.6092 - val_accuracy: 0.1875\n",
"Epoch 1559/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7573 - accuracy: 0.5625 - val_loss: 3.2767 - val_accuracy: 0.2188\n",
"Epoch 1560/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6483 - accuracy: 0.5938 - val_loss: 3.6486 - val_accuracy: 0.2188\n",
"Epoch 1561/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6866 - accuracy: 0.5625 - val_loss: 3.3313 - val_accuracy: 0.1875\n",
"Epoch 1562/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6700 - accuracy: 0.5312 - val_loss: 3.5426 - val_accuracy: 0.1875\n",
"Epoch 1563/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7333 - accuracy: 0.4688 - val_loss: 3.4797 - val_accuracy: 0.1875\n",
"Epoch 1564/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7503 - accuracy: 0.5312 - val_loss: 3.4507 - val_accuracy: 0.1875\n",
"Epoch 1565/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6980 - accuracy: 0.5625 - val_loss: 3.4723 - val_accuracy: 0.1875\n",
"Epoch 1566/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6751 - accuracy: 0.5312 - val_loss: 3.2857 - val_accuracy: 0.1875\n",
"Epoch 1567/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7346 - accuracy: 0.5312 - val_loss: 3.7904 - val_accuracy: 0.1875\n",
"Epoch 1568/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6085 - accuracy: 0.6875 - val_loss: 3.4134 - val_accuracy: 0.1562\n",
"Epoch 1569/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6910 - accuracy: 0.5625 - val_loss: 3.7179 - val_accuracy: 0.1562\n",
"Epoch 1570/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8050 - accuracy: 0.4688 - val_loss: 3.3299 - val_accuracy: 0.1562\n",
"Epoch 1571/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6372 - accuracy: 0.6250 - val_loss: 3.5368 - val_accuracy: 0.1875\n",
"Epoch 1572/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6741 - accuracy: 0.5625 - val_loss: 3.4792 - val_accuracy: 0.1562\n",
"Epoch 1573/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8758 - accuracy: 0.5000 - val_loss: 3.4163 - val_accuracy: 0.1875\n",
"Epoch 1574/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6554 - accuracy: 0.5000 - val_loss: 3.3734 - val_accuracy: 0.1875\n",
"Epoch 1575/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6552 - accuracy: 0.5625 - val_loss: 3.3999 - val_accuracy: 0.1875\n",
"Epoch 1576/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6051 - accuracy: 0.6875 - val_loss: 3.6916 - val_accuracy: 0.1875\n",
"Epoch 1577/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6574 - accuracy: 0.5625 - val_loss: 3.2163 - val_accuracy: 0.1875\n",
"Epoch 1578/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.9370 - accuracy: 0.3125 - val_loss: 3.8054 - val_accuracy: 0.1562\n",
"Epoch 1579/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7716 - accuracy: 0.5625 - val_loss: 3.0503 - val_accuracy: 0.1562\n",
"Epoch 1580/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.1917 - accuracy: 0.3125 - val_loss: 5.0558 - val_accuracy: 0.1562\n",
"Epoch 1581/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.3094 - accuracy: 0.1562 - val_loss: 9.9068 - val_accuracy: 0.1250\n",
"Epoch 1582/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 33.6222 - accuracy: 0.0625 - val_loss: 4.8163 - val_accuracy: 0.0312\n",
"Epoch 1583/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 4.4006 - accuracy: 0.1562 - val_loss: 3.8721 - val_accuracy: 0.0312\n",
"Epoch 1584/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 4.1178 - accuracy: 0.0938 - val_loss: 3.2978 - val_accuracy: 0.0312\n",
"Epoch 1585/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 3.7196 - accuracy: 0.1250 - val_loss: 3.0808 - val_accuracy: 0.0312\n",
"Epoch 1586/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 3.6770 - accuracy: 0.1562 - val_loss: 3.0110 - val_accuracy: 0.0625\n",
"Epoch 1587/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 3.0495 - accuracy: 0.1250 - val_loss: 2.9325 - val_accuracy: 0.0625\n",
"Epoch 1588/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 3.4413 - accuracy: 0.1875 - val_loss: 2.9140 - val_accuracy: 0.0625\n",
"Epoch 1589/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.8775 - accuracy: 0.1562 - val_loss: 2.8049 - val_accuracy: 0.0312\n",
"Epoch 1590/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.7954 - accuracy: 0.2812 - val_loss: 2.7247 - val_accuracy: 0.0625\n",
"Epoch 1591/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 2.9752 - accuracy: 0.1562 - val_loss: 2.6819 - val_accuracy: 0.0625\n",
"Epoch 1592/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 3.0515 - accuracy: 0.1562 - val_loss: 2.7545 - val_accuracy: 0.0625\n",
"Epoch 1593/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 2.9099 - accuracy: 0.1562 - val_loss: 2.7701 - val_accuracy: 0.0625\n",
"Epoch 1594/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.4904 - accuracy: 0.0625 - val_loss: 2.7433 - val_accuracy: 0.0625\n",
"Epoch 1595/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.7221 - accuracy: 0.1562 - val_loss: 2.7973 - val_accuracy: 0.0312\n",
"Epoch 1596/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 2.4402 - accuracy: 0.0938 - val_loss: 2.7516 - val_accuracy: 0.0938\n",
"Epoch 1597/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.4674 - accuracy: 0.0625 - val_loss: 2.7284 - val_accuracy: 0.1250\n",
"Epoch 1598/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.5514 - accuracy: 0.1875 - val_loss: 2.7801 - val_accuracy: 0.1250\n",
"Epoch 1599/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 2.2301 - accuracy: 0.1562 - val_loss: 2.7086 - val_accuracy: 0.0938\n",
"Epoch 1600/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.3997 - accuracy: 0.3125 - val_loss: 2.9120 - val_accuracy: 0.0625\n",
"Epoch 1601/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.2586 - accuracy: 0.1250 - val_loss: 2.9287 - val_accuracy: 0.0625\n",
"Epoch 1602/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 2.3723 - accuracy: 0.1250 - val_loss: 2.9760 - val_accuracy: 0.0625\n",
"Epoch 1603/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.4573 - accuracy: 0.2188 - val_loss: 2.8939 - val_accuracy: 0.0625\n",
"Epoch 1604/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.2325 - accuracy: 0.1875 - val_loss: 2.8862 - val_accuracy: 0.0312\n",
"Epoch 1605/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.4001 - accuracy: 0.1250 - val_loss: 2.7769 - val_accuracy: 0.0312\n",
"Epoch 1606/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.2240 - accuracy: 0.2188 - val_loss: 3.0053 - val_accuracy: 0.0312\n",
"Epoch 1607/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.2334 - accuracy: 0.0625 - val_loss: 2.9883 - val_accuracy: 0.0312\n",
"Epoch 1608/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 2.0552 - accuracy: 0.1250 - val_loss: 2.8904 - val_accuracy: 0.0312\n",
"Epoch 1609/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.4294 - accuracy: 0.1562 - val_loss: 2.9724 - val_accuracy: 0.0312\n",
"Epoch 1610/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.1334 - accuracy: 0.2812 - val_loss: 2.8784 - val_accuracy: 0.0312\n",
"Epoch 1611/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.1414 - accuracy: 0.1250 - val_loss: 2.8416 - val_accuracy: 0.0312\n",
"Epoch 1612/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.9714 - accuracy: 0.2500 - val_loss: 2.8386 - val_accuracy: 0.0312\n",
"Epoch 1613/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.3933 - accuracy: 0.1250 - val_loss: 2.9110 - val_accuracy: 0.0312\n",
"Epoch 1614/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 2.0998 - accuracy: 0.1250 - val_loss: 2.9547 - val_accuracy: 0.0312\n",
"Epoch 1615/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 2.2515 - accuracy: 0.1562 - val_loss: 2.8513 - val_accuracy: 0.0312\n",
"Epoch 1616/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.0306 - accuracy: 0.1875 - val_loss: 2.8497 - val_accuracy: 0.0312\n",
"Epoch 1617/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.1480 - accuracy: 0.1875 - val_loss: 2.8858 - val_accuracy: 0.0312\n",
"Epoch 1618/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.8887 - accuracy: 0.2500 - val_loss: 2.8674 - val_accuracy: 0.0312\n",
"Epoch 1619/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.0492 - accuracy: 0.2188 - val_loss: 2.9559 - val_accuracy: 0.0312\n",
"Epoch 1620/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.1736 - accuracy: 0.1875 - val_loss: 2.9773 - val_accuracy: 0.0312\n",
"Epoch 1621/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.7396 - accuracy: 0.1250 - val_loss: 2.9965 - val_accuracy: 0.0312\n",
"Epoch 1622/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 2.0528 - accuracy: 0.1250 - val_loss: 3.0258 - val_accuracy: 0.0312\n",
"Epoch 1623/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.7777 - accuracy: 0.1562 - val_loss: 2.9465 - val_accuracy: 0.0312\n",
"Epoch 1624/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.1379 - accuracy: 0.2500 - val_loss: 3.0301 - val_accuracy: 0.0625\n",
"Epoch 1625/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.0748 - accuracy: 0.1562 - val_loss: 2.9398 - val_accuracy: 0.0312\n",
"Epoch 1626/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 2.2892 - accuracy: 0.1875 - val_loss: 3.0026 - val_accuracy: 0.0312\n",
"Epoch 1627/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.7821 - accuracy: 0.2500 - val_loss: 2.9735 - val_accuracy: 0.0312\n",
"Epoch 1628/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.5828 - accuracy: 0.3125 - val_loss: 2.9372 - val_accuracy: 0.0625\n",
"Epoch 1629/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.5718 - accuracy: 0.2188 - val_loss: 2.9883 - val_accuracy: 0.0312\n",
"Epoch 1630/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.9982 - accuracy: 0.0938 - val_loss: 2.9044 - val_accuracy: 0.0625\n",
"Epoch 1631/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.7866 - accuracy: 0.1250 - val_loss: 2.9526 - val_accuracy: 0.0625\n",
"Epoch 1632/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.6275 - accuracy: 0.1562 - val_loss: 2.9538 - val_accuracy: 0.0938\n",
"Epoch 1633/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.5840 - accuracy: 0.2500 - val_loss: 3.0087 - val_accuracy: 0.0938\n",
"Epoch 1634/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.4326 - accuracy: 0.2812 - val_loss: 3.0204 - val_accuracy: 0.0938\n",
"Epoch 1635/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.4890 - accuracy: 0.2812 - val_loss: 3.0948 - val_accuracy: 0.0625\n",
"Epoch 1636/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.6080 - accuracy: 0.1562 - val_loss: 3.0458 - val_accuracy: 0.0625\n",
"Epoch 1637/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.7765 - accuracy: 0.1250 - val_loss: 3.0227 - val_accuracy: 0.0938\n",
"Epoch 1638/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.4348 - accuracy: 0.3125 - val_loss: 3.0078 - val_accuracy: 0.0938\n",
"Epoch 1639/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.7515 - accuracy: 0.1875 - val_loss: 3.0195 - val_accuracy: 0.0938\n",
"Epoch 1640/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.7239 - accuracy: 0.3125 - val_loss: 3.1377 - val_accuracy: 0.0938\n",
"Epoch 1641/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.8594 - accuracy: 0.1875 - val_loss: 3.0171 - val_accuracy: 0.0938\n",
"Epoch 1642/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.6427 - accuracy: 0.2500 - val_loss: 2.9434 - val_accuracy: 0.0938\n",
"Epoch 1643/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.8892 - accuracy: 0.1875 - val_loss: 2.9267 - val_accuracy: 0.0938\n",
"Epoch 1644/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.6099 - accuracy: 0.1562 - val_loss: 2.9543 - val_accuracy: 0.0938\n",
"Epoch 1645/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.5944 - accuracy: 0.1875 - val_loss: 2.8727 - val_accuracy: 0.1250\n",
"Epoch 1646/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.6310 - accuracy: 0.1875 - val_loss: 2.8373 - val_accuracy: 0.0938\n",
"Epoch 1647/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.6566 - accuracy: 0.1562 - val_loss: 2.8890 - val_accuracy: 0.1250\n",
"Epoch 1648/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.6518 - accuracy: 0.2812 - val_loss: 3.0127 - val_accuracy: 0.1250\n",
"Epoch 1649/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.9549 - accuracy: 0.1562 - val_loss: 2.9029 - val_accuracy: 0.0938\n",
"Epoch 1650/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.5978 - accuracy: 0.1875 - val_loss: 2.9326 - val_accuracy: 0.0938\n",
"Epoch 1651/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.3380 - accuracy: 0.2500 - val_loss: 2.9177 - val_accuracy: 0.0938\n",
"Epoch 1652/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.3270 - accuracy: 0.2812 - val_loss: 3.0647 - val_accuracy: 0.0938\n",
"Epoch 1653/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.7624 - accuracy: 0.3125 - val_loss: 3.4618 - val_accuracy: 0.1250\n",
"Epoch 1654/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.5645 - accuracy: 0.1875 - val_loss: 3.1318 - val_accuracy: 0.0938\n",
"Epoch 1655/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.6278 - accuracy: 0.1562 - val_loss: 3.1052 - val_accuracy: 0.0938\n",
"Epoch 1656/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.8929 - accuracy: 0.1562 - val_loss: 3.3204 - val_accuracy: 0.0938\n",
"Epoch 1657/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 1.5326 - accuracy: 0.1875 - val_loss: 2.9330 - val_accuracy: 0.0938\n",
"Epoch 1658/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.7844 - accuracy: 0.2500 - val_loss: 3.1191 - val_accuracy: 0.0938\n",
"Epoch 1659/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.6804 - accuracy: 0.2188 - val_loss: 3.0806 - val_accuracy: 0.0938\n",
"Epoch 1660/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.4626 - accuracy: 0.2188 - val_loss: 2.8760 - val_accuracy: 0.0938\n",
"Epoch 1661/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.2278 - accuracy: 0.2500 - val_loss: 2.7938 - val_accuracy: 0.0938\n",
"Epoch 1662/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.2355 - accuracy: 0.2500 - val_loss: 2.8082 - val_accuracy: 0.1250\n",
"Epoch 1663/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.4081 - accuracy: 0.2812 - val_loss: 2.8581 - val_accuracy: 0.0938\n",
"Epoch 1664/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.7705 - accuracy: 0.1562 - val_loss: 3.5722 - val_accuracy: 0.0938\n",
"Epoch 1665/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.8773 - accuracy: 0.2500 - val_loss: 2.8421 - val_accuracy: 0.0938\n",
"Epoch 1666/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.8548 - accuracy: 0.1875 - val_loss: 3.1211 - val_accuracy: 0.0625\n",
"Epoch 1667/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.4560 - accuracy: 0.3438 - val_loss: 2.9969 - val_accuracy: 0.0938\n",
"Epoch 1668/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.3139 - accuracy: 0.1875 - val_loss: 2.7992 - val_accuracy: 0.1250\n",
"Epoch 1669/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.6434 - accuracy: 0.3438 - val_loss: 3.0340 - val_accuracy: 0.0938\n",
"Epoch 1670/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.2880 - accuracy: 0.2500 - val_loss: 3.1466 - val_accuracy: 0.1562\n",
"Epoch 1671/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.7422 - accuracy: 0.2812 - val_loss: 3.8062 - val_accuracy: 0.1250\n",
"Epoch 1672/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.1879 - accuracy: 0.1875 - val_loss: 3.0700 - val_accuracy: 0.0938\n",
"Epoch 1673/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.9813 - accuracy: 0.1562 - val_loss: 3.1405 - val_accuracy: 0.1562\n",
"Epoch 1674/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.4740 - accuracy: 0.2188 - val_loss: 3.0448 - val_accuracy: 0.1562\n",
"Epoch 1675/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.3113 - accuracy: 0.2500 - val_loss: 3.0898 - val_accuracy: 0.1562\n",
"Epoch 1676/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.6794 - accuracy: 0.2500 - val_loss: 2.8968 - val_accuracy: 0.1250\n",
"Epoch 1677/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.5947 - accuracy: 0.3125 - val_loss: 2.9159 - val_accuracy: 0.1562\n",
"Epoch 1678/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.5034 - accuracy: 0.2188 - val_loss: 3.0455 - val_accuracy: 0.1562\n",
"Epoch 1679/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.6765 - accuracy: 0.1562 - val_loss: 3.1637 - val_accuracy: 0.1875\n",
"Epoch 1680/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.5940 - accuracy: 0.2500 - val_loss: 3.2511 - val_accuracy: 0.0312\n",
"Epoch 1681/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.3527 - accuracy: 0.3750 - val_loss: 2.9356 - val_accuracy: 0.1250\n",
"Epoch 1682/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.4047 - accuracy: 0.3125 - val_loss: 2.7730 - val_accuracy: 0.1250\n",
"Epoch 1683/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.3958 - accuracy: 0.2812 - val_loss: 2.8287 - val_accuracy: 0.1250\n",
"Epoch 1684/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.5394 - accuracy: 0.3438 - val_loss: 2.7747 - val_accuracy: 0.1250\n",
"Epoch 1685/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.9230 - accuracy: 0.2188 - val_loss: 4.4030 - val_accuracy: 0.1250\n",
"Epoch 1686/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.9601 - accuracy: 0.2188 - val_loss: 3.2200 - val_accuracy: 0.1562\n",
"Epoch 1687/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.4294 - accuracy: 0.3125 - val_loss: 3.0587 - val_accuracy: 0.1875\n",
"Epoch 1688/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.3450 - accuracy: 0.3750 - val_loss: 2.8366 - val_accuracy: 0.2188\n",
"Epoch 1689/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.5348 - accuracy: 0.2188 - val_loss: 2.8338 - val_accuracy: 0.1875\n",
"Epoch 1690/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.3285 - accuracy: 0.5000 - val_loss: 2.9254 - val_accuracy: 0.1562\n",
"Epoch 1691/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.7066 - accuracy: 0.3125 - val_loss: 2.9011 - val_accuracy: 0.1562\n",
"Epoch 1692/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.9903 - accuracy: 0.1875 - val_loss: 3.1268 - val_accuracy: 0.1562\n",
"Epoch 1693/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.0052 - accuracy: 0.2500 - val_loss: 3.0923 - val_accuracy: 0.2188\n",
"Epoch 1694/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.8745 - accuracy: 0.3125 - val_loss: 3.2020 - val_accuracy: 0.1875\n",
"Epoch 1695/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.5098 - accuracy: 0.2188 - val_loss: 2.9877 - val_accuracy: 0.1562\n",
"Epoch 1696/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.3117 - accuracy: 0.2500 - val_loss: 2.8100 - val_accuracy: 0.1562\n",
"Epoch 1697/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.2387 - accuracy: 0.3125 - val_loss: 2.8197 - val_accuracy: 0.1562\n",
"Epoch 1698/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.5959 - accuracy: 0.4062 - val_loss: 4.1760 - val_accuracy: 0.1562\n",
"Epoch 1699/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.5707 - accuracy: 0.1562 - val_loss: 3.3288 - val_accuracy: 0.1875\n",
"Epoch 1700/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.4406 - accuracy: 0.2500 - val_loss: 3.0624 - val_accuracy: 0.1250\n",
"Epoch 1701/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.4212 - accuracy: 0.2188 - val_loss: 3.0886 - val_accuracy: 0.1562\n",
"Epoch 1702/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.2987 - accuracy: 0.3438 - val_loss: 2.9520 - val_accuracy: 0.1562\n",
"Epoch 1703/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.0338 - accuracy: 0.3438 - val_loss: 3.0491 - val_accuracy: 0.1562\n",
"Epoch 1704/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.7569 - accuracy: 0.3438 - val_loss: 3.5472 - val_accuracy: 0.0938\n",
"Epoch 1705/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.2521 - accuracy: 0.2188 - val_loss: 3.2223 - val_accuracy: 0.0938\n",
"Epoch 1706/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.1039 - accuracy: 0.2812 - val_loss: 3.0809 - val_accuracy: 0.0938\n",
"Epoch 1707/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 1.6307 - accuracy: 0.2812 - val_loss: 3.1754 - val_accuracy: 0.0938\n",
"Epoch 1708/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 1.2057 - accuracy: 0.2500 - val_loss: 3.2023 - val_accuracy: 0.1250\n",
"Epoch 1709/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.3285 - accuracy: 0.2500 - val_loss: 2.9262 - val_accuracy: 0.1250\n",
"Epoch 1710/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.2316 - accuracy: 0.3125 - val_loss: 2.8857 - val_accuracy: 0.1250\n",
"Epoch 1711/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.2022 - accuracy: 0.3125 - val_loss: 3.1191 - val_accuracy: 0.1250\n",
"Epoch 1712/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.4539 - accuracy: 0.3125 - val_loss: 3.2754 - val_accuracy: 0.1250\n",
"Epoch 1713/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 1.3530 - accuracy: 0.2188 - val_loss: 2.9218 - val_accuracy: 0.1250\n",
"Epoch 1714/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 1.0616 - accuracy: 0.3438 - val_loss: 2.9773 - val_accuracy: 0.1250\n",
"Epoch 1715/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.5219 - accuracy: 0.3125 - val_loss: 3.7315 - val_accuracy: 0.1250\n",
"Epoch 1716/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.3967 - accuracy: 0.2500 - val_loss: 2.9191 - val_accuracy: 0.1250\n",
"Epoch 1717/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.1796 - accuracy: 0.2500 - val_loss: 2.8712 - val_accuracy: 0.1562\n",
"Epoch 1718/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.1452 - accuracy: 0.2500 - val_loss: 2.8778 - val_accuracy: 0.1562\n",
"Epoch 1719/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.1433 - accuracy: 0.2812 - val_loss: 3.0854 - val_accuracy: 0.1562\n",
"Epoch 1720/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 2.8665 - accuracy: 0.3125 - val_loss: 4.3841 - val_accuracy: 0.0938\n",
"Epoch 1721/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.7139 - accuracy: 0.1250 - val_loss: 3.4202 - val_accuracy: 0.1562\n",
"Epoch 1722/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.3294 - accuracy: 0.2500 - val_loss: 3.2544 - val_accuracy: 0.1562\n",
"Epoch 1723/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.5767 - accuracy: 0.2500 - val_loss: 3.0893 - val_accuracy: 0.1562\n",
"Epoch 1724/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.2568 - accuracy: 0.3750 - val_loss: 3.1336 - val_accuracy: 0.0938\n",
"Epoch 1725/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.8545 - accuracy: 0.3438 - val_loss: 3.2948 - val_accuracy: 0.0938\n",
"Epoch 1726/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.5736 - accuracy: 0.2500 - val_loss: 3.1265 - val_accuracy: 0.0938\n",
"Epoch 1727/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.5222 - accuracy: 0.2812 - val_loss: 3.1605 - val_accuracy: 0.0938\n",
"Epoch 1728/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 1.1700 - accuracy: 0.3750 - val_loss: 2.9224 - val_accuracy: 0.0938\n",
"Epoch 1729/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.8588 - accuracy: 0.3125 - val_loss: 3.7069 - val_accuracy: 0.0625\n",
"Epoch 1730/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.2463 - accuracy: 0.2500 - val_loss: 3.0370 - val_accuracy: 0.0938\n",
"Epoch 1731/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.3406 - accuracy: 0.2188 - val_loss: 3.3060 - val_accuracy: 0.0938\n",
"Epoch 1732/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.4162 - accuracy: 0.2812 - val_loss: 2.9173 - val_accuracy: 0.0625\n",
"Epoch 1733/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.3399 - accuracy: 0.3750 - val_loss: 3.8796 - val_accuracy: 0.0938\n",
"Epoch 1734/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.5781 - accuracy: 0.2500 - val_loss: 2.9514 - val_accuracy: 0.1250\n",
"Epoch 1735/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0800 - accuracy: 0.3438 - val_loss: 2.9453 - val_accuracy: 0.1250\n",
"Epoch 1736/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.0853 - accuracy: 0.3750 - val_loss: 3.2096 - val_accuracy: 0.1250\n",
"Epoch 1737/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.4803 - accuracy: 0.2500 - val_loss: 3.2167 - val_accuracy: 0.0625\n",
"Epoch 1738/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.1098 - accuracy: 0.4688 - val_loss: 3.1800 - val_accuracy: 0.0938\n",
"Epoch 1739/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.1013 - accuracy: 0.2500 - val_loss: 3.0660 - val_accuracy: 0.0938\n",
"Epoch 1740/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.2887 - accuracy: 0.5312 - val_loss: 3.3959 - val_accuracy: 0.1250\n",
"Epoch 1741/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.2518 - accuracy: 0.3125 - val_loss: 3.3541 - val_accuracy: 0.1250\n",
"Epoch 1742/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.1260 - accuracy: 0.2812 - val_loss: 3.1218 - val_accuracy: 0.1250\n",
"Epoch 1743/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.4027 - accuracy: 0.4375 - val_loss: 3.2428 - val_accuracy: 0.0938\n",
"Epoch 1744/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9086 - accuracy: 0.4062 - val_loss: 3.1257 - val_accuracy: 0.0938\n",
"Epoch 1745/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.2821 - accuracy: 0.4375 - val_loss: 3.1986 - val_accuracy: 0.1250\n",
"Epoch 1746/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.0364 - accuracy: 0.3125 - val_loss: 3.1195 - val_accuracy: 0.0938\n",
"Epoch 1747/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.1388 - accuracy: 0.3438 - val_loss: 3.2346 - val_accuracy: 0.0938\n",
"Epoch 1748/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9825 - accuracy: 0.4062 - val_loss: 2.9434 - val_accuracy: 0.0938\n",
"Epoch 1749/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.4899 - accuracy: 0.3750 - val_loss: 3.2715 - val_accuracy: 0.0938\n",
"Epoch 1750/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.2203 - accuracy: 0.3750 - val_loss: 3.0181 - val_accuracy: 0.1250\n",
"Epoch 1751/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.0693 - accuracy: 0.4062 - val_loss: 3.0316 - val_accuracy: 0.0938\n",
"Epoch 1752/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 1.1018 - accuracy: 0.2812 - val_loss: 3.0391 - val_accuracy: 0.1250\n",
"Epoch 1753/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.1226 - accuracy: 0.2500 - val_loss: 3.0092 - val_accuracy: 0.0938\n",
"Epoch 1754/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.5106 - accuracy: 0.3438 - val_loss: 3.2031 - val_accuracy: 0.1250\n",
"Epoch 1755/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.2271 - accuracy: 0.3125 - val_loss: 3.1826 - val_accuracy: 0.1250\n",
"Epoch 1756/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.4816 - accuracy: 0.4375 - val_loss: 3.3248 - val_accuracy: 0.1250\n",
"Epoch 1757/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0393 - accuracy: 0.3750 - val_loss: 3.3865 - val_accuracy: 0.1250\n",
"Epoch 1758/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.2636 - accuracy: 0.2500 - val_loss: 3.3056 - val_accuracy: 0.1250\n",
"Epoch 1759/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.0834 - accuracy: 0.4062 - val_loss: 3.3621 - val_accuracy: 0.1562\n",
"Epoch 1760/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8808 - accuracy: 0.4062 - val_loss: 3.2468 - val_accuracy: 0.1250\n",
"Epoch 1761/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.2159 - accuracy: 0.4375 - val_loss: 3.6389 - val_accuracy: 0.1250\n",
"Epoch 1762/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.0795 - accuracy: 0.2812 - val_loss: 3.2273 - val_accuracy: 0.1250\n",
"Epoch 1763/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.1656 - accuracy: 0.3125 - val_loss: 3.2078 - val_accuracy: 0.1250\n",
"Epoch 1764/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.1577 - accuracy: 0.4375 - val_loss: 3.2714 - val_accuracy: 0.1562\n",
"Epoch 1765/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9842 - accuracy: 0.4062 - val_loss: 3.2658 - val_accuracy: 0.1250\n",
"Epoch 1766/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.9092 - accuracy: 0.4688 - val_loss: 3.1541 - val_accuracy: 0.1250\n",
"Epoch 1767/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9972 - accuracy: 0.4062 - val_loss: 3.0803 - val_accuracy: 0.1250\n",
"Epoch 1768/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.0261 - accuracy: 0.4375 - val_loss: 3.0383 - val_accuracy: 0.1562\n",
"Epoch 1769/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.9856 - accuracy: 0.4688 - val_loss: 3.0248 - val_accuracy: 0.1250\n",
"Epoch 1770/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.9485 - accuracy: 0.5938 - val_loss: 3.0567 - val_accuracy: 0.1250\n",
"Epoch 1771/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8892 - accuracy: 0.4688 - val_loss: 3.0261 - val_accuracy: 0.1250\n",
"Epoch 1772/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9565 - accuracy: 0.4062 - val_loss: 2.9685 - val_accuracy: 0.1250\n",
"Epoch 1773/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.2026 - accuracy: 0.4375 - val_loss: 3.1628 - val_accuracy: 0.1562\n",
"Epoch 1774/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9852 - accuracy: 0.5000 - val_loss: 3.7494 - val_accuracy: 0.1562\n",
"Epoch 1775/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.0382 - accuracy: 0.3750 - val_loss: 3.2248 - val_accuracy: 0.1562\n",
"Epoch 1776/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9174 - accuracy: 0.3750 - val_loss: 3.1776 - val_accuracy: 0.1250\n",
"Epoch 1777/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9365 - accuracy: 0.5000 - val_loss: 3.0591 - val_accuracy: 0.1250\n",
"Epoch 1778/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.0750 - accuracy: 0.4688 - val_loss: 3.2843 - val_accuracy: 0.1562\n",
"Epoch 1779/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9053 - accuracy: 0.5312 - val_loss: 3.2032 - val_accuracy: 0.1562\n",
"Epoch 1780/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8076 - accuracy: 0.5000 - val_loss: 3.2395 - val_accuracy: 0.1250\n",
"Epoch 1781/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.9555 - accuracy: 0.5000 - val_loss: 3.2355 - val_accuracy: 0.1562\n",
"Epoch 1782/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9746 - accuracy: 0.4688 - val_loss: 3.1699 - val_accuracy: 0.1562\n",
"Epoch 1783/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.9100 - accuracy: 0.3750 - val_loss: 3.2062 - val_accuracy: 0.1250\n",
"Epoch 1784/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.9066 - accuracy: 0.5000 - val_loss: 3.1258 - val_accuracy: 0.1562\n",
"Epoch 1785/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.8478 - accuracy: 0.5000 - val_loss: 3.0959 - val_accuracy: 0.1250\n",
"Epoch 1786/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.9017 - accuracy: 0.5000 - val_loss: 3.2752 - val_accuracy: 0.1562\n",
"Epoch 1787/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7966 - accuracy: 0.5000 - val_loss: 3.1783 - val_accuracy: 0.1562\n",
"Epoch 1788/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8667 - accuracy: 0.4062 - val_loss: 3.3680 - val_accuracy: 0.1875\n",
"Epoch 1789/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8837 - accuracy: 0.5312 - val_loss: 3.1748 - val_accuracy: 0.1875\n",
"Epoch 1790/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.0531 - accuracy: 0.5312 - val_loss: 4.0785 - val_accuracy: 0.1562\n",
"Epoch 1791/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.2551 - accuracy: 0.3438 - val_loss: 2.9165 - val_accuracy: 0.2188\n",
"Epoch 1792/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.0243 - accuracy: 0.5000 - val_loss: 3.2082 - val_accuracy: 0.1875\n",
"Epoch 1793/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7527 - accuracy: 0.5938 - val_loss: 3.1652 - val_accuracy: 0.1875\n",
"Epoch 1794/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8307 - accuracy: 0.5938 - val_loss: 3.1668 - val_accuracy: 0.1875\n",
"Epoch 1795/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8627 - accuracy: 0.5938 - val_loss: 3.0805 - val_accuracy: 0.2188\n",
"Epoch 1796/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7918 - accuracy: 0.6562 - val_loss: 3.1723 - val_accuracy: 0.1875\n",
"Epoch 1797/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7977 - accuracy: 0.5625 - val_loss: 3.1046 - val_accuracy: 0.1875\n",
"Epoch 1798/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.1232 - accuracy: 0.2812 - val_loss: 3.1136 - val_accuracy: 0.1875\n",
"Epoch 1799/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.9481 - accuracy: 0.3750 - val_loss: 3.1278 - val_accuracy: 0.1875\n",
"Epoch 1800/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.9169 - accuracy: 0.5312 - val_loss: 3.3003 - val_accuracy: 0.1875\n",
"Epoch 1801/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7790 - accuracy: 0.4062 - val_loss: 3.2187 - val_accuracy: 0.2188\n",
"Epoch 1802/5000\n",
"1/1 [==============================] - 0s 207ms/step - loss: 0.7492 - accuracy: 0.5312 - val_loss: 3.2275 - val_accuracy: 0.1875\n",
"Epoch 1803/5000\n",
"1/1 [==============================] - 0s 208ms/step - loss: 0.7854 - accuracy: 0.4688 - val_loss: 3.1487 - val_accuracy: 0.1875\n",
"Epoch 1804/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7805 - accuracy: 0.5625 - val_loss: 3.3015 - val_accuracy: 0.1875\n",
"Epoch 1805/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8173 - accuracy: 0.5312 - val_loss: 3.1227 - val_accuracy: 0.2188\n",
"Epoch 1806/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8230 - accuracy: 0.5312 - val_loss: 3.3343 - val_accuracy: 0.2188\n",
"Epoch 1807/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8605 - accuracy: 0.5312 - val_loss: 3.2426 - val_accuracy: 0.2188\n",
"Epoch 1808/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8364 - accuracy: 0.5000 - val_loss: 3.3671 - val_accuracy: 0.1875\n",
"Epoch 1809/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8401 - accuracy: 0.4375 - val_loss: 3.2668 - val_accuracy: 0.2188\n",
"Epoch 1810/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7897 - accuracy: 0.5000 - val_loss: 3.0907 - val_accuracy: 0.2188\n",
"Epoch 1811/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8132 - accuracy: 0.5312 - val_loss: 3.2404 - val_accuracy: 0.1875\n",
"Epoch 1812/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7829 - accuracy: 0.5312 - val_loss: 3.2267 - val_accuracy: 0.1875\n",
"Epoch 1813/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6309 - accuracy: 0.6875 - val_loss: 3.2022 - val_accuracy: 0.2188\n",
"Epoch 1814/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.8366 - accuracy: 0.5312 - val_loss: 3.4758 - val_accuracy: 0.2188\n",
"Epoch 1815/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.8034 - accuracy: 0.5938 - val_loss: 3.2558 - val_accuracy: 0.2188\n",
"Epoch 1816/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7143 - accuracy: 0.5312 - val_loss: 3.2634 - val_accuracy: 0.2188\n",
"Epoch 1817/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.2448 - accuracy: 0.4375 - val_loss: 5.0695 - val_accuracy: 0.1875\n",
"Epoch 1818/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.9110 - accuracy: 0.2812 - val_loss: 2.7232 - val_accuracy: 0.2500\n",
"Epoch 1819/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 1.6732 - accuracy: 0.3750 - val_loss: 6.0544 - val_accuracy: 0.0625\n",
"Epoch 1820/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 2.7048 - accuracy: 0.2500 - val_loss: 3.1055 - val_accuracy: 0.1250\n",
"Epoch 1821/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0837 - accuracy: 0.4375 - val_loss: 3.3664 - val_accuracy: 0.0938\n",
"Epoch 1822/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8883 - accuracy: 0.3438 - val_loss: 3.3542 - val_accuracy: 0.1250\n",
"Epoch 1823/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8524 - accuracy: 0.4688 - val_loss: 3.3716 - val_accuracy: 0.0938\n",
"Epoch 1824/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9040 - accuracy: 0.5312 - val_loss: 3.4628 - val_accuracy: 0.1562\n",
"Epoch 1825/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8241 - accuracy: 0.5625 - val_loss: 3.2691 - val_accuracy: 0.1562\n",
"Epoch 1826/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8347 - accuracy: 0.5000 - val_loss: 3.2448 - val_accuracy: 0.1562\n",
"Epoch 1827/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8327 - accuracy: 0.5000 - val_loss: 3.2698 - val_accuracy: 0.1562\n",
"Epoch 1828/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8943 - accuracy: 0.5000 - val_loss: 3.3155 - val_accuracy: 0.1562\n",
"Epoch 1829/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8192 - accuracy: 0.4062 - val_loss: 3.4719 - val_accuracy: 0.1562\n",
"Epoch 1830/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7774 - accuracy: 0.5625 - val_loss: 3.2973 - val_accuracy: 0.1562\n",
"Epoch 1831/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7972 - accuracy: 0.5938 - val_loss: 3.3188 - val_accuracy: 0.1562\n",
"Epoch 1832/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.1970 - accuracy: 0.5000 - val_loss: 3.1588 - val_accuracy: 0.1562\n",
"Epoch 1833/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8420 - accuracy: 0.4688 - val_loss: 3.3571 - val_accuracy: 0.1562\n",
"Epoch 1834/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8372 - accuracy: 0.5000 - val_loss: 3.3352 - val_accuracy: 0.1562\n",
"Epoch 1835/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8106 - accuracy: 0.5000 - val_loss: 3.2871 - val_accuracy: 0.1562\n",
"Epoch 1836/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7303 - accuracy: 0.5625 - val_loss: 3.2530 - val_accuracy: 0.1875\n",
"Epoch 1837/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8114 - accuracy: 0.5625 - val_loss: 3.1988 - val_accuracy: 0.1875\n",
"Epoch 1838/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7520 - accuracy: 0.5625 - val_loss: 3.3876 - val_accuracy: 0.1562\n",
"Epoch 1839/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6212 - accuracy: 0.5625 - val_loss: 3.2764 - val_accuracy: 0.1562\n",
"Epoch 1840/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7900 - accuracy: 0.5000 - val_loss: 3.0925 - val_accuracy: 0.1875\n",
"Epoch 1841/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8209 - accuracy: 0.4375 - val_loss: 3.4931 - val_accuracy: 0.1562\n",
"Epoch 1842/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7150 - accuracy: 0.5625 - val_loss: 3.3553 - val_accuracy: 0.1562\n",
"Epoch 1843/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7769 - accuracy: 0.4375 - val_loss: 3.1903 - val_accuracy: 0.1562\n",
"Epoch 1844/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7497 - accuracy: 0.6562 - val_loss: 3.1504 - val_accuracy: 0.1875\n",
"Epoch 1845/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8180 - accuracy: 0.4688 - val_loss: 3.3545 - val_accuracy: 0.1562\n",
"Epoch 1846/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.8015 - accuracy: 0.5000 - val_loss: 3.1301 - val_accuracy: 0.1875\n",
"Epoch 1847/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7010 - accuracy: 0.5938 - val_loss: 3.2535 - val_accuracy: 0.1875\n",
"Epoch 1848/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7432 - accuracy: 0.5312 - val_loss: 3.1620 - val_accuracy: 0.2188\n",
"Epoch 1849/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7997 - accuracy: 0.5000 - val_loss: 3.2833 - val_accuracy: 0.1875\n",
"Epoch 1850/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6253 - accuracy: 0.6562 - val_loss: 3.2612 - val_accuracy: 0.1875\n",
"Epoch 1851/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7439 - accuracy: 0.5625 - val_loss: 3.3115 - val_accuracy: 0.1875\n",
"Epoch 1852/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7608 - accuracy: 0.5625 - val_loss: 3.2021 - val_accuracy: 0.2188\n",
"Epoch 1853/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8460 - accuracy: 0.4688 - val_loss: 3.2869 - val_accuracy: 0.1562\n",
"Epoch 1854/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7828 - accuracy: 0.5938 - val_loss: 3.2807 - val_accuracy: 0.1875\n",
"Epoch 1855/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7521 - accuracy: 0.5000 - val_loss: 3.2334 - val_accuracy: 0.2188\n",
"Epoch 1856/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6442 - accuracy: 0.6250 - val_loss: 3.1712 - val_accuracy: 0.2188\n",
"Epoch 1857/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7856 - accuracy: 0.5312 - val_loss: 3.3244 - val_accuracy: 0.2188\n",
"Epoch 1858/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.9963 - accuracy: 0.4688 - val_loss: 3.5903 - val_accuracy: 0.2188\n",
"Epoch 1859/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7019 - accuracy: 0.5938 - val_loss: 3.4442 - val_accuracy: 0.2188\n",
"Epoch 1860/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9222 - accuracy: 0.4062 - val_loss: 3.3137 - val_accuracy: 0.2500\n",
"Epoch 1861/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7258 - accuracy: 0.5625 - val_loss: 3.3658 - val_accuracy: 0.2500\n",
"Epoch 1862/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6891 - accuracy: 0.5938 - val_loss: 3.4265 - val_accuracy: 0.2188\n",
"Epoch 1863/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7538 - accuracy: 0.5938 - val_loss: 3.3329 - val_accuracy: 0.2188\n",
"Epoch 1864/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7640 - accuracy: 0.5938 - val_loss: 3.3263 - val_accuracy: 0.2188\n",
"Epoch 1865/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7134 - accuracy: 0.5312 - val_loss: 3.2426 - val_accuracy: 0.2188\n",
"Epoch 1866/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7088 - accuracy: 0.6562 - val_loss: 3.3633 - val_accuracy: 0.2188\n",
"Epoch 1867/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6916 - accuracy: 0.5312 - val_loss: 3.3822 - val_accuracy: 0.2188\n",
"Epoch 1868/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8125 - accuracy: 0.4688 - val_loss: 3.3550 - val_accuracy: 0.2188\n",
"Epoch 1869/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7881 - accuracy: 0.4688 - val_loss: 3.3432 - val_accuracy: 0.1875\n",
"Epoch 1870/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6983 - accuracy: 0.6250 - val_loss: 3.5655 - val_accuracy: 0.2188\n",
"Epoch 1871/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7317 - accuracy: 0.4688 - val_loss: 3.3647 - val_accuracy: 0.2500\n",
"Epoch 1872/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7954 - accuracy: 0.5625 - val_loss: 3.4813 - val_accuracy: 0.2188\n",
"Epoch 1873/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6754 - accuracy: 0.6562 - val_loss: 3.3693 - val_accuracy: 0.2188\n",
"Epoch 1874/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.8737 - accuracy: 0.4375 - val_loss: 3.2653 - val_accuracy: 0.2188\n",
"Epoch 1875/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7123 - accuracy: 0.5312 - val_loss: 3.4395 - val_accuracy: 0.2188\n",
"Epoch 1876/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6631 - accuracy: 0.5625 - val_loss: 3.3834 - val_accuracy: 0.1875\n",
"Epoch 1877/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7429 - accuracy: 0.5312 - val_loss: 3.3684 - val_accuracy: 0.2188\n",
"Epoch 1878/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6985 - accuracy: 0.5312 - val_loss: 3.3499 - val_accuracy: 0.1875\n",
"Epoch 1879/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7021 - accuracy: 0.6875 - val_loss: 3.4024 - val_accuracy: 0.2188\n",
"Epoch 1880/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6041 - accuracy: 0.6562 - val_loss: 3.3925 - val_accuracy: 0.2188\n",
"Epoch 1881/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.7252 - accuracy: 0.5000 - val_loss: 3.4124 - val_accuracy: 0.1875\n",
"Epoch 1882/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6435 - accuracy: 0.5938 - val_loss: 3.4364 - val_accuracy: 0.1875\n",
"Epoch 1883/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7665 - accuracy: 0.5625 - val_loss: 3.3546 - val_accuracy: 0.2188\n",
"Epoch 1884/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6378 - accuracy: 0.6250 - val_loss: 3.4274 - val_accuracy: 0.2188\n",
"Epoch 1885/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6972 - accuracy: 0.5312 - val_loss: 3.3350 - val_accuracy: 0.2188\n",
"Epoch 1886/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7714 - accuracy: 0.4688 - val_loss: 3.5748 - val_accuracy: 0.2500\n",
"Epoch 1887/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7867 - accuracy: 0.5000 - val_loss: 3.2305 - val_accuracy: 0.2500\n",
"Epoch 1888/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6396 - accuracy: 0.5000 - val_loss: 3.4146 - val_accuracy: 0.2188\n",
"Epoch 1889/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6602 - accuracy: 0.5625 - val_loss: 3.4292 - val_accuracy: 0.2188\n",
"Epoch 1890/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7120 - accuracy: 0.5938 - val_loss: 3.3373 - val_accuracy: 0.1875\n",
"Epoch 1891/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7524 - accuracy: 0.5938 - val_loss: 3.3261 - val_accuracy: 0.2188\n",
"Epoch 1892/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.8349 - accuracy: 0.4062 - val_loss: 3.3365 - val_accuracy: 0.2188\n",
"Epoch 1893/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5976 - accuracy: 0.6562 - val_loss: 3.4819 - val_accuracy: 0.2188\n",
"Epoch 1894/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7226 - accuracy: 0.6250 - val_loss: 3.2577 - val_accuracy: 0.2188\n",
"Epoch 1895/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6268 - accuracy: 0.6562 - val_loss: 3.3505 - val_accuracy: 0.2188\n",
"Epoch 1896/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7423 - accuracy: 0.5312 - val_loss: 3.3584 - val_accuracy: 0.2188\n",
"Epoch 1897/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6290 - accuracy: 0.5625 - val_loss: 3.5134 - val_accuracy: 0.2188\n",
"Epoch 1898/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7609 - accuracy: 0.4688 - val_loss: 3.3165 - val_accuracy: 0.1875\n",
"Epoch 1899/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.6793 - accuracy: 0.5312 - val_loss: 3.4730 - val_accuracy: 0.1875\n",
"Epoch 1900/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6735 - accuracy: 0.4688 - val_loss: 3.6528 - val_accuracy: 0.2500\n",
"Epoch 1901/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8069 - accuracy: 0.4688 - val_loss: 3.4069 - val_accuracy: 0.1875\n",
"Epoch 1902/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6769 - accuracy: 0.6250 - val_loss: 3.3300 - val_accuracy: 0.2188\n",
"Epoch 1903/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7273 - accuracy: 0.5000 - val_loss: 3.5016 - val_accuracy: 0.2188\n",
"Epoch 1904/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7804 - accuracy: 0.4688 - val_loss: 3.3932 - val_accuracy: 0.2188\n",
"Epoch 1905/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6748 - accuracy: 0.5625 - val_loss: 3.4267 - val_accuracy: 0.2188\n",
"Epoch 1906/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7733 - accuracy: 0.5625 - val_loss: 3.2833 - val_accuracy: 0.2188\n",
"Epoch 1907/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6695 - accuracy: 0.6250 - val_loss: 3.3521 - val_accuracy: 0.2188\n",
"Epoch 1908/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6256 - accuracy: 0.59 - 0s 167ms/step - loss: 0.6256 - accuracy: 0.5938 - val_loss: 3.4923 - val_accuracy: 0.2188\n",
"Epoch 1909/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7026 - accuracy: 0.6250 - val_loss: 3.4290 - val_accuracy: 0.2188\n",
"Epoch 1910/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6055 - accuracy: 0.5625 - val_loss: 3.4048 - val_accuracy: 0.1875\n",
"Epoch 1911/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5055 - accuracy: 0.6875 - val_loss: 3.4352 - val_accuracy: 0.1875\n",
"Epoch 1912/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7121 - accuracy: 0.6562 - val_loss: 3.2428 - val_accuracy: 0.2188\n",
"Epoch 1913/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7749 - accuracy: 0.5312 - val_loss: 3.5730 - val_accuracy: 0.1875\n",
"Epoch 1914/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6666 - accuracy: 0.5938 - val_loss: 3.3907 - val_accuracy: 0.2188\n",
"Epoch 1915/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6911 - accuracy: 0.6875 - val_loss: 3.4252 - val_accuracy: 0.1875\n",
"Epoch 1916/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7091 - accuracy: 0.6250 - val_loss: 3.4474 - val_accuracy: 0.2188\n",
"Epoch 1917/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7214 - accuracy: 0.5312 - val_loss: 3.4774 - val_accuracy: 0.2188\n",
"Epoch 1918/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7207 - accuracy: 0.6250 - val_loss: 3.4908 - val_accuracy: 0.1562\n",
"Epoch 1919/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6916 - accuracy: 0.5000 - val_loss: 3.4564 - val_accuracy: 0.1562\n",
"Epoch 1920/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6554 - accuracy: 0.5000 - val_loss: 3.4800 - val_accuracy: 0.1875\n",
"Epoch 1921/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8059 - accuracy: 0.4688 - val_loss: 3.4468 - val_accuracy: 0.1875\n",
"Epoch 1922/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6914 - accuracy: 0.5312 - val_loss: 3.5989 - val_accuracy: 0.1875\n",
"Epoch 1923/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7851 - accuracy: 0.3750 - val_loss: 3.4443 - val_accuracy: 0.2188\n",
"Epoch 1924/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6269 - accuracy: 0.6562 - val_loss: 3.5204 - val_accuracy: 0.1875\n",
"Epoch 1925/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7149 - accuracy: 0.5625 - val_loss: 3.4002 - val_accuracy: 0.1875\n",
"Epoch 1926/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5819 - accuracy: 0.6250 - val_loss: 3.5229 - val_accuracy: 0.2188\n",
"Epoch 1927/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6602 - accuracy: 0.5938 - val_loss: 3.4499 - val_accuracy: 0.2188\n",
"Epoch 1928/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6755 - accuracy: 0.6250 - val_loss: 3.4701 - val_accuracy: 0.2188\n",
"Epoch 1929/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7444 - accuracy: 0.5312 - val_loss: 3.4624 - val_accuracy: 0.2188\n",
"Epoch 1930/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6128 - accuracy: 0.6875 - val_loss: 3.4164 - val_accuracy: 0.2188\n",
"Epoch 1931/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6949 - accuracy: 0.5625 - val_loss: 3.4385 - val_accuracy: 0.2188\n",
"Epoch 1932/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.8340 - accuracy: 0.50 - 0s 162ms/step - loss: 0.8340 - accuracy: 0.5000 - val_loss: 3.4611 - val_accuracy: 0.1875\n",
"Epoch 1933/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6762 - accuracy: 0.5000 - val_loss: 3.6776 - val_accuracy: 0.2188\n",
"Epoch 1934/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7113 - accuracy: 0.4688 - val_loss: 3.2574 - val_accuracy: 0.2188\n",
"Epoch 1935/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9210 - accuracy: 0.4375 - val_loss: 3.7185 - val_accuracy: 0.2500\n",
"Epoch 1936/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6976 - accuracy: 0.6250 - val_loss: 3.3639 - val_accuracy: 0.2188\n",
"Epoch 1937/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7010 - accuracy: 0.5000 - val_loss: 3.4921 - val_accuracy: 0.1875\n",
"Epoch 1938/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7614 - accuracy: 0.5312 - val_loss: 3.4890 - val_accuracy: 0.1875\n",
"Epoch 1939/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7700 - accuracy: 0.5000 - val_loss: 3.4330 - val_accuracy: 0.1562\n",
"Epoch 1940/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6068 - accuracy: 0.6562 - val_loss: 3.4019 - val_accuracy: 0.1562\n",
"Epoch 1941/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6614 - accuracy: 0.5625 - val_loss: 3.5591 - val_accuracy: 0.1875\n",
"Epoch 1942/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6188 - accuracy: 0.5938 - val_loss: 3.5481 - val_accuracy: 0.1875\n",
"Epoch 1943/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6325 - accuracy: 0.5625 - val_loss: 3.5254 - val_accuracy: 0.1875\n",
"Epoch 1944/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5418 - accuracy: 0.6562 - val_loss: 3.6309 - val_accuracy: 0.1875\n",
"Epoch 1945/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7367 - accuracy: 0.5000 - val_loss: 3.4539 - val_accuracy: 0.2188\n",
"Epoch 1946/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7041 - accuracy: 0.5938 - val_loss: 3.6795 - val_accuracy: 0.2500\n",
"Epoch 1947/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6733 - accuracy: 0.5312 - val_loss: 3.4203 - val_accuracy: 0.1875\n",
"Epoch 1948/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5458 - accuracy: 0.6250 - val_loss: 3.5017 - val_accuracy: 0.2188\n",
"Epoch 1949/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7000 - accuracy: 0.5000 - val_loss: 3.4547 - val_accuracy: 0.2188\n",
"Epoch 1950/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6396 - accuracy: 0.5312 - val_loss: 3.4451 - val_accuracy: 0.1562\n",
"Epoch 1951/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5804 - accuracy: 0.6562 - val_loss: 3.4254 - val_accuracy: 0.1562\n",
"Epoch 1952/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6741 - accuracy: 0.6250 - val_loss: 3.4420 - val_accuracy: 0.1875\n",
"Epoch 1953/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7786 - accuracy: 0.5312 - val_loss: 3.5030 - val_accuracy: 0.1875\n",
"Epoch 1954/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6757 - accuracy: 0.6250 - val_loss: 3.5451 - val_accuracy: 0.1875\n",
"Epoch 1955/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6918 - accuracy: 0.5625 - val_loss: 3.4676 - val_accuracy: 0.1875\n",
"Epoch 1956/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6248 - accuracy: 0.5938 - val_loss: 3.6899 - val_accuracy: 0.2188\n",
"Epoch 1957/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5755 - accuracy: 0.7500 - val_loss: 3.4836 - val_accuracy: 0.1875\n",
"Epoch 1958/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6199 - accuracy: 0.5938 - val_loss: 3.5074 - val_accuracy: 0.2188\n",
"Epoch 1959/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7667 - accuracy: 0.5938 - val_loss: 3.6193 - val_accuracy: 0.2188\n",
"Epoch 1960/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6504 - accuracy: 0.6875 - val_loss: 3.6757 - val_accuracy: 0.2188\n",
"Epoch 1961/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6506 - accuracy: 0.5938 - val_loss: 3.3199 - val_accuracy: 0.1875\n",
"Epoch 1962/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6278 - accuracy: 0.6250 - val_loss: 3.5325 - val_accuracy: 0.2188\n",
"Epoch 1963/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5706 - accuracy: 0.6250 - val_loss: 3.4862 - val_accuracy: 0.2188\n",
"Epoch 1964/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6027 - accuracy: 0.6875 - val_loss: 3.6210 - val_accuracy: 0.2188\n",
"Epoch 1965/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6189 - accuracy: 0.6562 - val_loss: 3.5235 - val_accuracy: 0.2188\n",
"Epoch 1966/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9770 - accuracy: 0.6250 - val_loss: 4.4792 - val_accuracy: 0.1875\n",
"Epoch 1967/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.2363 - accuracy: 0.4062 - val_loss: 2.9338 - val_accuracy: 0.1875\n",
"Epoch 1968/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 5.5626 - accuracy: 0.3125 - val_loss: 8.7431 - val_accuracy: 0.0312\n",
"Epoch 1969/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 7.0042 - accuracy: 0.0625 - val_loss: 2.4241 - val_accuracy: 0.1875\n",
"Epoch 1970/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 4.9898 - accuracy: 0.2500 - val_loss: 4.5156 - val_accuracy: 0.0625\n",
"Epoch 1971/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.0162 - accuracy: 0.2188 - val_loss: 3.4884 - val_accuracy: 0.0625\n",
"Epoch 1972/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.4388 - accuracy: 0.2812 - val_loss: 3.2525 - val_accuracy: 0.1250\n",
"Epoch 1973/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.1528 - accuracy: 0.3438 - val_loss: 2.9870 - val_accuracy: 0.1250\n",
"Epoch 1974/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9340 - accuracy: 0.4375 - val_loss: 3.0272 - val_accuracy: 0.1250\n",
"Epoch 1975/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8433 - accuracy: 0.5000 - val_loss: 2.9199 - val_accuracy: 0.1250\n",
"Epoch 1976/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8073 - accuracy: 0.5000 - val_loss: 2.9281 - val_accuracy: 0.1562\n",
"Epoch 1977/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8504 - accuracy: 0.4062 - val_loss: 2.8883 - val_accuracy: 0.1562\n",
"Epoch 1978/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7446 - accuracy: 0.4062 - val_loss: 2.8766 - val_accuracy: 0.1562\n",
"Epoch 1979/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7455 - accuracy: 0.5312 - val_loss: 2.9025 - val_accuracy: 0.1562\n",
"Epoch 1980/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7625 - accuracy: 0.5625 - val_loss: 2.9268 - val_accuracy: 0.1562\n",
"Epoch 1981/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6565 - accuracy: 0.6562 - val_loss: 2.9505 - val_accuracy: 0.1562\n",
"Epoch 1982/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8846 - accuracy: 0.3438 - val_loss: 3.0466 - val_accuracy: 0.1562\n",
"Epoch 1983/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.8754 - accuracy: 0.3750 - val_loss: 3.0571 - val_accuracy: 0.1562\n",
"Epoch 1984/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7454 - accuracy: 0.5938 - val_loss: 3.0329 - val_accuracy: 0.1562\n",
"Epoch 1985/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.7112 - accuracy: 0.6562 - val_loss: 3.0203 - val_accuracy: 0.1562\n",
"Epoch 1986/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8120 - accuracy: 0.5625 - val_loss: 3.0419 - val_accuracy: 0.1562\n",
"Epoch 1987/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7868 - accuracy: 0.5312 - val_loss: 2.9670 - val_accuracy: 0.1562\n",
"Epoch 1988/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.9254 - accuracy: 0.5312 - val_loss: 3.2630 - val_accuracy: 0.1875\n",
"Epoch 1989/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8639 - accuracy: 0.5000 - val_loss: 2.9827 - val_accuracy: 0.1562\n",
"Epoch 1990/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7406 - accuracy: 0.5312 - val_loss: 3.0697 - val_accuracy: 0.1562\n",
"Epoch 1991/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8424 - accuracy: 0.5312 - val_loss: 3.1235 - val_accuracy: 0.1562\n",
"Epoch 1992/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7318 - accuracy: 0.4375 - val_loss: 3.0961 - val_accuracy: 0.1562\n",
"Epoch 1993/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7454 - accuracy: 0.5625 - val_loss: 3.0600 - val_accuracy: 0.1562\n",
"Epoch 1994/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7347 - accuracy: 0.5000 - val_loss: 3.0532 - val_accuracy: 0.1562\n",
"Epoch 1995/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7544 - accuracy: 0.5312 - val_loss: 3.0729 - val_accuracy: 0.1562\n",
"Epoch 1996/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7983 - accuracy: 0.5000 - val_loss: 3.0713 - val_accuracy: 0.1562\n",
"Epoch 1997/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6778 - accuracy: 0.6250 - val_loss: 3.0565 - val_accuracy: 0.1562\n",
"Epoch 1998/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8317 - accuracy: 0.5625 - val_loss: 3.2140 - val_accuracy: 0.1562\n",
"Epoch 1999/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6537 - accuracy: 0.7500 - val_loss: 3.1583 - val_accuracy: 0.1562\n",
"Epoch 2000/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7243 - accuracy: 0.5000 - val_loss: 3.0990 - val_accuracy: 0.1562\n",
"Epoch 2001/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7605 - accuracy: 0.4688 - val_loss: 3.1466 - val_accuracy: 0.1562\n",
"Epoch 2002/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6673 - accuracy: 0.4688 - val_loss: 3.1637 - val_accuracy: 0.1562\n",
"Epoch 2003/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7271 - accuracy: 0.4688 - val_loss: 3.1595 - val_accuracy: 0.1562\n",
"Epoch 2004/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6771 - accuracy: 0.6250 - val_loss: 3.1495 - val_accuracy: 0.1562\n",
"Epoch 2005/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7612 - accuracy: 0.5312 - val_loss: 3.1535 - val_accuracy: 0.1562\n",
"Epoch 2006/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8329 - accuracy: 0.5312 - val_loss: 3.2383 - val_accuracy: 0.1875\n",
"Epoch 2007/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7274 - accuracy: 0.6250 - val_loss: 3.0776 - val_accuracy: 0.1562\n",
"Epoch 2008/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6756 - accuracy: 0.6875 - val_loss: 3.1563 - val_accuracy: 0.1875\n",
"Epoch 2009/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6529 - accuracy: 0.6562 - val_loss: 3.1866 - val_accuracy: 0.1875\n",
"Epoch 2010/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6578 - accuracy: 0.7188 - val_loss: 3.2311 - val_accuracy: 0.1875\n",
"Epoch 2011/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6905 - accuracy: 0.6250 - val_loss: 3.2251 - val_accuracy: 0.1875\n",
"Epoch 2012/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6409 - accuracy: 0.6250 - val_loss: 3.2000 - val_accuracy: 0.1875\n",
"Epoch 2013/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6843 - accuracy: 0.6562 - val_loss: 3.2214 - val_accuracy: 0.1875\n",
"Epoch 2014/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7641 - accuracy: 0.5000 - val_loss: 3.1757 - val_accuracy: 0.1875\n",
"Epoch 2015/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7138 - accuracy: 0.4375 - val_loss: 3.2495 - val_accuracy: 0.1875\n",
"Epoch 2016/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7058 - accuracy: 0.6562 - val_loss: 3.2381 - val_accuracy: 0.1562\n",
"Epoch 2017/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6557 - accuracy: 0.5938 - val_loss: 3.2763 - val_accuracy: 0.1875\n",
"Epoch 2018/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6980 - accuracy: 0.5938 - val_loss: 3.2044 - val_accuracy: 0.1875\n",
"Epoch 2019/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6417 - accuracy: 0.6250 - val_loss: 3.3341 - val_accuracy: 0.1875\n",
"Epoch 2020/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.6855 - accuracy: 0.6250 - val_loss: 3.2064 - val_accuracy: 0.1875\n",
"Epoch 2021/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6641 - accuracy: 0.5938 - val_loss: 3.2062 - val_accuracy: 0.1562\n",
"Epoch 2022/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6812 - accuracy: 0.5625 - val_loss: 3.2363 - val_accuracy: 0.1562\n",
"Epoch 2023/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7236 - accuracy: 0.6250 - val_loss: 3.2538 - val_accuracy: 0.1562\n",
"Epoch 2024/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6644 - accuracy: 0.5625 - val_loss: 3.1290 - val_accuracy: 0.1562\n",
"Epoch 2025/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9396 - accuracy: 0.5625 - val_loss: 3.1391 - val_accuracy: 0.1562\n",
"Epoch 2026/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7758 - accuracy: 0.4375 - val_loss: 3.2919 - val_accuracy: 0.1562\n",
"Epoch 2027/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6587 - accuracy: 0.6562 - val_loss: 3.2695 - val_accuracy: 0.1562\n",
"Epoch 2028/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7263 - accuracy: 0.6875 - val_loss: 3.2591 - val_accuracy: 0.1562\n",
"Epoch 2029/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6400 - accuracy: 0.5938 - val_loss: 3.2246 - val_accuracy: 0.1562\n",
"Epoch 2030/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6200 - accuracy: 0.6562 - val_loss: 3.1500 - val_accuracy: 0.1562\n",
"Epoch 2031/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7068 - accuracy: 0.5938 - val_loss: 3.2225 - val_accuracy: 0.1562\n",
"Epoch 2032/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7339 - accuracy: 0.5312 - val_loss: 3.3689 - val_accuracy: 0.1562\n",
"Epoch 2033/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6274 - accuracy: 0.5625 - val_loss: 3.2530 - val_accuracy: 0.1562\n",
"Epoch 2034/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7097 - accuracy: 0.5000 - val_loss: 3.2621 - val_accuracy: 0.1562\n",
"Epoch 2035/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6926 - accuracy: 0.5938 - val_loss: 3.3447 - val_accuracy: 0.1562\n",
"Epoch 2036/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6796 - accuracy: 0.5312 - val_loss: 3.2202 - val_accuracy: 0.1562\n",
"Epoch 2037/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6832 - accuracy: 0.5625 - val_loss: 3.2727 - val_accuracy: 0.1875\n",
"Epoch 2038/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8246 - accuracy: 0.5312 - val_loss: 3.2918 - val_accuracy: 0.1875\n",
"Epoch 2039/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5765 - accuracy: 0.6250 - val_loss: 3.2439 - val_accuracy: 0.1562\n",
"Epoch 2040/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6711 - accuracy: 0.5625 - val_loss: 3.4381 - val_accuracy: 0.1875\n",
"Epoch 2041/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.6345 - accuracy: 0.6562 - val_loss: 3.4128 - val_accuracy: 0.1875\n",
"Epoch 2042/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7263 - accuracy: 0.5938 - val_loss: 3.1942 - val_accuracy: 0.2188\n",
"Epoch 2043/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 1.0199 - accuracy: 0.5625 - val_loss: 3.3351 - val_accuracy: 0.2188\n",
"Epoch 2044/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7805 - accuracy: 0.4688 - val_loss: 3.3572 - val_accuracy: 0.1875\n",
"Epoch 2045/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7196 - accuracy: 0.4375 - val_loss: 3.3866 - val_accuracy: 0.1875\n",
"Epoch 2046/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7247 - accuracy: 0.5000 - val_loss: 3.2974 - val_accuracy: 0.2188\n",
"Epoch 2047/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7605 - accuracy: 0.5625 - val_loss: 3.3357 - val_accuracy: 0.1875\n",
"Epoch 2048/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6653 - accuracy: 0.5625 - val_loss: 3.2621 - val_accuracy: 0.1875\n",
"Epoch 2049/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6572 - accuracy: 0.5938 - val_loss: 3.4311 - val_accuracy: 0.1875\n",
"Epoch 2050/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7191 - accuracy: 0.5312 - val_loss: 3.2964 - val_accuracy: 0.1875\n",
"Epoch 2051/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6960 - accuracy: 0.5938 - val_loss: 3.3479 - val_accuracy: 0.1562\n",
"Epoch 2052/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6757 - accuracy: 0.5625 - val_loss: 3.2555 - val_accuracy: 0.1562\n",
"Epoch 2053/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5548 - accuracy: 0.6875 - val_loss: 3.3730 - val_accuracy: 0.1875\n",
"Epoch 2054/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8048 - accuracy: 0.4062 - val_loss: 3.3690 - val_accuracy: 0.1875\n",
"Epoch 2055/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7928 - accuracy: 0.5000 - val_loss: 3.3318 - val_accuracy: 0.2188\n",
"Epoch 2056/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6167 - accuracy: 0.5625 - val_loss: 3.3380 - val_accuracy: 0.2188\n",
"Epoch 2057/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6830 - accuracy: 0.5312 - val_loss: 3.4759 - val_accuracy: 0.1875\n",
"Epoch 2058/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5896 - accuracy: 0.6875 - val_loss: 3.2687 - val_accuracy: 0.2188\n",
"Epoch 2059/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6372 - accuracy: 0.6250 - val_loss: 3.3947 - val_accuracy: 0.1875\n",
"Epoch 2060/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7448 - accuracy: 0.4688 - val_loss: 3.3575 - val_accuracy: 0.2188\n",
"Epoch 2061/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6180 - accuracy: 0.5938 - val_loss: 3.3496 - val_accuracy: 0.2188\n",
"Epoch 2062/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7484 - accuracy: 0.5625 - val_loss: 3.4122 - val_accuracy: 0.2188\n",
"Epoch 2063/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6870 - accuracy: 0.5000 - val_loss: 3.3763 - val_accuracy: 0.2188\n",
"Epoch 2064/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6300 - accuracy: 0.6875 - val_loss: 3.3955 - val_accuracy: 0.1875\n",
"Epoch 2065/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6287 - accuracy: 0.6250 - val_loss: 3.3772 - val_accuracy: 0.1875\n",
"Epoch 2066/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5966 - accuracy: 0.5625 - val_loss: 3.3451 - val_accuracy: 0.1562\n",
"Epoch 2067/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7824 - accuracy: 0.5312 - val_loss: 3.3971 - val_accuracy: 0.1562\n",
"Epoch 2068/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6311 - accuracy: 0.5938 - val_loss: 3.3986 - val_accuracy: 0.1875\n",
"Epoch 2069/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5280 - accuracy: 0.7188 - val_loss: 3.3938 - val_accuracy: 0.1875\n",
"Epoch 2070/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6832 - accuracy: 0.6250 - val_loss: 3.4564 - val_accuracy: 0.1875\n",
"Epoch 2071/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6337 - accuracy: 0.6250 - val_loss: 3.3609 - val_accuracy: 0.1875\n",
"Epoch 2072/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6612 - accuracy: 0.5000 - val_loss: 3.4073 - val_accuracy: 0.1875\n",
"Epoch 2073/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5507 - accuracy: 0.7500 - val_loss: 3.4821 - val_accuracy: 0.1875\n",
"Epoch 2074/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.7661 - accuracy: 0.5312 - val_loss: 3.4013 - val_accuracy: 0.2188\n",
"Epoch 2075/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.6540 - accuracy: 0.5938 - val_loss: 3.5665 - val_accuracy: 0.2188\n",
"Epoch 2076/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5957 - accuracy: 0.6250 - val_loss: 3.2717 - val_accuracy: 0.2188\n",
"Epoch 2077/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6780 - accuracy: 0.5312 - val_loss: 3.3918 - val_accuracy: 0.2188\n",
"Epoch 2078/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9206 - accuracy: 0.5000 - val_loss: 3.3115 - val_accuracy: 0.2188\n",
"Epoch 2079/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.5685 - accuracy: 0.6875 - val_loss: 3.5716 - val_accuracy: 0.2188\n",
"Epoch 2080/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7229 - accuracy: 0.6250 - val_loss: 3.4074 - val_accuracy: 0.1875\n",
"Epoch 2081/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6020 - accuracy: 0.5938 - val_loss: 3.4120 - val_accuracy: 0.1875\n",
"Epoch 2082/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6371 - accuracy: 0.5625 - val_loss: 3.3750 - val_accuracy: 0.2188\n",
"Epoch 2083/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7883 - accuracy: 0.5000 - val_loss: 3.5655 - val_accuracy: 0.2188\n",
"Epoch 2084/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7048 - accuracy: 0.6562 - val_loss: 3.3250 - val_accuracy: 0.2188\n",
"Epoch 2085/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6911 - accuracy: 0.5625 - val_loss: 3.4571 - val_accuracy: 0.2188\n",
"Epoch 2086/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6932 - accuracy: 0.7188 - val_loss: 3.5004 - val_accuracy: 0.2188\n",
"Epoch 2087/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6403 - accuracy: 0.6250 - val_loss: 3.4759 - val_accuracy: 0.2188\n",
"Epoch 2088/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7844 - accuracy: 0.4688 - val_loss: 3.4781 - val_accuracy: 0.2188\n",
"Epoch 2089/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5990 - accuracy: 0.6250 - val_loss: 3.5661 - val_accuracy: 0.2188\n",
"Epoch 2090/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6809 - accuracy: 0.5938 - val_loss: 3.4593 - val_accuracy: 0.2188\n",
"Epoch 2091/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7477 - accuracy: 0.5625 - val_loss: 3.5512 - val_accuracy: 0.1875\n",
"Epoch 2092/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7447 - accuracy: 0.5312 - val_loss: 3.3325 - val_accuracy: 0.1875\n",
"Epoch 2093/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6602 - accuracy: 0.6562 - val_loss: 3.4810 - val_accuracy: 0.1875\n",
"Epoch 2094/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6667 - accuracy: 0.5625 - val_loss: 3.4397 - val_accuracy: 0.1875\n",
"Epoch 2095/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5756 - accuracy: 0.6250 - val_loss: 3.4406 - val_accuracy: 0.1875\n",
"Epoch 2096/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6309 - accuracy: 0.5938 - val_loss: 3.4496 - val_accuracy: 0.1875\n",
"Epoch 2097/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6956 - accuracy: 0.5938 - val_loss: 3.4422 - val_accuracy: 0.1875\n",
"Epoch 2098/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5373 - accuracy: 0.6875 - val_loss: 3.5264 - val_accuracy: 0.1875\n",
"Epoch 2099/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6854 - accuracy: 0.5312 - val_loss: 3.4067 - val_accuracy: 0.2188\n",
"Epoch 2100/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6799 - accuracy: 0.5625 - val_loss: 3.6181 - val_accuracy: 0.1875\n",
"Epoch 2101/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6770 - accuracy: 0.6250 - val_loss: 3.5060 - val_accuracy: 0.1875\n",
"Epoch 2102/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5571 - accuracy: 0.6875 - val_loss: 3.4236 - val_accuracy: 0.2188\n",
"Epoch 2103/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6317 - accuracy: 0.6875 - val_loss: 3.4350 - val_accuracy: 0.2188\n",
"Epoch 2104/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7351 - accuracy: 0.5312 - val_loss: 3.3882 - val_accuracy: 0.2188\n",
"Epoch 2105/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8006 - accuracy: 0.5000 - val_loss: 3.5670 - val_accuracy: 0.1875\n",
"Epoch 2106/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7479 - accuracy: 0.5312 - val_loss: 3.4595 - val_accuracy: 0.1875\n",
"Epoch 2107/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6894 - accuracy: 0.6250 - val_loss: 3.4673 - val_accuracy: 0.1875\n",
"Epoch 2108/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6270 - accuracy: 0.6562 - val_loss: 3.3921 - val_accuracy: 0.1875\n",
"Epoch 2109/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6813 - accuracy: 0.6562 - val_loss: 3.4451 - val_accuracy: 0.2188\n",
"Epoch 2110/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5508 - accuracy: 0.7188 - val_loss: 3.5443 - val_accuracy: 0.1875\n",
"Epoch 2111/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7067 - accuracy: 0.5625 - val_loss: 3.4589 - val_accuracy: 0.2188\n",
"Epoch 2112/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6566 - accuracy: 0.5312 - val_loss: 3.5938 - val_accuracy: 0.1875\n",
"Epoch 2113/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7156 - accuracy: 0.5000 - val_loss: 3.2767 - val_accuracy: 0.1875\n",
"Epoch 2114/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6195 - accuracy: 0.5938 - val_loss: 3.5031 - val_accuracy: 0.1875\n",
"Epoch 2115/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5994 - accuracy: 0.6562 - val_loss: 3.3975 - val_accuracy: 0.1562\n",
"Epoch 2116/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7164 - accuracy: 0.5625 - val_loss: 3.4550 - val_accuracy: 0.1562\n",
"Epoch 2117/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6620 - accuracy: 0.5312 - val_loss: 3.3451 - val_accuracy: 0.1562\n",
"Epoch 2118/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5799 - accuracy: 0.7188 - val_loss: 3.6620 - val_accuracy: 0.1875\n",
"Epoch 2119/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7157 - accuracy: 0.5938 - val_loss: 3.3344 - val_accuracy: 0.1875\n",
"Epoch 2120/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6795 - accuracy: 0.6562 - val_loss: 3.5324 - val_accuracy: 0.1875\n",
"Epoch 2121/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7926 - accuracy: 0.6250 - val_loss: 3.8906 - val_accuracy: 0.2188\n",
"Epoch 2122/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7125 - accuracy: 0.5938 - val_loss: 3.8227 - val_accuracy: 0.2188\n",
"Epoch 2123/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6882 - accuracy: 0.6250 - val_loss: 3.5685 - val_accuracy: 0.2188\n",
"Epoch 2124/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6496 - accuracy: 0.6875 - val_loss: 3.7457 - val_accuracy: 0.2188\n",
"Epoch 2125/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7460 - accuracy: 0.5312 - val_loss: 3.5092 - val_accuracy: 0.2188\n",
"Epoch 2126/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6398 - accuracy: 0.5625 - val_loss: 3.6226 - val_accuracy: 0.2188\n",
"Epoch 2127/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6005 - accuracy: 0.6562 - val_loss: 3.6315 - val_accuracy: 0.2188\n",
"Epoch 2128/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6872 - accuracy: 0.5938 - val_loss: 3.5927 - val_accuracy: 0.2188\n",
"Epoch 2129/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5387 - accuracy: 0.6875 - val_loss: 3.7412 - val_accuracy: 0.2188\n",
"Epoch 2130/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6830 - accuracy: 0.5000 - val_loss: 3.6107 - val_accuracy: 0.2188\n",
"Epoch 2131/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6059 - accuracy: 0.6250 - val_loss: 3.6211 - val_accuracy: 0.2188\n",
"Epoch 2132/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5649 - accuracy: 0.5938 - val_loss: 3.6604 - val_accuracy: 0.1875\n",
"Epoch 2133/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6728 - accuracy: 0.6250 - val_loss: 3.6445 - val_accuracy: 0.1875\n",
"Epoch 2134/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7431 - accuracy: 0.5625 - val_loss: 3.5616 - val_accuracy: 0.1875\n",
"Epoch 2135/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7925 - accuracy: 0.5312 - val_loss: 3.6976 - val_accuracy: 0.1875\n",
"Epoch 2136/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6736 - accuracy: 0.5000 - val_loss: 3.5482 - val_accuracy: 0.1875\n",
"Epoch 2137/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6288 - accuracy: 0.6562 - val_loss: 3.6865 - val_accuracy: 0.1875\n",
"Epoch 2138/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6856 - accuracy: 0.5625 - val_loss: 3.5674 - val_accuracy: 0.1875\n",
"Epoch 2139/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.5944 - accuracy: 0.6562 - val_loss: 3.6469 - val_accuracy: 0.1875\n",
"Epoch 2140/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7772 - accuracy: 0.6250 - val_loss: 3.6069 - val_accuracy: 0.1875\n",
"Epoch 2141/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6371 - accuracy: 0.6562 - val_loss: 3.7480 - val_accuracy: 0.1875\n",
"Epoch 2142/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5993 - accuracy: 0.5625 - val_loss: 3.6004 - val_accuracy: 0.1875\n",
"Epoch 2143/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5570 - accuracy: 0.5625 - val_loss: 3.6457 - val_accuracy: 0.1875\n",
"Epoch 2144/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7647 - accuracy: 0.5938 - val_loss: 3.7204 - val_accuracy: 0.1875\n",
"Epoch 2145/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7263 - accuracy: 0.5938 - val_loss: 3.7393 - val_accuracy: 0.1875\n",
"Epoch 2146/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5254 - accuracy: 0.6875 - val_loss: 3.4616 - val_accuracy: 0.2188\n",
"Epoch 2147/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6026 - accuracy: 0.6562 - val_loss: 3.7810 - val_accuracy: 0.2188\n",
"Epoch 2148/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6184 - accuracy: 0.6562 - val_loss: 3.4479 - val_accuracy: 0.1562\n",
"Epoch 2149/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7032 - accuracy: 0.5938 - val_loss: 3.6237 - val_accuracy: 0.1875\n",
"Epoch 2150/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6031 - accuracy: 0.5938 - val_loss: 3.5211 - val_accuracy: 0.1875\n",
"Epoch 2151/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8111 - accuracy: 0.5000 - val_loss: 3.7071 - val_accuracy: 0.1875\n",
"Epoch 2152/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6736 - accuracy: 0.5312 - val_loss: 3.5651 - val_accuracy: 0.1875\n",
"Epoch 2153/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6444 - accuracy: 0.5938 - val_loss: 3.5365 - val_accuracy: 0.1875\n",
"Epoch 2154/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8509 - accuracy: 0.4375 - val_loss: 3.7628 - val_accuracy: 0.2188\n",
"Epoch 2155/5000\n",
"1/1 [==============================] - 0s 151ms/step - loss: 0.6899 - accuracy: 0.5938 - val_loss: 3.4301 - val_accuracy: 0.1562\n",
"Epoch 2156/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.7528 - accuracy: 0.62 - 0s 161ms/step - loss: 0.7528 - accuracy: 0.6250 - val_loss: 3.6924 - val_accuracy: 0.1875\n",
"Epoch 2157/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7444 - accuracy: 0.5625 - val_loss: 3.5881 - val_accuracy: 0.1875\n",
"Epoch 2158/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6656 - accuracy: 0.5312 - val_loss: 3.6449 - val_accuracy: 0.1875\n",
"Epoch 2159/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6681 - accuracy: 0.4375 - val_loss: 3.6027 - val_accuracy: 0.1875\n",
"Epoch 2160/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6501 - accuracy: 0.6250 - val_loss: 3.5663 - val_accuracy: 0.1875\n",
"Epoch 2161/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6621 - accuracy: 0.5625 - val_loss: 3.5652 - val_accuracy: 0.1875\n",
"Epoch 2162/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7695 - accuracy: 0.4688 - val_loss: 3.6050 - val_accuracy: 0.1875\n",
"Epoch 2163/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6268 - accuracy: 0.6250 - val_loss: 3.6649 - val_accuracy: 0.1875\n",
"Epoch 2164/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6722 - accuracy: 0.6250 - val_loss: 3.5442 - val_accuracy: 0.1875\n",
"Epoch 2165/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7435 - accuracy: 0.4375 - val_loss: 3.7762 - val_accuracy: 0.1875\n",
"Epoch 2166/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7229 - accuracy: 0.5312 - val_loss: 3.3944 - val_accuracy: 0.1562\n",
"Epoch 2167/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6921 - accuracy: 0.5938 - val_loss: 3.9216 - val_accuracy: 0.2188\n",
"Epoch 2168/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.8118 - accuracy: 0.4688 - val_loss: 3.3552 - val_accuracy: 0.2188\n",
"Epoch 2169/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5546 - accuracy: 0.5938 - val_loss: 3.9390 - val_accuracy: 0.2188\n",
"Epoch 2170/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7956 - accuracy: 0.5938 - val_loss: 3.2297 - val_accuracy: 0.2500\n",
"Epoch 2171/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7265 - accuracy: 0.5938 - val_loss: 3.7877 - val_accuracy: 0.2188\n",
"Epoch 2172/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.6877 - accuracy: 0.6250 - val_loss: 3.4855 - val_accuracy: 0.1875\n",
"Epoch 2173/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6531 - accuracy: 0.6562 - val_loss: 3.6592 - val_accuracy: 0.1875\n",
"Epoch 2174/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.9849 - accuracy: 0.4688 - val_loss: 4.5037 - val_accuracy: 0.1875\n",
"Epoch 2175/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.9274 - accuracy: 0.5000 - val_loss: 2.9293 - val_accuracy: 0.1875\n",
"Epoch 2176/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 4.5927 - accuracy: 0.2812 - val_loss: 17.3447 - val_accuracy: 0.0312\n",
"Epoch 2177/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 26.0210 - accuracy: 0.0312 - val_loss: 2.2572 - val_accuracy: 0.0000e+00\n",
"Epoch 2178/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 4.1873 - accuracy: 0.1562 - val_loss: 2.3274 - val_accuracy: 0.0312\n",
"Epoch 2179/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 3.0336 - accuracy: 0.0625 - val_loss: 2.4603 - val_accuracy: 0.0312\n",
"Epoch 2180/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 3.1814 - accuracy: 0.0625 - val_loss: 2.4322 - val_accuracy: 0.0312\n",
"Epoch 2181/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 3.2694 - accuracy: 0.0938 - val_loss: 2.4131 - val_accuracy: 0.0938\n",
"Epoch 2182/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 3.0215 - accuracy: 0.1250 - val_loss: 2.5410 - val_accuracy: 0.0625\n",
"Epoch 2183/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 2.6133 - accuracy: 0.1250 - val_loss: 2.4820 - val_accuracy: 0.0625\n",
"Epoch 2184/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.5507 - accuracy: 0.1562 - val_loss: 2.5713 - val_accuracy: 0.0625\n",
"Epoch 2185/5000\n",
"1/1 [==============================] - 0s 151ms/step - loss: 2.6037 - accuracy: 0.1562 - val_loss: 2.6731 - val_accuracy: 0.0312\n",
"Epoch 2186/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.9150 - accuracy: 0.0938 - val_loss: 2.7548 - val_accuracy: 0.0312\n",
"Epoch 2187/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.2786 - accuracy: 0.1875 - val_loss: 2.7498 - val_accuracy: 0.0312\n",
"Epoch 2188/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.1690 - accuracy: 0.1562 - val_loss: 2.7672 - val_accuracy: 0.0312\n",
"Epoch 2189/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 2.0171 - accuracy: 0.1250 - val_loss: 2.8563 - val_accuracy: 0.0312\n",
"Epoch 2190/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.0866 - accuracy: 0.1875 - val_loss: 2.9179 - val_accuracy: 0.0312\n",
"Epoch 2191/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.8592 - accuracy: 0.1250 - val_loss: 2.8274 - val_accuracy: 0.0938\n",
"Epoch 2192/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.0902 - accuracy: 0.1562 - val_loss: 2.9064 - val_accuracy: 0.0312\n",
"Epoch 2193/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.9489 - accuracy: 0.2812 - val_loss: 2.8219 - val_accuracy: 0.0938\n",
"Epoch 2194/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.1999 - accuracy: 0.1875 - val_loss: 3.1491 - val_accuracy: 0.0312\n",
"Epoch 2195/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.0239 - accuracy: 0.1562 - val_loss: 2.8923 - val_accuracy: 0.0938\n",
"Epoch 2196/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.7440 - accuracy: 0.2500 - val_loss: 2.9854 - val_accuracy: 0.0938\n",
"Epoch 2197/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.7130 - accuracy: 0.2500 - val_loss: 2.9391 - val_accuracy: 0.1562\n",
"Epoch 2198/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.6934 - accuracy: 0.2812 - val_loss: 2.9652 - val_accuracy: 0.1562\n",
"Epoch 2199/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.2688 - accuracy: 0.4062 - val_loss: 2.8164 - val_accuracy: 0.2188\n",
"Epoch 2200/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.1304 - accuracy: 0.4688 - val_loss: 2.7426 - val_accuracy: 0.2188\n",
"Epoch 2201/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 1.1876 - accuracy: 0.2812 - val_loss: 2.8152 - val_accuracy: 0.2500\n",
"Epoch 2202/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.1717 - accuracy: 0.3750 - val_loss: 2.7768 - val_accuracy: 0.2500\n",
"Epoch 2203/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.0286 - accuracy: 0.4062 - val_loss: 2.7756 - val_accuracy: 0.2812\n",
"Epoch 2204/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.9742 - accuracy: 0.4375 - val_loss: 2.7174 - val_accuracy: 0.2812\n",
"Epoch 2205/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9223 - accuracy: 0.5312 - val_loss: 2.7135 - val_accuracy: 0.2812\n",
"Epoch 2206/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9469 - accuracy: 0.5000 - val_loss: 2.7044 - val_accuracy: 0.2812\n",
"Epoch 2207/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9477 - accuracy: 0.5000 - val_loss: 2.7458 - val_accuracy: 0.2500\n",
"Epoch 2208/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9406 - accuracy: 0.5312 - val_loss: 2.7638 - val_accuracy: 0.2500\n",
"Epoch 2209/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9010 - accuracy: 0.6562 - val_loss: 2.7578 - val_accuracy: 0.2812\n",
"Epoch 2210/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7885 - accuracy: 0.5625 - val_loss: 2.7491 - val_accuracy: 0.2500\n",
"Epoch 2211/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8951 - accuracy: 0.5000 - val_loss: 2.7625 - val_accuracy: 0.2500\n",
"Epoch 2212/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8914 - accuracy: 0.5938 - val_loss: 2.7687 - val_accuracy: 0.2500\n",
"Epoch 2213/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8976 - accuracy: 0.4688 - val_loss: 2.7767 - val_accuracy: 0.2500\n",
"Epoch 2214/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8487 - accuracy: 0.5625 - val_loss: 2.7545 - val_accuracy: 0.2500\n",
"Epoch 2215/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8015 - accuracy: 0.5938 - val_loss: 2.7903 - val_accuracy: 0.2500\n",
"Epoch 2216/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7875 - accuracy: 0.6562 - val_loss: 2.7489 - val_accuracy: 0.2500\n",
"Epoch 2217/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8675 - accuracy: 0.5000 - val_loss: 2.7644 - val_accuracy: 0.2500\n",
"Epoch 2218/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7763 - accuracy: 0.5312 - val_loss: 2.7621 - val_accuracy: 0.2500\n",
"Epoch 2219/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7243 - accuracy: 0.5938 - val_loss: 2.7637 - val_accuracy: 0.2500\n",
"Epoch 2220/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8142 - accuracy: 0.6250 - val_loss: 2.7871 - val_accuracy: 0.2500\n",
"Epoch 2221/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.8558 - accuracy: 0.5625 - val_loss: 2.8532 - val_accuracy: 0.2500\n",
"Epoch 2222/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8166 - accuracy: 0.5000 - val_loss: 2.7953 - val_accuracy: 0.2500\n",
"Epoch 2223/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7484 - accuracy: 0.6562 - val_loss: 2.7933 - val_accuracy: 0.2500\n",
"Epoch 2224/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7417 - accuracy: 0.6250 - val_loss: 2.7924 - val_accuracy: 0.2500\n",
"Epoch 2225/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8507 - accuracy: 0.5938 - val_loss: 2.8546 - val_accuracy: 0.2500\n",
"Epoch 2226/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.8627 - accuracy: 0.5625 - val_loss: 2.8307 - val_accuracy: 0.2500\n",
"Epoch 2227/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7578 - accuracy: 0.5625 - val_loss: 2.8603 - val_accuracy: 0.2500\n",
"Epoch 2228/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7699 - accuracy: 0.5000 - val_loss: 2.8391 - val_accuracy: 0.2500\n",
"Epoch 2229/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6633 - accuracy: 0.5938 - val_loss: 2.8380 - val_accuracy: 0.2500\n",
"Epoch 2230/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8619 - accuracy: 0.5625 - val_loss: 2.8925 - val_accuracy: 0.2188\n",
"Epoch 2231/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7624 - accuracy: 0.5938 - val_loss: 2.8405 - val_accuracy: 0.2500\n",
"Epoch 2232/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7486 - accuracy: 0.5312 - val_loss: 2.8609 - val_accuracy: 0.2500\n",
"Epoch 2233/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8529 - accuracy: 0.5000 - val_loss: 2.9430 - val_accuracy: 0.2500\n",
"Epoch 2234/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6647 - accuracy: 0.6562 - val_loss: 2.9510 - val_accuracy: 0.2500\n",
"Epoch 2235/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7001 - accuracy: 0.5938 - val_loss: 2.9537 - val_accuracy: 0.2188\n",
"Epoch 2236/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6578 - accuracy: 0.5312 - val_loss: 2.9155 - val_accuracy: 0.2500\n",
"Epoch 2237/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7026 - accuracy: 0.6875 - val_loss: 2.9953 - val_accuracy: 0.2188\n",
"Epoch 2238/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.7004 - accuracy: 0.6562 - val_loss: 2.9234 - val_accuracy: 0.2188\n",
"Epoch 2239/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6989 - accuracy: 0.5625 - val_loss: 2.9798 - val_accuracy: 0.2188\n",
"Epoch 2240/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7375 - accuracy: 0.6562 - val_loss: 2.8718 - val_accuracy: 0.2500\n",
"Epoch 2241/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9958 - accuracy: 0.4375 - val_loss: 3.1433 - val_accuracy: 0.1875\n",
"Epoch 2242/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7981 - accuracy: 0.4062 - val_loss: 3.0021 - val_accuracy: 0.2188\n",
"Epoch 2243/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6444 - accuracy: 0.6562 - val_loss: 2.9490 - val_accuracy: 0.2188\n",
"Epoch 2244/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7886 - accuracy: 0.5000 - val_loss: 3.0252 - val_accuracy: 0.2188\n",
"Epoch 2245/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8177 - accuracy: 0.5000 - val_loss: 2.9907 - val_accuracy: 0.2188\n",
"Epoch 2246/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6877 - accuracy: 0.5938 - val_loss: 3.0288 - val_accuracy: 0.2188\n",
"Epoch 2247/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6250 - accuracy: 0.5625 - val_loss: 2.9975 - val_accuracy: 0.2188\n",
"Epoch 2248/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6432 - accuracy: 0.6250 - val_loss: 3.0248 - val_accuracy: 0.2188\n",
"Epoch 2249/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7765 - accuracy: 0.5625 - val_loss: 3.1025 - val_accuracy: 0.2188\n",
"Epoch 2250/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6711 - accuracy: 0.6562 - val_loss: 3.0908 - val_accuracy: 0.2188\n",
"Epoch 2251/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6146 - accuracy: 0.6875 - val_loss: 3.0892 - val_accuracy: 0.2188\n",
"Epoch 2252/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7771 - accuracy: 0.4062 - val_loss: 2.9995 - val_accuracy: 0.2500\n",
"Epoch 2253/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6360 - accuracy: 0.6562 - val_loss: 2.9968 - val_accuracy: 0.2188\n",
"Epoch 2254/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7241 - accuracy: 0.5625 - val_loss: 3.1194 - val_accuracy: 0.2188\n",
"Epoch 2255/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7725 - accuracy: 0.5000 - val_loss: 2.9908 - val_accuracy: 0.2500\n",
"Epoch 2256/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6845 - accuracy: 0.6562 - val_loss: 3.1666 - val_accuracy: 0.1875\n",
"Epoch 2257/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7611 - accuracy: 0.5938 - val_loss: 3.0658 - val_accuracy: 0.2188\n",
"Epoch 2258/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6743 - accuracy: 0.6250 - val_loss: 3.1058 - val_accuracy: 0.1875\n",
"Epoch 2259/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6619 - accuracy: 0.6562 - val_loss: 3.0605 - val_accuracy: 0.2188\n",
"Epoch 2260/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7001 - accuracy: 0.5625 - val_loss: 3.0826 - val_accuracy: 0.2188\n",
"Epoch 2261/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6105 - accuracy: 0.6562 - val_loss: 3.0913 - val_accuracy: 0.2188\n",
"Epoch 2262/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6755 - accuracy: 0.5938 - val_loss: 3.0788 - val_accuracy: 0.2188\n",
"Epoch 2263/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6725 - accuracy: 0.6562 - val_loss: 3.1252 - val_accuracy: 0.1875\n",
"Epoch 2264/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7054 - accuracy: 0.5000 - val_loss: 3.0714 - val_accuracy: 0.2188\n",
"Epoch 2265/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7220 - accuracy: 0.5938 - val_loss: 3.0922 - val_accuracy: 0.1875\n",
"Epoch 2266/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6399 - accuracy: 0.5625 - val_loss: 3.1221 - val_accuracy: 0.1875\n",
"Epoch 2267/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7075 - accuracy: 0.5938 - val_loss: 3.1456 - val_accuracy: 0.1875\n",
"Epoch 2268/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5964 - accuracy: 0.6250 - val_loss: 3.1319 - val_accuracy: 0.1875\n",
"Epoch 2269/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7081 - accuracy: 0.5625 - val_loss: 3.1388 - val_accuracy: 0.1875\n",
"Epoch 2270/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7937 - accuracy: 0.4688 - val_loss: 3.1769 - val_accuracy: 0.1875\n",
"Epoch 2271/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7988 - accuracy: 0.5312 - val_loss: 3.0911 - val_accuracy: 0.1875\n",
"Epoch 2272/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6446 - accuracy: 0.6250 - val_loss: 3.2210 - val_accuracy: 0.2188\n",
"Epoch 2273/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6591 - accuracy: 0.5625 - val_loss: 3.1620 - val_accuracy: 0.2188\n",
"Epoch 2274/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6484 - accuracy: 0.6250 - val_loss: 3.0639 - val_accuracy: 0.1875\n",
"Epoch 2275/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6152 - accuracy: 0.6250 - val_loss: 3.1033 - val_accuracy: 0.2188\n",
"Epoch 2276/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7127 - accuracy: 0.5938 - val_loss: 3.2608 - val_accuracy: 0.2188\n",
"Epoch 2277/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7710 - accuracy: 0.4688 - val_loss: 3.0647 - val_accuracy: 0.1875\n",
"Epoch 2278/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7278 - accuracy: 0.5000 - val_loss: 3.1817 - val_accuracy: 0.1562\n",
"Epoch 2279/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6387 - accuracy: 0.6250 - val_loss: 3.0825 - val_accuracy: 0.1875\n",
"Epoch 2280/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5871 - accuracy: 0.6562 - val_loss: 3.1010 - val_accuracy: 0.1875\n",
"Epoch 2281/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7780 - accuracy: 0.5938 - val_loss: 3.1426 - val_accuracy: 0.1562\n",
"Epoch 2282/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8252 - accuracy: 0.5625 - val_loss: 3.0981 - val_accuracy: 0.1562\n",
"Epoch 2283/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7081 - accuracy: 0.5625 - val_loss: 3.0587 - val_accuracy: 0.1562\n",
"Epoch 2284/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6362 - accuracy: 0.6250 - val_loss: 3.1131 - val_accuracy: 0.1562\n",
"Epoch 2285/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7873 - accuracy: 0.5625 - val_loss: 3.1066 - val_accuracy: 0.1562\n",
"Epoch 2286/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5559 - accuracy: 0.6875 - val_loss: 3.1326 - val_accuracy: 0.1562\n",
"Epoch 2287/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7040 - accuracy: 0.5312 - val_loss: 3.1228 - val_accuracy: 0.1562\n",
"Epoch 2288/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6146 - accuracy: 0.6250 - val_loss: 3.1711 - val_accuracy: 0.2188\n",
"Epoch 2289/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6944 - accuracy: 0.6250 - val_loss: 3.0999 - val_accuracy: 0.2188\n",
"Epoch 2290/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7483 - accuracy: 0.5312 - val_loss: 3.2429 - val_accuracy: 0.2188\n",
"Epoch 2291/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7444 - accuracy: 0.5000 - val_loss: 3.1005 - val_accuracy: 0.2188\n",
"Epoch 2292/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5842 - accuracy: 0.6250 - val_loss: 3.1399 - val_accuracy: 0.2188\n",
"Epoch 2293/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6528 - accuracy: 0.5312 - val_loss: 3.1816 - val_accuracy: 0.2188\n",
"Epoch 2294/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6066 - accuracy: 0.5938 - val_loss: 3.2080 - val_accuracy: 0.1875\n",
"Epoch 2295/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6193 - accuracy: 0.6562 - val_loss: 3.1877 - val_accuracy: 0.2188\n",
"Epoch 2296/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5889 - accuracy: 0.6562 - val_loss: 3.3217 - val_accuracy: 0.1875\n",
"Epoch 2297/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6197 - accuracy: 0.5938 - val_loss: 3.2226 - val_accuracy: 0.2188\n",
"Epoch 2298/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6395 - accuracy: 0.6250 - val_loss: 3.2373 - val_accuracy: 0.2188\n",
"Epoch 2299/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7008 - accuracy: 0.6562 - val_loss: 3.3114 - val_accuracy: 0.2188\n",
"Epoch 2300/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6128 - accuracy: 0.5938 - val_loss: 3.1831 - val_accuracy: 0.2188\n",
"Epoch 2301/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6719 - accuracy: 0.6875 - val_loss: 3.1646 - val_accuracy: 0.1875\n",
"Epoch 2302/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8142 - accuracy: 0.5625 - val_loss: 3.3126 - val_accuracy: 0.2188\n",
"Epoch 2303/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6803 - accuracy: 0.5625 - val_loss: 3.2007 - val_accuracy: 0.2188\n",
"Epoch 2304/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6761 - accuracy: 0.5938 - val_loss: 3.1983 - val_accuracy: 0.2188\n",
"Epoch 2305/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6986 - accuracy: 0.4688 - val_loss: 3.3396 - val_accuracy: 0.1875\n",
"Epoch 2306/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7761 - accuracy: 0.5000 - val_loss: 3.2617 - val_accuracy: 0.2188\n",
"Epoch 2307/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5934 - accuracy: 0.5312 - val_loss: 3.3117 - val_accuracy: 0.2188\n",
"Epoch 2308/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6781 - accuracy: 0.6250 - val_loss: 3.2082 - val_accuracy: 0.2188\n",
"Epoch 2309/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6415 - accuracy: 0.5000 - val_loss: 3.2828 - val_accuracy: 0.2188\n",
"Epoch 2310/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6533 - accuracy: 0.5625 - val_loss: 3.2825 - val_accuracy: 0.1875\n",
"Epoch 2311/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7438 - accuracy: 0.5000 - val_loss: 3.2755 - val_accuracy: 0.2188\n",
"Epoch 2312/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6970 - accuracy: 0.5000 - val_loss: 3.2557 - val_accuracy: 0.2188\n",
"Epoch 2313/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.8328 - accuracy: 0.53 - 0s 160ms/step - loss: 0.8328 - accuracy: 0.5312 - val_loss: 3.4078 - val_accuracy: 0.1875\n",
"Epoch 2314/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6846 - accuracy: 0.5625 - val_loss: 3.2313 - val_accuracy: 0.2188\n",
"Epoch 2315/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5362 - accuracy: 0.6875 - val_loss: 3.2578 - val_accuracy: 0.2188\n",
"Epoch 2316/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6709 - accuracy: 0.5312 - val_loss: 3.3984 - val_accuracy: 0.1875\n",
"Epoch 2317/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6485 - accuracy: 0.5000 - val_loss: 3.1877 - val_accuracy: 0.2188\n",
"Epoch 2318/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5897 - accuracy: 0.7188 - val_loss: 3.3166 - val_accuracy: 0.1875\n",
"Epoch 2319/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6572 - accuracy: 0.5625 - val_loss: 3.2883 - val_accuracy: 0.2188\n",
"Epoch 2320/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5573 - accuracy: 0.6250 - val_loss: 3.3595 - val_accuracy: 0.1875\n",
"Epoch 2321/5000\n",
"1/1 [==============================] - 0s 228ms/step - loss: 0.7091 - accuracy: 0.5938 - val_loss: 3.3656 - val_accuracy: 0.1875\n",
"Epoch 2322/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.7374 - accuracy: 0.5625 - val_loss: 3.3237 - val_accuracy: 0.2188\n",
"Epoch 2323/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7468 - accuracy: 0.5625 - val_loss: 3.3503 - val_accuracy: 0.2188\n",
"Epoch 2324/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6701 - accuracy: 0.6250 - val_loss: 3.3306 - val_accuracy: 0.2188\n",
"Epoch 2325/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7380 - accuracy: 0.5625 - val_loss: 3.3527 - val_accuracy: 0.2188\n",
"Epoch 2326/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6043 - accuracy: 0.5312 - val_loss: 3.3524 - val_accuracy: 0.2188\n",
"Epoch 2327/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7983 - accuracy: 0.5625 - val_loss: 3.4820 - val_accuracy: 0.1875\n",
"Epoch 2328/5000\n",
"1/1 [==============================] - 0s 278ms/step - loss: 0.6729 - accuracy: 0.5938 - val_loss: 3.4449 - val_accuracy: 0.1875\n",
"Epoch 2329/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.5605 - accuracy: 0.6875 - val_loss: 3.4687 - val_accuracy: 0.2188\n",
"Epoch 2330/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7841 - accuracy: 0.5312 - val_loss: 3.4126 - val_accuracy: 0.1875\n",
"Epoch 2331/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6231 - accuracy: 0.6250 - val_loss: 3.4065 - val_accuracy: 0.1875\n",
"Epoch 2332/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6710 - accuracy: 0.5938 - val_loss: 3.4877 - val_accuracy: 0.1875\n",
"Epoch 2333/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5520 - accuracy: 0.6875 - val_loss: 3.3800 - val_accuracy: 0.1875\n",
"Epoch 2334/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6839 - accuracy: 0.5312 - val_loss: 3.3936 - val_accuracy: 0.1875\n",
"Epoch 2335/5000\n",
"1/1 [==============================] - 0s 226ms/step - loss: 0.5978 - accuracy: 0.6562 - val_loss: 3.4744 - val_accuracy: 0.1875\n",
"Epoch 2336/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6502 - accuracy: 0.5938 - val_loss: 3.2782 - val_accuracy: 0.1562\n",
"Epoch 2337/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5584 - accuracy: 0.7500 - val_loss: 3.4033 - val_accuracy: 0.1875\n",
"Epoch 2338/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5544 - accuracy: 0.5625 - val_loss: 3.4340 - val_accuracy: 0.1875\n",
"Epoch 2339/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6577 - accuracy: 0.5625 - val_loss: 3.4806 - val_accuracy: 0.1875\n",
"Epoch 2340/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6249 - accuracy: 0.5312 - val_loss: 3.3940 - val_accuracy: 0.1875\n",
"Epoch 2341/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7203 - accuracy: 0.5938 - val_loss: 3.5099 - val_accuracy: 0.1875\n",
"Epoch 2342/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5812 - accuracy: 0.5938 - val_loss: 3.4481 - val_accuracy: 0.1875\n",
"Epoch 2343/5000\n",
"1/1 [==============================] - 0s 229ms/step - loss: 0.5775 - accuracy: 0.6875 - val_loss: 3.4831 - val_accuracy: 0.1875\n",
"Epoch 2344/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.7284 - accuracy: 0.5000 - val_loss: 3.4713 - val_accuracy: 0.1875\n",
"Epoch 2345/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.6428 - accuracy: 0.6250 - val_loss: 3.4243 - val_accuracy: 0.1875\n",
"Epoch 2346/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.7022 - accuracy: 0.4688 - val_loss: 3.3716 - val_accuracy: 0.1875\n",
"Epoch 2347/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 0.6410 - accuracy: 0.5625 - val_loss: 3.5248 - val_accuracy: 0.1875\n",
"Epoch 2348/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6823 - accuracy: 0.5625 - val_loss: 3.3443 - val_accuracy: 0.1875\n",
"Epoch 2349/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.5785 - accuracy: 0.6562 - val_loss: 3.5430 - val_accuracy: 0.1875\n",
"Epoch 2350/5000\n",
"1/1 [==============================] - 0s 222ms/step - loss: 0.5401 - accuracy: 0.6562 - val_loss: 3.4855 - val_accuracy: 0.1875\n",
"Epoch 2351/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6899 - accuracy: 0.5000 - val_loss: 3.4799 - val_accuracy: 0.1875\n",
"Epoch 2352/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6703 - accuracy: 0.5625 - val_loss: 3.4783 - val_accuracy: 0.1875\n",
"Epoch 2353/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7000 - accuracy: 0.5938 - val_loss: 3.4377 - val_accuracy: 0.2188\n",
"Epoch 2354/5000\n",
"1/1 [==============================] - 0s 345ms/step - loss: 0.6771 - accuracy: 0.5625 - val_loss: 3.6125 - val_accuracy: 0.1875\n",
"Epoch 2355/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6606 - accuracy: 0.6250 - val_loss: 3.4822 - val_accuracy: 0.1875\n",
"Epoch 2356/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5598 - accuracy: 0.6250 - val_loss: 3.4547 - val_accuracy: 0.1875\n",
"Epoch 2357/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6636 - accuracy: 0.6562 - val_loss: 3.3988 - val_accuracy: 0.1875\n",
"Epoch 2358/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7193 - accuracy: 0.6250 - val_loss: 3.5423 - val_accuracy: 0.1875\n",
"Epoch 2359/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5892 - accuracy: 0.5312 - val_loss: 3.4817 - val_accuracy: 0.1875\n",
"Epoch 2360/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6952 - accuracy: 0.6250 - val_loss: 3.4209 - val_accuracy: 0.1875\n",
"Epoch 2361/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7329 - accuracy: 0.5312 - val_loss: 3.4385 - val_accuracy: 0.1875\n",
"Epoch 2362/5000\n",
"1/1 [==============================] - 0s 363ms/step - loss: 0.6805 - accuracy: 0.5625 - val_loss: 3.4861 - val_accuracy: 0.1875\n",
"Epoch 2363/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6029 - accuracy: 0.6562 - val_loss: 3.3322 - val_accuracy: 0.1875\n",
"Epoch 2364/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7098 - accuracy: 0.6250 - val_loss: 3.5192 - val_accuracy: 0.1875\n",
"Epoch 2365/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5606 - accuracy: 0.6875 - val_loss: 3.4085 - val_accuracy: 0.1875\n",
"Epoch 2366/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6958 - accuracy: 0.4375 - val_loss: 3.4846 - val_accuracy: 0.1875\n",
"Epoch 2367/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6825 - accuracy: 0.5312 - val_loss: 3.4050 - val_accuracy: 0.1875\n",
"Epoch 2368/5000\n",
"1/1 [==============================] - 0s 479ms/step - loss: 0.6606 - accuracy: 0.5938 - val_loss: 3.3794 - val_accuracy: 0.1875\n",
"Epoch 2369/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6872 - accuracy: 0.4688 - val_loss: 3.5868 - val_accuracy: 0.2188\n",
"Epoch 2370/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.6602 - accuracy: 0.6250 - val_loss: 3.2952 - val_accuracy: 0.1562\n",
"Epoch 2371/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5918 - accuracy: 0.6562 - val_loss: 3.5571 - val_accuracy: 0.1875\n",
"Epoch 2372/5000\n",
"1/1 [==============================] - 0s 271ms/step - loss: 0.6742 - accuracy: 0.6250 - val_loss: 3.3819 - val_accuracy: 0.1562\n",
"Epoch 2373/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.6158 - accuracy: 0.5625 - val_loss: 3.4361 - val_accuracy: 0.1875\n",
"Epoch 2374/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6852 - accuracy: 0.5312 - val_loss: 3.4114 - val_accuracy: 0.1562\n",
"Epoch 2375/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5174 - accuracy: 0.6875 - val_loss: 3.2735 - val_accuracy: 0.1875\n",
"Epoch 2376/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.4991 - accuracy: 0.6562 - val_loss: 3.5136 - val_accuracy: 0.1562\n",
"Epoch 2377/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6262 - accuracy: 0.6875 - val_loss: 3.4248 - val_accuracy: 0.1562\n",
"Epoch 2378/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6156 - accuracy: 0.5625 - val_loss: 3.4680 - val_accuracy: 0.2188\n",
"Epoch 2379/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7292 - accuracy: 0.5312 - val_loss: 3.5246 - val_accuracy: 0.1875\n",
"Epoch 2380/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5488 - accuracy: 0.6250 - val_loss: 3.4478 - val_accuracy: 0.1875\n",
"Epoch 2381/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5568 - accuracy: 0.6562 - val_loss: 3.4614 - val_accuracy: 0.1875\n",
"Epoch 2382/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.4965 - accuracy: 0.7812 - val_loss: 3.4989 - val_accuracy: 0.1875\n",
"Epoch 2383/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5855 - accuracy: 0.5938 - val_loss: 3.3747 - val_accuracy: 0.1875\n",
"Epoch 2384/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5947 - accuracy: 0.6250 - val_loss: 3.4266 - val_accuracy: 0.1875\n",
"Epoch 2385/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6629 - accuracy: 0.6875 - val_loss: 3.4243 - val_accuracy: 0.2188\n",
"Epoch 2386/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6768 - accuracy: 0.5625 - val_loss: 3.6321 - val_accuracy: 0.2188\n",
"Epoch 2387/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7001 - accuracy: 0.5000 - val_loss: 3.3218 - val_accuracy: 0.2188\n",
"Epoch 2388/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6759 - accuracy: 0.6250 - val_loss: 3.6066 - val_accuracy: 0.1875\n",
"Epoch 2389/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6885 - accuracy: 0.6562 - val_loss: 3.4857 - val_accuracy: 0.1875\n",
"Epoch 2390/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7246 - accuracy: 0.5312 - val_loss: 3.3634 - val_accuracy: 0.1875\n",
"Epoch 2391/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6253 - accuracy: 0.5000 - val_loss: 3.3711 - val_accuracy: 0.1875\n",
"Epoch 2392/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6757 - accuracy: 0.6250 - val_loss: 3.4494 - val_accuracy: 0.1875\n",
"Epoch 2393/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6321 - accuracy: 0.5938 - val_loss: 3.5131 - val_accuracy: 0.1875\n",
"Epoch 2394/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5833 - accuracy: 0.7500 - val_loss: 3.4595 - val_accuracy: 0.1875\n",
"Epoch 2395/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.5794 - accuracy: 0.5625 - val_loss: 3.4175 - val_accuracy: 0.1875\n",
"Epoch 2396/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5984 - accuracy: 0.6562 - val_loss: 3.5364 - val_accuracy: 0.1875\n",
"Epoch 2397/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7295 - accuracy: 0.4688 - val_loss: 3.5581 - val_accuracy: 0.2188\n",
"Epoch 2398/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5948 - accuracy: 0.7500 - val_loss: 3.6019 - val_accuracy: 0.1875\n",
"Epoch 2399/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7703 - accuracy: 0.6875 - val_loss: 3.4615 - val_accuracy: 0.2188\n",
"Epoch 2400/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6187 - accuracy: 0.6250 - val_loss: 3.7512 - val_accuracy: 0.1875\n",
"Epoch 2401/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6846 - accuracy: 0.6562 - val_loss: 3.2621 - val_accuracy: 0.1875\n",
"Epoch 2402/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8086 - accuracy: 0.4062 - val_loss: 4.0420 - val_accuracy: 0.1875\n",
"Epoch 2403/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7058 - accuracy: 0.5625 - val_loss: 3.1464 - val_accuracy: 0.2188\n",
"Epoch 2404/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7943 - accuracy: 0.5000 - val_loss: 3.6978 - val_accuracy: 0.2188\n",
"Epoch 2405/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8651 - accuracy: 0.3750 - val_loss: 3.1951 - val_accuracy: 0.1562\n",
"Epoch 2406/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6697 - accuracy: 0.6250 - val_loss: 3.4897 - val_accuracy: 0.1875\n",
"Epoch 2407/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6567 - accuracy: 0.5625 - val_loss: 3.4861 - val_accuracy: 0.1875\n",
"Epoch 2408/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6592 - accuracy: 0.6562 - val_loss: 3.4936 - val_accuracy: 0.1875\n",
"Epoch 2409/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6372 - accuracy: 0.5938 - val_loss: 3.6254 - val_accuracy: 0.1875\n",
"Epoch 2410/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6332 - accuracy: 0.5625 - val_loss: 3.3227 - val_accuracy: 0.1875\n",
"Epoch 2411/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7971 - accuracy: 0.6875 - val_loss: 3.7484 - val_accuracy: 0.1875\n",
"Epoch 2412/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7096 - accuracy: 0.5625 - val_loss: 3.3566 - val_accuracy: 0.1875\n",
"Epoch 2413/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6931 - accuracy: 0.5938 - val_loss: 3.4888 - val_accuracy: 0.1875\n",
"Epoch 2414/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7750 - accuracy: 0.5625 - val_loss: 3.6968 - val_accuracy: 0.1875\n",
"Epoch 2415/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6724 - accuracy: 0.5000 - val_loss: 3.4909 - val_accuracy: 0.1875\n",
"Epoch 2416/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6019 - accuracy: 0.5625 - val_loss: 3.6407 - val_accuracy: 0.1875\n",
"Epoch 2417/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6087 - accuracy: 0.6562 - val_loss: 3.5605 - val_accuracy: 0.1875\n",
"Epoch 2418/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.6009 - accuracy: 0.5312 - val_loss: 3.4825 - val_accuracy: 0.1875\n",
"Epoch 2419/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6283 - accuracy: 0.6562 - val_loss: 3.5925 - val_accuracy: 0.1875\n",
"Epoch 2420/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6902 - accuracy: 0.6250 - val_loss: 3.5584 - val_accuracy: 0.1875\n",
"Epoch 2421/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6426 - accuracy: 0.5000 - val_loss: 3.6732 - val_accuracy: 0.1875\n",
"Epoch 2422/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6140 - accuracy: 0.6250 - val_loss: 3.5244 - val_accuracy: 0.1875\n",
"Epoch 2423/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6607 - accuracy: 0.5938 - val_loss: 3.5945 - val_accuracy: 0.1875\n",
"Epoch 2424/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5531 - accuracy: 0.6562 - val_loss: 3.5971 - val_accuracy: 0.1875\n",
"Epoch 2425/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6103 - accuracy: 0.6562 - val_loss: 3.5742 - val_accuracy: 0.1875\n",
"Epoch 2426/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6097 - accuracy: 0.6250 - val_loss: 3.5447 - val_accuracy: 0.1875\n",
"Epoch 2427/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6676 - accuracy: 0.5625 - val_loss: 3.6522 - val_accuracy: 0.1875\n",
"Epoch 2428/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6991 - accuracy: 0.5000 - val_loss: 3.5114 - val_accuracy: 0.1875\n",
"Epoch 2429/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7288 - accuracy: 0.5938 - val_loss: 3.6290 - val_accuracy: 0.1875\n",
"Epoch 2430/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5204 - accuracy: 0.6562 - val_loss: 3.5953 - val_accuracy: 0.1875\n",
"Epoch 2431/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5954 - accuracy: 0.6875 - val_loss: 3.5652 - val_accuracy: 0.1875\n",
"Epoch 2432/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6580 - accuracy: 0.5000 - val_loss: 3.5901 - val_accuracy: 0.1875\n",
"Epoch 2433/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.6110 - accuracy: 0.6250 - val_loss: 3.6574 - val_accuracy: 0.1875\n",
"Epoch 2434/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5915 - accuracy: 0.7188 - val_loss: 3.5032 - val_accuracy: 0.1875\n",
"Epoch 2435/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7352 - accuracy: 0.5000 - val_loss: 3.6026 - val_accuracy: 0.1875\n",
"Epoch 2436/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5935 - accuracy: 0.5312 - val_loss: 3.5967 - val_accuracy: 0.1875\n",
"Epoch 2437/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6738 - accuracy: 0.6562 - val_loss: 3.5190 - val_accuracy: 0.1875\n",
"Epoch 2438/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6434 - accuracy: 0.5938 - val_loss: 3.4864 - val_accuracy: 0.1875\n",
"Epoch 2439/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6221 - accuracy: 0.6875 - val_loss: 3.6646 - val_accuracy: 0.1875\n",
"Epoch 2440/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5627 - accuracy: 0.7188 - val_loss: 3.4607 - val_accuracy: 0.1562\n",
"Epoch 2441/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7274 - accuracy: 0.5312 - val_loss: 3.7804 - val_accuracy: 0.1875\n",
"Epoch 2442/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6310 - accuracy: 0.5625 - val_loss: 3.4854 - val_accuracy: 0.1875\n",
"Epoch 2443/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6439 - accuracy: 0.5938 - val_loss: 3.7850 - val_accuracy: 0.1875\n",
"Epoch 2444/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6457 - accuracy: 0.5625 - val_loss: 3.5945 - val_accuracy: 0.1875\n",
"Epoch 2445/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6082 - accuracy: 0.6562 - val_loss: 3.6612 - val_accuracy: 0.1875\n",
"Epoch 2446/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5726 - accuracy: 0.5625 - val_loss: 3.5827 - val_accuracy: 0.1875\n",
"Epoch 2447/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6691 - accuracy: 0.5000 - val_loss: 3.7689 - val_accuracy: 0.1875\n",
"Epoch 2448/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5748 - accuracy: 0.6875 - val_loss: 3.4596 - val_accuracy: 0.1875\n",
"Epoch 2449/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6327 - accuracy: 0.6562 - val_loss: 3.5343 - val_accuracy: 0.1875\n",
"Epoch 2450/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6259 - accuracy: 0.6250 - val_loss: 3.4769 - val_accuracy: 0.1875\n",
"Epoch 2451/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6242 - accuracy: 0.6250 - val_loss: 3.6771 - val_accuracy: 0.1875\n",
"Epoch 2452/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6278 - accuracy: 0.5938 - val_loss: 3.6174 - val_accuracy: 0.1875\n",
"Epoch 2453/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6882 - accuracy: 0.6250 - val_loss: 3.5447 - val_accuracy: 0.1875\n",
"Epoch 2454/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5959 - accuracy: 0.5938 - val_loss: 3.6789 - val_accuracy: 0.1875\n",
"Epoch 2455/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5342 - accuracy: 0.6562 - val_loss: 3.4863 - val_accuracy: 0.1562\n",
"Epoch 2456/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6362 - accuracy: 0.5938 - val_loss: 3.8633 - val_accuracy: 0.1562\n",
"Epoch 2457/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6020 - accuracy: 0.5625 - val_loss: 3.4300 - val_accuracy: 0.1562\n",
"Epoch 2458/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6820 - accuracy: 0.5938 - val_loss: 3.7678 - val_accuracy: 0.1562\n",
"Epoch 2459/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7419 - accuracy: 0.4375 - val_loss: 3.5605 - val_accuracy: 0.1875\n",
"Epoch 2460/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5390 - accuracy: 0.6562 - val_loss: 3.5784 - val_accuracy: 0.1875\n",
"Epoch 2461/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7009 - accuracy: 0.5000 - val_loss: 3.6222 - val_accuracy: 0.1875\n",
"Epoch 2462/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6525 - accuracy: 0.5938 - val_loss: 3.5054 - val_accuracy: 0.1875\n",
"Epoch 2463/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6460 - accuracy: 0.5312 - val_loss: 3.8274 - val_accuracy: 0.2188\n",
"Epoch 2464/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6528 - accuracy: 0.5625 - val_loss: 3.3785 - val_accuracy: 0.1875\n",
"Epoch 2465/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8275 - accuracy: 0.6562 - val_loss: 3.4225 - val_accuracy: 0.1875\n",
"Epoch 2466/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6837 - accuracy: 0.5312 - val_loss: 4.2015 - val_accuracy: 0.1875\n",
"Epoch 2467/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8530 - accuracy: 0.4062 - val_loss: 3.2897 - val_accuracy: 0.2188\n",
"Epoch 2468/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.8463 - accuracy: 0.5000 - val_loss: 3.8991 - val_accuracy: 0.2188\n",
"Epoch 2469/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7032 - accuracy: 0.4688 - val_loss: 3.4733 - val_accuracy: 0.1875\n",
"Epoch 2470/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5731 - accuracy: 0.6250 - val_loss: 3.7031 - val_accuracy: 0.1875\n",
"Epoch 2471/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5933 - accuracy: 0.5938 - val_loss: 3.5678 - val_accuracy: 0.1875\n",
"Epoch 2472/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5949 - accuracy: 0.6562 - val_loss: 3.6687 - val_accuracy: 0.1875\n",
"Epoch 2473/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6041 - accuracy: 0.5000 - val_loss: 3.6125 - val_accuracy: 0.1875\n",
"Epoch 2474/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5817 - accuracy: 0.6562 - val_loss: 3.5894 - val_accuracy: 0.1875\n",
"Epoch 2475/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5819 - accuracy: 0.5625 - val_loss: 3.5526 - val_accuracy: 0.1875\n",
"Epoch 2476/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7316 - accuracy: 0.4375 - val_loss: 3.6122 - val_accuracy: 0.1875\n",
"Epoch 2477/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5564 - accuracy: 0.6875 - val_loss: 3.6775 - val_accuracy: 0.1875\n",
"Epoch 2478/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6469 - accuracy: 0.5938 - val_loss: 3.6719 - val_accuracy: 0.1875\n",
"Epoch 2479/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5875 - accuracy: 0.6562 - val_loss: 3.6140 - val_accuracy: 0.1875\n",
"Epoch 2480/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.4923 - accuracy: 0.7812 - val_loss: 3.4852 - val_accuracy: 0.1875\n",
"Epoch 2481/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6708 - accuracy: 0.5625 - val_loss: 3.6475 - val_accuracy: 0.2188\n",
"Epoch 2482/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5000 - accuracy: 0.6875 - val_loss: 3.5311 - val_accuracy: 0.1875\n",
"Epoch 2483/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7513 - accuracy: 0.5938 - val_loss: 3.5531 - val_accuracy: 0.1875\n",
"Epoch 2484/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6781 - accuracy: 0.5312 - val_loss: 3.6421 - val_accuracy: 0.1875\n",
"Epoch 2485/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6153 - accuracy: 0.6562 - val_loss: 3.6004 - val_accuracy: 0.1875\n",
"Epoch 2486/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7325 - accuracy: 0.5938 - val_loss: 3.6454 - val_accuracy: 0.1875\n",
"Epoch 2487/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.5644 - accuracy: 0.7500 - val_loss: 3.6387 - val_accuracy: 0.1875\n",
"Epoch 2488/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5708 - accuracy: 0.5625 - val_loss: 3.6673 - val_accuracy: 0.1875\n",
"Epoch 2489/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6265 - accuracy: 0.5625 - val_loss: 3.5474 - val_accuracy: 0.1875\n",
"Epoch 2490/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5252 - accuracy: 0.5938 - val_loss: 3.6301 - val_accuracy: 0.1875\n",
"Epoch 2491/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5300 - accuracy: 0.7500 - val_loss: 3.5526 - val_accuracy: 0.1875\n",
"Epoch 2492/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6267 - accuracy: 0.5938 - val_loss: 3.7072 - val_accuracy: 0.1875\n",
"Epoch 2493/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5211 - accuracy: 0.6250 - val_loss: 3.6108 - val_accuracy: 0.1875\n",
"Epoch 2494/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5370 - accuracy: 0.6875 - val_loss: 3.6034 - val_accuracy: 0.1875\n",
"Epoch 2495/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6946 - accuracy: 0.5625 - val_loss: 3.6841 - val_accuracy: 0.1875\n",
"Epoch 2496/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7187 - accuracy: 0.6250 - val_loss: 3.6276 - val_accuracy: 0.1875\n",
"Epoch 2497/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6201 - accuracy: 0.5312 - val_loss: 3.6904 - val_accuracy: 0.1875\n",
"Epoch 2498/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.6191 - accuracy: 0.6250 - val_loss: 3.6694 - val_accuracy: 0.1875\n",
"Epoch 2499/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6570 - accuracy: 0.6250 - val_loss: 3.5524 - val_accuracy: 0.1875\n",
"Epoch 2500/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6552 - accuracy: 0.5312 - val_loss: 3.7882 - val_accuracy: 0.2188\n",
"Epoch 2501/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6861 - accuracy: 0.5312 - val_loss: 3.5427 - val_accuracy: 0.1875\n",
"Epoch 2502/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7113 - accuracy: 0.6250 - val_loss: 3.7201 - val_accuracy: 0.1875\n",
"Epoch 2503/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5345 - accuracy: 0.5938 - val_loss: 3.5238 - val_accuracy: 0.1875\n",
"Epoch 2504/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6188 - accuracy: 0.6250 - val_loss: 3.6779 - val_accuracy: 0.1875\n",
"Epoch 2505/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6241 - accuracy: 0.6562 - val_loss: 3.6317 - val_accuracy: 0.1875\n",
"Epoch 2506/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4733 - accuracy: 0.7500 - val_loss: 3.7122 - val_accuracy: 0.1875\n",
"Epoch 2507/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6370 - accuracy: 0.6562 - val_loss: 3.8606 - val_accuracy: 0.2188\n",
"Epoch 2508/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5614 - accuracy: 0.6562 - val_loss: 3.7738 - val_accuracy: 0.2188\n",
"Epoch 2509/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6230 - accuracy: 0.5625 - val_loss: 3.5650 - val_accuracy: 0.2188\n",
"Epoch 2510/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6167 - accuracy: 0.5000 - val_loss: 3.9563 - val_accuracy: 0.2188\n",
"Epoch 2511/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5733 - accuracy: 0.6562 - val_loss: 3.5691 - val_accuracy: 0.2500\n",
"Epoch 2512/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6329 - accuracy: 0.6562 - val_loss: 3.5217 - val_accuracy: 0.2188\n",
"Epoch 2513/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7060 - accuracy: 0.5312 - val_loss: 3.8793 - val_accuracy: 0.2188\n",
"Epoch 2514/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5288 - accuracy: 0.7188 - val_loss: 3.5089 - val_accuracy: 0.2500\n",
"Epoch 2515/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.6384 - accuracy: 0.5938 - val_loss: 3.8906 - val_accuracy: 0.2188\n",
"Epoch 2516/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5709 - accuracy: 0.6250 - val_loss: 3.4983 - val_accuracy: 0.2500\n",
"Epoch 2517/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5871 - accuracy: 0.6250 - val_loss: 3.8198 - val_accuracy: 0.2188\n",
"Epoch 2518/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5974 - accuracy: 0.5312 - val_loss: 3.4971 - val_accuracy: 0.2500\n",
"Epoch 2519/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5843 - accuracy: 0.6250 - val_loss: 3.7714 - val_accuracy: 0.2188\n",
"Epoch 2520/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6606 - accuracy: 0.4688 - val_loss: 3.7379 - val_accuracy: 0.1875\n",
"Epoch 2521/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.6142 - accuracy: 0.7188 - val_loss: 3.6921 - val_accuracy: 0.1875\n",
"Epoch 2522/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7447 - accuracy: 0.5625 - val_loss: 3.6035 - val_accuracy: 0.1875\n",
"Epoch 2523/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.5992 - accuracy: 0.6562 - val_loss: 3.5905 - val_accuracy: 0.1875\n",
"Epoch 2524/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.5176 - accuracy: 0.7500 - val_loss: 3.6329 - val_accuracy: 0.1875\n",
"Epoch 2525/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.6372 - accuracy: 0.5938 - val_loss: 3.7777 - val_accuracy: 0.1875\n",
"Epoch 2526/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5755 - accuracy: 0.6875 - val_loss: 3.7183 - val_accuracy: 0.1875\n",
"Epoch 2527/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5253 - accuracy: 0.6562 - val_loss: 3.6435 - val_accuracy: 0.1875\n",
"Epoch 2528/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6411 - accuracy: 0.6875 - val_loss: 3.7353 - val_accuracy: 0.1875\n",
"Epoch 2529/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6258 - accuracy: 0.5312 - val_loss: 3.6196 - val_accuracy: 0.1875\n",
"Epoch 2530/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7411 - accuracy: 0.5312 - val_loss: 3.8177 - val_accuracy: 0.1875\n",
"Epoch 2531/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5408 - accuracy: 0.6875 - val_loss: 3.5808 - val_accuracy: 0.1875\n",
"Epoch 2532/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6628 - accuracy: 0.5625 - val_loss: 3.6347 - val_accuracy: 0.1875\n",
"Epoch 2533/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6451 - accuracy: 0.6250 - val_loss: 3.6516 - val_accuracy: 0.1875\n",
"Epoch 2534/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6098 - accuracy: 0.6875 - val_loss: 3.7144 - val_accuracy: 0.1875\n",
"Epoch 2535/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5078 - accuracy: 0.6875 - val_loss: 3.6493 - val_accuracy: 0.1875\n",
"Epoch 2536/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6141 - accuracy: 0.5312 - val_loss: 3.7703 - val_accuracy: 0.1875\n",
"Epoch 2537/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6054 - accuracy: 0.6250 - val_loss: 3.6504 - val_accuracy: 0.1875\n",
"Epoch 2538/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5173 - accuracy: 0.5938 - val_loss: 3.7646 - val_accuracy: 0.1875\n",
"Epoch 2539/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6021 - accuracy: 0.5312 - val_loss: 3.6676 - val_accuracy: 0.1875\n",
"Epoch 2540/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6609 - accuracy: 0.5625 - val_loss: 3.6384 - val_accuracy: 0.1875\n",
"Epoch 2541/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.5451 - accuracy: 0.6250 - val_loss: 3.5694 - val_accuracy: 0.1875\n",
"Epoch 2542/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6081 - accuracy: 0.6250 - val_loss: 3.9857 - val_accuracy: 0.2188\n",
"Epoch 2543/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8004 - accuracy: 0.5000 - val_loss: 3.3471 - val_accuracy: 0.2500\n",
"Epoch 2544/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8763 - accuracy: 0.5000 - val_loss: 4.3708 - val_accuracy: 0.1875\n",
"Epoch 2545/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7653 - accuracy: 0.3750 - val_loss: 3.4870 - val_accuracy: 0.1875\n",
"Epoch 2546/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5141 - accuracy: 0.6875 - val_loss: 3.5109 - val_accuracy: 0.1875\n",
"Epoch 2547/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7386 - accuracy: 0.5000 - val_loss: 3.8152 - val_accuracy: 0.2188\n",
"Epoch 2548/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6187 - accuracy: 0.6562 - val_loss: 3.5285 - val_accuracy: 0.1875\n",
"Epoch 2549/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7727 - accuracy: 0.6250 - val_loss: 3.8542 - val_accuracy: 0.1875\n",
"Epoch 2550/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7489 - accuracy: 0.4688 - val_loss: 3.5707 - val_accuracy: 0.1875\n",
"Epoch 2551/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6703 - accuracy: 0.4688 - val_loss: 3.9505 - val_accuracy: 0.2188\n",
"Epoch 2552/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6845 - accuracy: 0.6250 - val_loss: 3.3322 - val_accuracy: 0.1875\n",
"Epoch 2553/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.8503 - accuracy: 0.5312 - val_loss: 4.4409 - val_accuracy: 0.1562\n",
"Epoch 2554/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.0389 - accuracy: 0.4688 - val_loss: 3.2869 - val_accuracy: 0.1250\n",
"Epoch 2555/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.6314 - accuracy: 0.3750 - val_loss: 7.7064 - val_accuracy: 0.0312\n",
"Epoch 2556/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 5.8285 - accuracy: 0.1250 - val_loss: 3.4733 - val_accuracy: 0.1875\n",
"Epoch 2557/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8753 - accuracy: 0.4062 - val_loss: 3.0586 - val_accuracy: 0.1875\n",
"Epoch 2558/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8423 - accuracy: 0.4375 - val_loss: 3.2716 - val_accuracy: 0.1562\n",
"Epoch 2559/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6920 - accuracy: 0.6250 - val_loss: 3.1709 - val_accuracy: 0.1562\n",
"Epoch 2560/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8292 - accuracy: 0.4688 - val_loss: 3.2407 - val_accuracy: 0.1875\n",
"Epoch 2561/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7707 - accuracy: 0.4062 - val_loss: 3.2194 - val_accuracy: 0.1875\n",
"Epoch 2562/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6993 - accuracy: 0.6562 - val_loss: 3.4519 - val_accuracy: 0.1562\n",
"Epoch 2563/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.6541 - accuracy: 0.5938 - val_loss: 3.2778 - val_accuracy: 0.1875\n",
"Epoch 2564/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8097 - accuracy: 0.5625 - val_loss: 3.3404 - val_accuracy: 0.1562\n",
"Epoch 2565/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6584 - accuracy: 0.6875 - val_loss: 3.3066 - val_accuracy: 0.1875\n",
"Epoch 2566/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6773 - accuracy: 0.6250 - val_loss: 3.3361 - val_accuracy: 0.1562\n",
"Epoch 2567/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7356 - accuracy: 0.6562 - val_loss: 3.3510 - val_accuracy: 0.1875\n",
"Epoch 2568/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6159 - accuracy: 0.6562 - val_loss: 3.3563 - val_accuracy: 0.1875\n",
"Epoch 2569/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6926 - accuracy: 0.5312 - val_loss: 3.4188 - val_accuracy: 0.1875\n",
"Epoch 2570/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6268 - accuracy: 0.5938 - val_loss: 3.3681 - val_accuracy: 0.1875\n",
"Epoch 2571/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6623 - accuracy: 0.6250 - val_loss: 3.4955 - val_accuracy: 0.1875\n",
"Epoch 2572/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6401 - accuracy: 0.5938 - val_loss: 3.2853 - val_accuracy: 0.1562\n",
"Epoch 2573/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6538 - accuracy: 0.5625 - val_loss: 3.4498 - val_accuracy: 0.1875\n",
"Epoch 2574/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6213 - accuracy: 0.6250 - val_loss: 3.4159 - val_accuracy: 0.1875\n",
"Epoch 2575/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7070 - accuracy: 0.5938 - val_loss: 3.4332 - val_accuracy: 0.1875\n",
"Epoch 2576/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5991 - accuracy: 0.7500 - val_loss: 3.4952 - val_accuracy: 0.1875\n",
"Epoch 2577/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6476 - accuracy: 0.6250 - val_loss: 3.4234 - val_accuracy: 0.1875\n",
"Epoch 2578/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5531 - accuracy: 0.7500 - val_loss: 3.3504 - val_accuracy: 0.1875\n",
"Epoch 2579/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6186 - accuracy: 0.6875 - val_loss: 3.5106 - val_accuracy: 0.1875\n",
"Epoch 2580/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6986 - accuracy: 0.5625 - val_loss: 3.5089 - val_accuracy: 0.1875\n",
"Epoch 2581/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6133 - accuracy: 0.6875 - val_loss: 3.3310 - val_accuracy: 0.1875\n",
"Epoch 2582/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.0512 - accuracy: 0.5312 - val_loss: 3.3248 - val_accuracy: 0.1875\n",
"Epoch 2583/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6247 - accuracy: 0.6250 - val_loss: 3.5252 - val_accuracy: 0.1875\n",
"Epoch 2584/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.7059 - accuracy: 0.5938 - val_loss: 3.4083 - val_accuracy: 0.1875\n",
"Epoch 2585/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6264 - accuracy: 0.6875 - val_loss: 3.3993 - val_accuracy: 0.1875\n",
"Epoch 2586/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5796 - accuracy: 0.6875 - val_loss: 3.4591 - val_accuracy: 0.1875\n",
"Epoch 2587/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6272 - accuracy: 0.6875 - val_loss: 3.5410 - val_accuracy: 0.1875\n",
"Epoch 2588/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6959 - accuracy: 0.5625 - val_loss: 3.4921 - val_accuracy: 0.1875\n",
"Epoch 2589/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5990 - accuracy: 0.5312 - val_loss: 3.4406 - val_accuracy: 0.1875\n",
"Epoch 2590/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6386 - accuracy: 0.5625 - val_loss: 3.6551 - val_accuracy: 0.1875\n",
"Epoch 2591/5000\n",
"1/1 [==============================] - 0s 150ms/step - loss: 0.6291 - accuracy: 0.5938 - val_loss: 3.2743 - val_accuracy: 0.1562\n",
"Epoch 2592/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8019 - accuracy: 0.5000 - val_loss: 3.7229 - val_accuracy: 0.1562\n",
"Epoch 2593/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6224 - accuracy: 0.6562 - val_loss: 3.2305 - val_accuracy: 0.1562\n",
"Epoch 2594/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6418 - accuracy: 0.5938 - val_loss: 3.6790 - val_accuracy: 0.2188\n",
"Epoch 2595/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7310 - accuracy: 0.4688 - val_loss: 3.2684 - val_accuracy: 0.1562\n",
"Epoch 2596/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6980 - accuracy: 0.5625 - val_loss: 3.6234 - val_accuracy: 0.1875\n",
"Epoch 2597/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5431 - accuracy: 0.6562 - val_loss: 3.2237 - val_accuracy: 0.1875\n",
"Epoch 2598/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.5648 - accuracy: 0.71 - 0s 170ms/step - loss: 0.5648 - accuracy: 0.7188 - val_loss: 3.7392 - val_accuracy: 0.1875\n",
"Epoch 2599/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6566 - accuracy: 0.5938 - val_loss: 3.2289 - val_accuracy: 0.1562\n",
"Epoch 2600/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7044 - accuracy: 0.5625 - val_loss: 3.5125 - val_accuracy: 0.1875\n",
"Epoch 2601/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6004 - accuracy: 0.6250 - val_loss: 3.4741 - val_accuracy: 0.1875\n",
"Epoch 2602/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6357 - accuracy: 0.5938 - val_loss: 3.5986 - val_accuracy: 0.1875\n",
"Epoch 2603/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6562 - accuracy: 0.5625 - val_loss: 3.5192 - val_accuracy: 0.1875\n",
"Epoch 2604/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6158 - accuracy: 0.5938 - val_loss: 3.5030 - val_accuracy: 0.1875\n",
"Epoch 2605/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6519 - accuracy: 0.5000 - val_loss: 3.3752 - val_accuracy: 0.1875\n",
"Epoch 2606/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5195 - accuracy: 0.6875 - val_loss: 3.4232 - val_accuracy: 0.1875\n",
"Epoch 2607/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6163 - accuracy: 0.6250 - val_loss: 3.5010 - val_accuracy: 0.1875\n",
"Epoch 2608/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6540 - accuracy: 0.6562 - val_loss: 3.5766 - val_accuracy: 0.1875\n",
"Epoch 2609/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.4607 - accuracy: 0.7500 - val_loss: 3.4825 - val_accuracy: 0.1875\n",
"Epoch 2610/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6042 - accuracy: 0.6562 - val_loss: 3.6802 - val_accuracy: 0.1562\n",
"Epoch 2611/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6426 - accuracy: 0.6562 - val_loss: 3.5007 - val_accuracy: 0.1875\n",
"Epoch 2612/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5487 - accuracy: 0.7500 - val_loss: 3.6348 - val_accuracy: 0.1875\n",
"Epoch 2613/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6109 - accuracy: 0.6562 - val_loss: 3.5567 - val_accuracy: 0.1875\n",
"Epoch 2614/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.6257 - accuracy: 0.5625 - val_loss: 3.7167 - val_accuracy: 0.1875\n",
"Epoch 2615/5000\n",
"1/1 [==============================] - 0s 223ms/step - loss: 0.6058 - accuracy: 0.6875 - val_loss: 3.5032 - val_accuracy: 0.1875\n",
"Epoch 2616/5000\n",
"1/1 [==============================] - 0s 211ms/step - loss: 0.6195 - accuracy: 0.6875 - val_loss: 3.7563 - val_accuracy: 0.1875\n",
"Epoch 2617/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6530 - accuracy: 0.5625 - val_loss: 3.5647 - val_accuracy: 0.2188\n",
"Epoch 2618/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6941 - accuracy: 0.5938 - val_loss: 3.6320 - val_accuracy: 0.1875\n",
"Epoch 2619/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6892 - accuracy: 0.5938 - val_loss: 3.4585 - val_accuracy: 0.1875\n",
"Epoch 2620/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6694 - accuracy: 0.5938 - val_loss: 3.6706 - val_accuracy: 0.1875\n",
"Epoch 2621/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4878 - accuracy: 0.7188 - val_loss: 3.4687 - val_accuracy: 0.1875\n",
"Epoch 2622/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6044 - accuracy: 0.5625 - val_loss: 3.7124 - val_accuracy: 0.1562\n",
"Epoch 2623/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6613 - accuracy: 0.6250 - val_loss: 3.4832 - val_accuracy: 0.1875\n",
"Epoch 2624/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.8050 - accuracy: 0.4375 - val_loss: 3.5422 - val_accuracy: 0.1875\n",
"Epoch 2625/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7089 - accuracy: 0.5312 - val_loss: 3.7860 - val_accuracy: 0.2188\n",
"Epoch 2626/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5903 - accuracy: 0.5938 - val_loss: 3.3427 - val_accuracy: 0.1875\n",
"Epoch 2627/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6889 - accuracy: 0.5938 - val_loss: 3.9452 - val_accuracy: 0.1875\n",
"Epoch 2628/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7502 - accuracy: 0.5312 - val_loss: 3.2957 - val_accuracy: 0.1875\n",
"Epoch 2629/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7605 - accuracy: 0.4688 - val_loss: 3.9022 - val_accuracy: 0.2188\n",
"Epoch 2630/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6594 - accuracy: 0.6875 - val_loss: 3.3285 - val_accuracy: 0.1875\n",
"Epoch 2631/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7705 - accuracy: 0.4688 - val_loss: 3.6286 - val_accuracy: 0.2188\n",
"Epoch 2632/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.0028 - accuracy: 0.4688 - val_loss: 3.8445 - val_accuracy: 0.1875\n",
"Epoch 2633/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5357 - accuracy: 0.7500 - val_loss: 3.5059 - val_accuracy: 0.1875\n",
"Epoch 2634/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7044 - accuracy: 0.6562 - val_loss: 3.6597 - val_accuracy: 0.1875\n",
"Epoch 2635/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6900 - accuracy: 0.5312 - val_loss: 3.6936 - val_accuracy: 0.1875\n",
"Epoch 2636/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6249 - accuracy: 0.5625 - val_loss: 3.6256 - val_accuracy: 0.1875\n",
"Epoch 2637/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6697 - accuracy: 0.5625 - val_loss: 3.5418 - val_accuracy: 0.1875\n",
"Epoch 2638/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6007 - accuracy: 0.5625 - val_loss: 3.7473 - val_accuracy: 0.1875\n",
"Epoch 2639/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6998 - accuracy: 0.5938 - val_loss: 3.5460 - val_accuracy: 0.1875\n",
"Epoch 2640/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6367 - accuracy: 0.6875 - val_loss: 3.5989 - val_accuracy: 0.1875\n",
"Epoch 2641/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5793 - accuracy: 0.5938 - val_loss: 3.5492 - val_accuracy: 0.1875\n",
"Epoch 2642/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5209 - accuracy: 0.5938 - val_loss: 3.6673 - val_accuracy: 0.1875\n",
"Epoch 2643/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6703 - accuracy: 0.6250 - val_loss: 3.5789 - val_accuracy: 0.1875\n",
"Epoch 2644/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6504 - accuracy: 0.5625 - val_loss: 3.7634 - val_accuracy: 0.1875\n",
"Epoch 2645/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6029 - accuracy: 0.5625 - val_loss: 3.4748 - val_accuracy: 0.1875\n",
"Epoch 2646/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5872 - accuracy: 0.6875 - val_loss: 3.4866 - val_accuracy: 0.1875\n",
"Epoch 2647/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6764 - accuracy: 0.50 - 0s 161ms/step - loss: 0.6764 - accuracy: 0.5000 - val_loss: 3.7018 - val_accuracy: 0.1875\n",
"Epoch 2648/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6746 - accuracy: 0.6875 - val_loss: 3.5300 - val_accuracy: 0.1875\n",
"Epoch 2649/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6134 - accuracy: 0.6250 - val_loss: 3.5900 - val_accuracy: 0.1875\n",
"Epoch 2650/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6076 - accuracy: 0.6250 - val_loss: 3.6160 - val_accuracy: 0.1875\n",
"Epoch 2651/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6534 - accuracy: 0.5625 - val_loss: 3.6839 - val_accuracy: 0.1875\n",
"Epoch 2652/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5694 - accuracy: 0.6250 - val_loss: 3.4484 - val_accuracy: 0.1562\n",
"Epoch 2653/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6846 - accuracy: 0.6250 - val_loss: 3.8310 - val_accuracy: 0.1875\n",
"Epoch 2654/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6773 - accuracy: 0.5625 - val_loss: 3.4044 - val_accuracy: 0.1562\n",
"Epoch 2655/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6820 - accuracy: 0.5938 - val_loss: 3.9367 - val_accuracy: 0.2188\n",
"Epoch 2656/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6603 - accuracy: 0.6250 - val_loss: 3.3043 - val_accuracy: 0.1562\n",
"Epoch 2657/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7293 - accuracy: 0.6562 - val_loss: 4.0099 - val_accuracy: 0.2500\n",
"Epoch 2658/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7521 - accuracy: 0.5938 - val_loss: 3.2126 - val_accuracy: 0.2188\n",
"Epoch 2659/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8629 - accuracy: 0.5312 - val_loss: 4.2956 - val_accuracy: 0.1562\n",
"Epoch 2660/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.0248 - accuracy: 0.3438 - val_loss: 3.1209 - val_accuracy: 0.1562\n",
"Epoch 2661/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.0260 - accuracy: 0.4688 - val_loss: 5.0133 - val_accuracy: 0.1562\n",
"Epoch 2662/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.9335 - accuracy: 0.2812 - val_loss: 3.8305 - val_accuracy: 0.2500\n",
"Epoch 2663/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 11.7465 - accuracy: 0.2188 - val_loss: 10.3858 - val_accuracy: 0.0312\n",
"Epoch 2664/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 10.0222 - accuracy: 0.0625 - val_loss: 3.4733 - val_accuracy: 0.0938\n",
"Epoch 2665/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 5.0070 - accuracy: 0.1250 - val_loss: 3.2294 - val_accuracy: 0.1250\n",
"Epoch 2666/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 3.8670 - accuracy: 0.0938 - val_loss: 3.1352 - val_accuracy: 0.1250\n",
"Epoch 2667/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 2.6721 - accuracy: 0.1562 - val_loss: 2.9113 - val_accuracy: 0.1250\n",
"Epoch 2668/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.8869 - accuracy: 0.1875 - val_loss: 2.7239 - val_accuracy: 0.0938\n",
"Epoch 2669/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.3826 - accuracy: 0.2188 - val_loss: 2.5371 - val_accuracy: 0.1250\n",
"Epoch 2670/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 2.9615 - accuracy: 0.2500 - val_loss: 2.7427 - val_accuracy: 0.1250\n",
"Epoch 2671/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.7091 - accuracy: 0.3438 - val_loss: 2.9085 - val_accuracy: 0.1250\n",
"Epoch 2672/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 2.2360 - accuracy: 0.1875 - val_loss: 2.9056 - val_accuracy: 0.1562\n",
"Epoch 2673/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.0333 - accuracy: 0.2188 - val_loss: 2.8741 - val_accuracy: 0.1250\n",
"Epoch 2674/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.5110 - accuracy: 0.1250 - val_loss: 2.9173 - val_accuracy: 0.1250\n",
"Epoch 2675/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 2.4504 - accuracy: 0.1875 - val_loss: 2.6829 - val_accuracy: 0.1250\n",
"Epoch 2676/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.8689 - accuracy: 0.2812 - val_loss: 2.8038 - val_accuracy: 0.0938\n",
"Epoch 2677/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.2482 - accuracy: 0.2812 - val_loss: 2.7323 - val_accuracy: 0.0938\n",
"Epoch 2678/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.8414 - accuracy: 0.2188 - val_loss: 2.7473 - val_accuracy: 0.0938\n",
"Epoch 2679/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.1723 - accuracy: 0.1562 - val_loss: 2.8568 - val_accuracy: 0.0938\n",
"Epoch 2680/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.2041 - accuracy: 0.1562 - val_loss: 2.8560 - val_accuracy: 0.0938\n",
"Epoch 2681/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.8007 - accuracy: 0.2812 - val_loss: 2.8481 - val_accuracy: 0.0625\n",
"Epoch 2682/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.6159 - accuracy: 0.2188 - val_loss: 2.7279 - val_accuracy: 0.0938\n",
"Epoch 2683/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.6418 - accuracy: 0.2500 - val_loss: 2.7483 - val_accuracy: 0.0938\n",
"Epoch 2684/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.3055 - accuracy: 0.2188 - val_loss: 2.9030 - val_accuracy: 0.0938\n",
"Epoch 2685/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.7797 - accuracy: 0.2500 - val_loss: 2.8389 - val_accuracy: 0.0938\n",
"Epoch 2686/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.9657 - accuracy: 0.2500 - val_loss: 2.7923 - val_accuracy: 0.0938\n",
"Epoch 2687/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.8333 - accuracy: 0.2500 - val_loss: 2.8977 - val_accuracy: 0.0938\n",
"Epoch 2688/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.9166 - accuracy: 0.2500 - val_loss: 3.2626 - val_accuracy: 0.0938\n",
"Epoch 2689/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.2539 - accuracy: 0.1875 - val_loss: 3.0931 - val_accuracy: 0.0625\n",
"Epoch 2690/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.6736 - accuracy: 0.2188 - val_loss: 2.9088 - val_accuracy: 0.0938\n",
"Epoch 2691/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.8923 - accuracy: 0.1875 - val_loss: 2.8963 - val_accuracy: 0.0938\n",
"Epoch 2692/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.6203 - accuracy: 0.2812 - val_loss: 2.8281 - val_accuracy: 0.0938\n",
"Epoch 2693/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.2736 - accuracy: 0.2812 - val_loss: 2.8077 - val_accuracy: 0.0938\n",
"Epoch 2694/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.3943 - accuracy: 0.3125 - val_loss: 2.8982 - val_accuracy: 0.0938\n",
"Epoch 2695/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.7417 - accuracy: 0.1875 - val_loss: 2.8933 - val_accuracy: 0.1250\n",
"Epoch 2696/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.5352 - accuracy: 0.2812 - val_loss: 3.0368 - val_accuracy: 0.1250\n",
"Epoch 2697/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.6925 - accuracy: 0.1562 - val_loss: 2.8057 - val_accuracy: 0.0938\n",
"Epoch 2698/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.3431 - accuracy: 0.2188 - val_loss: 2.8414 - val_accuracy: 0.1250\n",
"Epoch 2699/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.3127 - accuracy: 0.3125 - val_loss: 3.0410 - val_accuracy: 0.1250\n",
"Epoch 2700/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.9510 - accuracy: 0.2188 - val_loss: 3.1350 - val_accuracy: 0.0938\n",
"Epoch 2701/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.3099 - accuracy: 0.2188 - val_loss: 2.8838 - val_accuracy: 0.1250\n",
"Epoch 2702/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.3508 - accuracy: 0.3125 - val_loss: 2.9271 - val_accuracy: 0.0938\n",
"Epoch 2703/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.4607 - accuracy: 0.4062 - val_loss: 2.8219 - val_accuracy: 0.1250\n",
"Epoch 2704/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.4695 - accuracy: 0.3750 - val_loss: 2.9196 - val_accuracy: 0.0625\n",
"Epoch 2705/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 1.6039 - accuracy: 0.2812 - val_loss: 3.0328 - val_accuracy: 0.0625\n",
"Epoch 2706/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 1.1620 - accuracy: 0.3125 - val_loss: 2.9283 - val_accuracy: 0.0625\n",
"Epoch 2707/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.2287 - accuracy: 0.3438 - val_loss: 3.1217 - val_accuracy: 0.0625\n",
"Epoch 2708/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.4323 - accuracy: 0.3750 - val_loss: 3.1088 - val_accuracy: 0.0625\n",
"Epoch 2709/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.7915 - accuracy: 0.1875 - val_loss: 3.7373 - val_accuracy: 0.1250\n",
"Epoch 2710/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.4904 - accuracy: 0.2500 - val_loss: 3.1736 - val_accuracy: 0.1250\n",
"Epoch 2711/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 1.8821 - accuracy: 0.3125 - val_loss: 3.1763 - val_accuracy: 0.1562\n",
"Epoch 2712/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.2581 - accuracy: 0.2812 - val_loss: 2.9352 - val_accuracy: 0.1562\n",
"Epoch 2713/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.2031 - accuracy: 0.3438 - val_loss: 2.9998 - val_accuracy: 0.1250\n",
"Epoch 2714/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.1021 - accuracy: 0.3438 - val_loss: 3.2295 - val_accuracy: 0.1562\n",
"Epoch 2715/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.2480 - accuracy: 0.3438 - val_loss: 3.0243 - val_accuracy: 0.1250\n",
"Epoch 2716/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.1579 - accuracy: 0.3438 - val_loss: 2.9711 - val_accuracy: 0.1250\n",
"Epoch 2717/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.1031 - accuracy: 0.4688 - val_loss: 2.9852 - val_accuracy: 0.1250\n",
"Epoch 2718/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.8182 - accuracy: 0.5000 - val_loss: 4.2602 - val_accuracy: 0.0625\n",
"Epoch 2719/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.7490 - accuracy: 0.2188 - val_loss: 3.3294 - val_accuracy: 0.0938\n",
"Epoch 2720/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.1309 - accuracy: 0.4375 - val_loss: 3.1468 - val_accuracy: 0.0625\n",
"Epoch 2721/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0676 - accuracy: 0.2812 - val_loss: 3.0130 - val_accuracy: 0.0938\n",
"Epoch 2722/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.0576 - accuracy: 0.4688 - val_loss: 2.9286 - val_accuracy: 0.0938\n",
"Epoch 2723/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.9009 - accuracy: 0.5312 - val_loss: 2.9585 - val_accuracy: 0.0938\n",
"Epoch 2724/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.9830 - accuracy: 0.4688 - val_loss: 2.9662 - val_accuracy: 0.1250\n",
"Epoch 2725/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.8904 - accuracy: 0.6562 - val_loss: 2.8550 - val_accuracy: 0.1562\n",
"Epoch 2726/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9710 - accuracy: 0.3750 - val_loss: 2.9791 - val_accuracy: 0.1562\n",
"Epoch 2727/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.9791 - accuracy: 0.4375 - val_loss: 2.9263 - val_accuracy: 0.1875\n",
"Epoch 2728/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.9024 - accuracy: 0.2500 - val_loss: 3.0595 - val_accuracy: 0.0938\n",
"Epoch 2729/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8300 - accuracy: 0.5625 - val_loss: 2.9572 - val_accuracy: 0.2188\n",
"Epoch 2730/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8227 - accuracy: 0.5625 - val_loss: 2.9281 - val_accuracy: 0.2188\n",
"Epoch 2731/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9282 - accuracy: 0.4375 - val_loss: 3.1901 - val_accuracy: 0.1875\n",
"Epoch 2732/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.8161 - accuracy: 0.4375 - val_loss: 3.0829 - val_accuracy: 0.2188\n",
"Epoch 2733/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.7975 - accuracy: 0.6250 - val_loss: 2.9878 - val_accuracy: 0.2188\n",
"Epoch 2734/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7504 - accuracy: 0.5000 - val_loss: 2.9643 - val_accuracy: 0.2188\n",
"Epoch 2735/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8884 - accuracy: 0.5000 - val_loss: 3.0819 - val_accuracy: 0.1875\n",
"Epoch 2736/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7504 - accuracy: 0.4688 - val_loss: 3.0220 - val_accuracy: 0.1875\n",
"Epoch 2737/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.8794 - accuracy: 0.4688 - val_loss: 3.0041 - val_accuracy: 0.2188\n",
"Epoch 2738/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.7207 - accuracy: 0.6562 - val_loss: 3.0198 - val_accuracy: 0.2188\n",
"Epoch 2739/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7945 - accuracy: 0.5938 - val_loss: 3.0141 - val_accuracy: 0.2188\n",
"Epoch 2740/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7612 - accuracy: 0.5625 - val_loss: 3.0414 - val_accuracy: 0.1875\n",
"Epoch 2741/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7764 - accuracy: 0.5938 - val_loss: 2.9895 - val_accuracy: 0.1875\n",
"Epoch 2742/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7509 - accuracy: 0.5000 - val_loss: 3.0008 - val_accuracy: 0.1875\n",
"Epoch 2743/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8321 - accuracy: 0.5625 - val_loss: 3.0039 - val_accuracy: 0.1875\n",
"Epoch 2744/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.7206 - accuracy: 0.6250 - val_loss: 3.0487 - val_accuracy: 0.1875\n",
"Epoch 2745/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.8756 - accuracy: 0.5000 - val_loss: 3.1060 - val_accuracy: 0.1875\n",
"Epoch 2746/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6449 - accuracy: 0.6250 - val_loss: 3.0226 - val_accuracy: 0.1875\n",
"Epoch 2747/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7253 - accuracy: 0.6875 - val_loss: 3.0069 - val_accuracy: 0.1875\n",
"Epoch 2748/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7596 - accuracy: 0.5000 - val_loss: 3.0248 - val_accuracy: 0.1875\n",
"Epoch 2749/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8601 - accuracy: 0.5000 - val_loss: 3.0824 - val_accuracy: 0.1875\n",
"Epoch 2750/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6835 - accuracy: 0.6875 - val_loss: 3.0945 - val_accuracy: 0.1875\n",
"Epoch 2751/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7949 - accuracy: 0.5000 - val_loss: 3.1374 - val_accuracy: 0.1875\n",
"Epoch 2752/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6986 - accuracy: 0.5938 - val_loss: 3.1517 - val_accuracy: 0.1875\n",
"Epoch 2753/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8093 - accuracy: 0.5938 - val_loss: 3.0014 - val_accuracy: 0.1875\n",
"Epoch 2754/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7282 - accuracy: 0.5000 - val_loss: 3.0994 - val_accuracy: 0.1875\n",
"Epoch 2755/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6802 - accuracy: 0.6250 - val_loss: 3.1503 - val_accuracy: 0.1875\n",
"Epoch 2756/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5800 - accuracy: 0.6875 - val_loss: 3.1465 - val_accuracy: 0.1875\n",
"Epoch 2757/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6481 - accuracy: 0.7188 - val_loss: 3.1398 - val_accuracy: 0.1875\n",
"Epoch 2758/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7292 - accuracy: 0.5625 - val_loss: 3.2193 - val_accuracy: 0.1875\n",
"Epoch 2759/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.1623 - accuracy: 0.6562 - val_loss: 4.2511 - val_accuracy: 0.1562\n",
"Epoch 2760/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.1926 - accuracy: 0.3750 - val_loss: 2.7235 - val_accuracy: 0.1562\n",
"Epoch 2761/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 1.2570 - accuracy: 0.4062 - val_loss: 4.1107 - val_accuracy: 0.1562\n",
"Epoch 2762/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 1.0382 - accuracy: 0.3438 - val_loss: 3.0878 - val_accuracy: 0.1875\n",
"Epoch 2763/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7414 - accuracy: 0.5938 - val_loss: 3.1708 - val_accuracy: 0.1875\n",
"Epoch 2764/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6970 - accuracy: 0.6250 - val_loss: 3.2459 - val_accuracy: 0.1875\n",
"Epoch 2765/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6789 - accuracy: 0.7188 - val_loss: 3.2585 - val_accuracy: 0.1875\n",
"Epoch 2766/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6529 - accuracy: 0.5625 - val_loss: 3.2630 - val_accuracy: 0.1875\n",
"Epoch 2767/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7755 - accuracy: 0.5938 - val_loss: 3.3116 - val_accuracy: 0.1875\n",
"Epoch 2768/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7130 - accuracy: 0.5938 - val_loss: 3.2586 - val_accuracy: 0.1875\n",
"Epoch 2769/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6578 - accuracy: 0.5000 - val_loss: 3.2769 - val_accuracy: 0.1875\n",
"Epoch 2770/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6860 - accuracy: 0.6250 - val_loss: 3.2627 - val_accuracy: 0.1875\n",
"Epoch 2771/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6963 - accuracy: 0.5312 - val_loss: 3.4441 - val_accuracy: 0.1875\n",
"Epoch 2772/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6856 - accuracy: 0.5312 - val_loss: 3.3154 - val_accuracy: 0.1875\n",
"Epoch 2773/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7189 - accuracy: 0.5938 - val_loss: 3.3050 - val_accuracy: 0.2188\n",
"Epoch 2774/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7273 - accuracy: 0.5000 - val_loss: 3.2621 - val_accuracy: 0.1875\n",
"Epoch 2775/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7258 - accuracy: 0.5312 - val_loss: 3.4675 - val_accuracy: 0.1875\n",
"Epoch 2776/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6234 - accuracy: 0.6875 - val_loss: 3.2790 - val_accuracy: 0.2188\n",
"Epoch 2777/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6676 - accuracy: 0.6875 - val_loss: 3.2724 - val_accuracy: 0.2188\n",
"Epoch 2778/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5313 - accuracy: 0.7812 - val_loss: 3.3387 - val_accuracy: 0.1875\n",
"Epoch 2779/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6991 - accuracy: 0.5312 - val_loss: 3.3064 - val_accuracy: 0.1875\n",
"Epoch 2780/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7908 - accuracy: 0.4688 - val_loss: 3.4007 - val_accuracy: 0.1875\n",
"Epoch 2781/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6946 - accuracy: 0.6562 - val_loss: 3.2462 - val_accuracy: 0.2188\n",
"Epoch 2782/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6563 - accuracy: 0.5938 - val_loss: 3.3379 - val_accuracy: 0.1875\n",
"Epoch 2783/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6616 - accuracy: 0.4688 - val_loss: 3.2527 - val_accuracy: 0.1875\n",
"Epoch 2784/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6564 - accuracy: 0.7188 - val_loss: 3.3060 - val_accuracy: 0.1875\n",
"Epoch 2785/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5857 - accuracy: 0.5625 - val_loss: 3.2467 - val_accuracy: 0.1875\n",
"Epoch 2786/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6084 - accuracy: 0.6250 - val_loss: 3.2877 - val_accuracy: 0.1875\n",
"Epoch 2787/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6834 - accuracy: 0.6562 - val_loss: 3.3182 - val_accuracy: 0.1875\n",
"Epoch 2788/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6832 - accuracy: 0.5625 - val_loss: 3.2867 - val_accuracy: 0.1875\n",
"Epoch 2789/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6049 - accuracy: 0.6250 - val_loss: 3.3463 - val_accuracy: 0.1875\n",
"Epoch 2790/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.5277 - accuracy: 0.6562 - val_loss: 3.2365 - val_accuracy: 0.1875\n",
"Epoch 2791/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6305 - accuracy: 0.5625 - val_loss: 3.3304 - val_accuracy: 0.1875\n",
"Epoch 2792/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6837 - accuracy: 0.6250 - val_loss: 3.3994 - val_accuracy: 0.1875\n",
"Epoch 2793/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7266 - accuracy: 0.5625 - val_loss: 3.3681 - val_accuracy: 0.1875\n",
"Epoch 2794/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6010 - accuracy: 0.5938 - val_loss: 3.3431 - val_accuracy: 0.1875\n",
"Epoch 2795/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.6370 - accuracy: 0.5625 - val_loss: 3.3280 - val_accuracy: 0.1875\n",
"Epoch 2796/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6082 - accuracy: 0.5312 - val_loss: 3.3212 - val_accuracy: 0.1875\n",
"Epoch 2797/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5436 - accuracy: 0.7188 - val_loss: 3.3496 - val_accuracy: 0.1875\n",
"Epoch 2798/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7235 - accuracy: 0.5625 - val_loss: 3.4524 - val_accuracy: 0.1875\n",
"Epoch 2799/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6593 - accuracy: 0.5938 - val_loss: 3.3066 - val_accuracy: 0.1875\n",
"Epoch 2800/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6396 - accuracy: 0.6562 - val_loss: 3.5306 - val_accuracy: 0.1875\n",
"Epoch 2801/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6273 - accuracy: 0.5938 - val_loss: 3.2967 - val_accuracy: 0.1875\n",
"Epoch 2802/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5622 - accuracy: 0.7188 - val_loss: 3.3604 - val_accuracy: 0.1875\n",
"Epoch 2803/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6279 - accuracy: 0.6562 - val_loss: 3.3316 - val_accuracy: 0.1875\n",
"Epoch 2804/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5941 - accuracy: 0.6250 - val_loss: 3.4066 - val_accuracy: 0.1875\n",
"Epoch 2805/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6632 - accuracy: 0.5625 - val_loss: 3.4334 - val_accuracy: 0.1875\n",
"Epoch 2806/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.6000 - accuracy: 0.5625 - val_loss: 3.3313 - val_accuracy: 0.1875\n",
"Epoch 2807/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6179 - accuracy: 0.5938 - val_loss: 3.5046 - val_accuracy: 0.1875\n",
"Epoch 2808/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7089 - accuracy: 0.5938 - val_loss: 3.3650 - val_accuracy: 0.1875\n",
"Epoch 2809/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6500 - accuracy: 0.6562 - val_loss: 3.3322 - val_accuracy: 0.1562\n",
"Epoch 2810/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5807 - accuracy: 0.6250 - val_loss: 3.3589 - val_accuracy: 0.1562\n",
"Epoch 2811/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6901 - accuracy: 0.7188 - val_loss: 3.3959 - val_accuracy: 0.1875\n",
"Epoch 2812/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7133 - accuracy: 0.5312 - val_loss: 3.3518 - val_accuracy: 0.1562\n",
"Epoch 2813/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5369 - accuracy: 0.7812 - val_loss: 3.3499 - val_accuracy: 0.1562\n",
"Epoch 2814/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7282 - accuracy: 0.6250 - val_loss: 3.6518 - val_accuracy: 0.1875\n",
"Epoch 2815/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8316 - accuracy: 0.4375 - val_loss: 3.6577 - val_accuracy: 0.1875\n",
"Epoch 2816/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5684 - accuracy: 0.7500 - val_loss: 3.5256 - val_accuracy: 0.2188\n",
"Epoch 2817/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5939 - accuracy: 0.5312 - val_loss: 3.5006 - val_accuracy: 0.1875\n",
"Epoch 2818/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7526 - accuracy: 0.5625 - val_loss: 3.7623 - val_accuracy: 0.1875\n",
"Epoch 2819/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6169 - accuracy: 0.7188 - val_loss: 3.4714 - val_accuracy: 0.1875\n",
"Epoch 2820/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6815 - accuracy: 0.5000 - val_loss: 3.5518 - val_accuracy: 0.1875\n",
"Epoch 2821/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6916 - accuracy: 0.5000 - val_loss: 3.5447 - val_accuracy: 0.1875\n",
"Epoch 2822/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7068 - accuracy: 0.5938 - val_loss: 3.5370 - val_accuracy: 0.1875\n",
"Epoch 2823/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6280 - accuracy: 0.6562 - val_loss: 3.4996 - val_accuracy: 0.1875\n",
"Epoch 2824/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6449 - accuracy: 0.6562 - val_loss: 3.5626 - val_accuracy: 0.1875\n",
"Epoch 2825/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7184 - accuracy: 0.5625 - val_loss: 3.6159 - val_accuracy: 0.1875\n",
"Epoch 2826/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7092 - accuracy: 0.5938 - val_loss: 3.5225 - val_accuracy: 0.1875\n",
"Epoch 2827/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6064 - accuracy: 0.6562 - val_loss: 3.4563 - val_accuracy: 0.1875\n",
"Epoch 2828/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.6287 - accuracy: 0.5938 - val_loss: 3.4690 - val_accuracy: 0.1875\n",
"Epoch 2829/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6901 - accuracy: 0.5938 - val_loss: 3.6433 - val_accuracy: 0.1875\n",
"Epoch 2830/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6619 - accuracy: 0.7188 - val_loss: 3.6042 - val_accuracy: 0.1875\n",
"Epoch 2831/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6042 - accuracy: 0.5938 - val_loss: 3.4659 - val_accuracy: 0.1875\n",
"Epoch 2832/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6671 - accuracy: 0.5625 - val_loss: 3.4357 - val_accuracy: 0.1875\n",
"Epoch 2833/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5173 - accuracy: 0.6875 - val_loss: 3.4904 - val_accuracy: 0.1875\n",
"Epoch 2834/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6116 - accuracy: 0.6250 - val_loss: 3.6129 - val_accuracy: 0.1875\n",
"Epoch 2835/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5888 - accuracy: 0.6875 - val_loss: 3.4517 - val_accuracy: 0.1875\n",
"Epoch 2836/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5869 - accuracy: 0.5625 - val_loss: 3.5530 - val_accuracy: 0.1875\n",
"Epoch 2837/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6279 - accuracy: 0.6250 - val_loss: 3.5210 - val_accuracy: 0.1875\n",
"Epoch 2838/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6048 - accuracy: 0.5312 - val_loss: 3.4510 - val_accuracy: 0.1875\n",
"Epoch 2839/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.6004 - accuracy: 0.5938 - val_loss: 3.6527 - val_accuracy: 0.1875\n",
"Epoch 2840/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6750 - accuracy: 0.5312 - val_loss: 3.4440 - val_accuracy: 0.1875\n",
"Epoch 2841/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6324 - accuracy: 0.6875 - val_loss: 3.4451 - val_accuracy: 0.1875\n",
"Epoch 2842/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7090 - accuracy: 0.5625 - val_loss: 3.4708 - val_accuracy: 0.1875\n",
"Epoch 2843/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5543 - accuracy: 0.5312 - val_loss: 3.4744 - val_accuracy: 0.1875\n",
"Epoch 2844/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5657 - accuracy: 0.6250 - val_loss: 3.4367 - val_accuracy: 0.1875\n",
"Epoch 2845/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6077 - accuracy: 0.6875 - val_loss: 3.5064 - val_accuracy: 0.1875\n",
"Epoch 2846/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5354 - accuracy: 0.6562 - val_loss: 3.6087 - val_accuracy: 0.1875\n",
"Epoch 2847/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7369 - accuracy: 0.5000 - val_loss: 3.5707 - val_accuracy: 0.1875\n",
"Epoch 2848/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6053 - accuracy: 0.6562 - val_loss: 3.4825 - val_accuracy: 0.1875\n",
"Epoch 2849/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7190 - accuracy: 0.5625 - val_loss: 3.6047 - val_accuracy: 0.1875\n",
"Epoch 2850/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6381 - accuracy: 0.5938 - val_loss: 3.3021 - val_accuracy: 0.1562\n",
"Epoch 2851/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5597 - accuracy: 0.6562 - val_loss: 3.4202 - val_accuracy: 0.1875\n",
"Epoch 2852/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6087 - accuracy: 0.5625 - val_loss: 3.6816 - val_accuracy: 0.1875\n",
"Epoch 2853/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5656 - accuracy: 0.6875 - val_loss: 3.3748 - val_accuracy: 0.1875\n",
"Epoch 2854/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5755 - accuracy: 0.6250 - val_loss: 3.3792 - val_accuracy: 0.1875\n",
"Epoch 2855/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6100 - accuracy: 0.6562 - val_loss: 3.4370 - val_accuracy: 0.1875\n",
"Epoch 2856/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6812 - accuracy: 0.5938 - val_loss: 3.5216 - val_accuracy: 0.1875\n",
"Epoch 2857/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6372 - accuracy: 0.6250 - val_loss: 3.5599 - val_accuracy: 0.1875\n",
"Epoch 2858/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6597 - accuracy: 0.6562 - val_loss: 3.5798 - val_accuracy: 0.1875\n",
"Epoch 2859/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6018 - accuracy: 0.7188 - val_loss: 3.3960 - val_accuracy: 0.1875\n",
"Epoch 2860/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6676 - accuracy: 0.6875 - val_loss: 3.5635 - val_accuracy: 0.1875\n",
"Epoch 2861/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6345 - accuracy: 0.6562 - val_loss: 3.4801 - val_accuracy: 0.1875\n",
"Epoch 2862/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.4904 - accuracy: 0.6562 - val_loss: 3.4594 - val_accuracy: 0.1875\n",
"Epoch 2863/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6330 - accuracy: 0.5312 - val_loss: 3.6318 - val_accuracy: 0.1875\n",
"Epoch 2864/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5144 - accuracy: 0.7188 - val_loss: 3.5241 - val_accuracy: 0.1875\n",
"Epoch 2865/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5969 - accuracy: 0.5000 - val_loss: 3.4445 - val_accuracy: 0.1875\n",
"Epoch 2866/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5906 - accuracy: 0.6875 - val_loss: 3.4358 - val_accuracy: 0.1875\n",
"Epoch 2867/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6989 - accuracy: 0.5625 - val_loss: 3.4648 - val_accuracy: 0.1875\n",
"Epoch 2868/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5337 - accuracy: 0.6562 - val_loss: 3.6743 - val_accuracy: 0.2188\n",
"Epoch 2869/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6080 - accuracy: 0.5938 - val_loss: 3.4722 - val_accuracy: 0.1875\n",
"Epoch 2870/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5650 - accuracy: 0.6562 - val_loss: 3.5324 - val_accuracy: 0.1875\n",
"Epoch 2871/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6196 - accuracy: 0.6250 - val_loss: 3.4551 - val_accuracy: 0.1875\n",
"Epoch 2872/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6781 - accuracy: 0.5000 - val_loss: 3.6870 - val_accuracy: 0.1875\n",
"Epoch 2873/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6596 - accuracy: 0.6250 - val_loss: 3.4652 - val_accuracy: 0.1875\n",
"Epoch 2874/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6284 - accuracy: 0.6562 - val_loss: 3.7164 - val_accuracy: 0.2188\n",
"Epoch 2875/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5797 - accuracy: 0.5625 - val_loss: 3.5570 - val_accuracy: 0.1875\n",
"Epoch 2876/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5562 - accuracy: 0.6250 - val_loss: 3.4598 - val_accuracy: 0.1875\n",
"Epoch 2877/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6613 - accuracy: 0.6875 - val_loss: 3.7804 - val_accuracy: 0.2188\n",
"Epoch 2878/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6366 - accuracy: 0.6250 - val_loss: 3.4116 - val_accuracy: 0.1875\n",
"Epoch 2879/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7288 - accuracy: 0.5938 - val_loss: 3.7269 - val_accuracy: 0.2188\n",
"Epoch 2880/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5176 - accuracy: 0.5938 - val_loss: 3.5926 - val_accuracy: 0.1875\n",
"Epoch 2881/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5738 - accuracy: 0.5625 - val_loss: 3.5719 - val_accuracy: 0.1875\n",
"Epoch 2882/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5640 - accuracy: 0.6875 - val_loss: 3.4857 - val_accuracy: 0.1875\n",
"Epoch 2883/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6073 - accuracy: 0.6875 - val_loss: 3.4768 - val_accuracy: 0.1875\n",
"Epoch 2884/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5907 - accuracy: 0.6875 - val_loss: 3.5947 - val_accuracy: 0.1875\n",
"Epoch 2885/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5772 - accuracy: 0.6250 - val_loss: 3.4747 - val_accuracy: 0.1875\n",
"Epoch 2886/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6042 - accuracy: 0.6875 - val_loss: 3.5502 - val_accuracy: 0.1875\n",
"Epoch 2887/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5438 - accuracy: 0.6562 - val_loss: 3.6246 - val_accuracy: 0.1875\n",
"Epoch 2888/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5840 - accuracy: 0.6250 - val_loss: 3.5341 - val_accuracy: 0.1875\n",
"Epoch 2889/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5979 - accuracy: 0.5625 - val_loss: 3.7307 - val_accuracy: 0.1875\n",
"Epoch 2890/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5208 - accuracy: 0.8125 - val_loss: 3.5742 - val_accuracy: 0.1875\n",
"Epoch 2891/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6194 - accuracy: 0.6875 - val_loss: 3.6493 - val_accuracy: 0.1875\n",
"Epoch 2892/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6291 - accuracy: 0.5938 - val_loss: 3.5492 - val_accuracy: 0.1875\n",
"Epoch 2893/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6562 - accuracy: 0.5312 - val_loss: 3.7190 - val_accuracy: 0.1875\n",
"Epoch 2894/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6235 - accuracy: 0.5938 - val_loss: 3.5037 - val_accuracy: 0.1875\n",
"Epoch 2895/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5238 - accuracy: 0.6875 - val_loss: 3.6384 - val_accuracy: 0.1875\n",
"Epoch 2896/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5658 - accuracy: 0.6875 - val_loss: 3.6745 - val_accuracy: 0.1875\n",
"Epoch 2897/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5323 - accuracy: 0.7500 - val_loss: 3.5599 - val_accuracy: 0.1875\n",
"Epoch 2898/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5944 - accuracy: 0.5625 - val_loss: 3.6241 - val_accuracy: 0.1875\n",
"Epoch 2899/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5665 - accuracy: 0.6250 - val_loss: 3.4897 - val_accuracy: 0.1875\n",
"Epoch 2900/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6302 - accuracy: 0.5625 - val_loss: 3.5804 - val_accuracy: 0.1875\n",
"Epoch 2901/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6558 - accuracy: 0.6875 - val_loss: 3.7625 - val_accuracy: 0.2188\n",
"Epoch 2902/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.5738 - accuracy: 0.6875 - val_loss: 3.5079 - val_accuracy: 0.1875\n",
"Epoch 2903/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6200 - accuracy: 0.5625 - val_loss: 3.6192 - val_accuracy: 0.1875\n",
"Epoch 2904/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5177 - accuracy: 0.6562 - val_loss: 3.6072 - val_accuracy: 0.1875\n",
"Epoch 2905/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6261 - accuracy: 0.5938 - val_loss: 3.7801 - val_accuracy: 0.1875\n",
"Epoch 2906/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6608 - accuracy: 0.5312 - val_loss: 3.5041 - val_accuracy: 0.1875\n",
"Epoch 2907/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.5808 - accuracy: 0.6875 - val_loss: 3.8050 - val_accuracy: 0.1875\n",
"Epoch 2908/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5116 - accuracy: 0.7500 - val_loss: 3.6776 - val_accuracy: 0.1875\n",
"Epoch 2909/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5914 - accuracy: 0.7188 - val_loss: 3.5549 - val_accuracy: 0.1875\n",
"Epoch 2910/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6895 - accuracy: 0.5312 - val_loss: 3.8553 - val_accuracy: 0.2188\n",
"Epoch 2911/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6354 - accuracy: 0.5938 - val_loss: 3.5462 - val_accuracy: 0.1875\n",
"Epoch 2912/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5573 - accuracy: 0.6875 - val_loss: 3.6246 - val_accuracy: 0.1875\n",
"Epoch 2913/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7273 - accuracy: 0.5000 - val_loss: 3.5990 - val_accuracy: 0.1875\n",
"Epoch 2914/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6069 - accuracy: 0.6250 - val_loss: 3.5564 - val_accuracy: 0.1875\n",
"Epoch 2915/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4855 - accuracy: 0.6562 - val_loss: 3.7504 - val_accuracy: 0.1875\n",
"Epoch 2916/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6167 - accuracy: 0.5312 - val_loss: 3.5480 - val_accuracy: 0.1875\n",
"Epoch 2917/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7417 - accuracy: 0.4688 - val_loss: 3.9145 - val_accuracy: 0.2188\n",
"Epoch 2918/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6267 - accuracy: 0.5312 - val_loss: 3.4567 - val_accuracy: 0.1875\n",
"Epoch 2919/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7212 - accuracy: 0.6875 - val_loss: 3.7222 - val_accuracy: 0.1875\n",
"Epoch 2920/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5753 - accuracy: 0.6875 - val_loss: 3.7453 - val_accuracy: 0.1875\n",
"Epoch 2921/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5989 - accuracy: 0.6562 - val_loss: 3.6355 - val_accuracy: 0.1875\n",
"Epoch 2922/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.6196 - accuracy: 0.5625 - val_loss: 3.6459 - val_accuracy: 0.1875\n",
"Epoch 2923/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5712 - accuracy: 0.6250 - val_loss: 3.6133 - val_accuracy: 0.1875\n",
"Epoch 2924/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5668 - accuracy: 0.5625 - val_loss: 3.8943 - val_accuracy: 0.1875\n",
"Epoch 2925/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7037 - accuracy: 0.5312 - val_loss: 3.5710 - val_accuracy: 0.1875\n",
"Epoch 2926/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6249 - accuracy: 0.6250 - val_loss: 3.8287 - val_accuracy: 0.2188\n",
"Epoch 2927/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5641 - accuracy: 0.6562 - val_loss: 3.6830 - val_accuracy: 0.1875\n",
"Epoch 2928/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6253 - accuracy: 0.6562 - val_loss: 3.6967 - val_accuracy: 0.1875\n",
"Epoch 2929/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6032 - accuracy: 0.6250 - val_loss: 3.7789 - val_accuracy: 0.2188\n",
"Epoch 2930/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5607 - accuracy: 0.6875 - val_loss: 3.6691 - val_accuracy: 0.1875\n",
"Epoch 2931/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.4841 - accuracy: 0.6875 - val_loss: 3.6510 - val_accuracy: 0.1875\n",
"Epoch 2932/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5506 - accuracy: 0.6562 - val_loss: 3.7787 - val_accuracy: 0.1875\n",
"Epoch 2933/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6928 - accuracy: 0.5000 - val_loss: 3.7537 - val_accuracy: 0.1875\n",
"Epoch 2934/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6820 - accuracy: 0.5625 - val_loss: 3.6560 - val_accuracy: 0.1875\n",
"Epoch 2935/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5791 - accuracy: 0.6562 - val_loss: 3.7712 - val_accuracy: 0.1875\n",
"Epoch 2936/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5624 - accuracy: 0.5938 - val_loss: 3.5685 - val_accuracy: 0.1875\n",
"Epoch 2937/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.5844 - accuracy: 0.5938 - val_loss: 3.8096 - val_accuracy: 0.1875\n",
"Epoch 2938/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5878 - accuracy: 0.6250 - val_loss: 3.4612 - val_accuracy: 0.1562\n",
"Epoch 2939/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5679 - accuracy: 0.6875 - val_loss: 3.8226 - val_accuracy: 0.1875\n",
"Epoch 2940/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6480 - accuracy: 0.6250 - val_loss: 3.5430 - val_accuracy: 0.1875\n",
"Epoch 2941/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5242 - accuracy: 0.7188 - val_loss: 3.5543 - val_accuracy: 0.1875\n",
"Epoch 2942/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5713 - accuracy: 0.6562 - val_loss: 3.6029 - val_accuracy: 0.1875\n",
"Epoch 2943/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6284 - accuracy: 0.5938 - val_loss: 3.8707 - val_accuracy: 0.1875\n",
"Epoch 2944/5000\n",
"1/1 [==============================] - 0s 218ms/step - loss: 0.7172 - accuracy: 0.5312 - val_loss: 3.4645 - val_accuracy: 0.1875\n",
"Epoch 2945/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5984 - accuracy: 0.5625 - val_loss: 3.7986 - val_accuracy: 0.1875\n",
"Epoch 2946/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7156 - accuracy: 0.5625 - val_loss: 3.6423 - val_accuracy: 0.1875\n",
"Epoch 2947/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5298 - accuracy: 0.6875 - val_loss: 3.7072 - val_accuracy: 0.1875\n",
"Epoch 2948/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6827 - accuracy: 0.5000 - val_loss: 3.6619 - val_accuracy: 0.1875\n",
"Epoch 2949/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5412 - accuracy: 0.6562 - val_loss: 3.5059 - val_accuracy: 0.1875\n",
"Epoch 2950/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5715 - accuracy: 0.6562 - val_loss: 3.7008 - val_accuracy: 0.1875\n",
"Epoch 2951/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6126 - accuracy: 0.6250 - val_loss: 3.6741 - val_accuracy: 0.1875\n",
"Epoch 2952/5000\n",
"1/1 [==============================] - 0s 233ms/step - loss: 0.5376 - accuracy: 0.6562 - val_loss: 3.5535 - val_accuracy: 0.1875\n",
"Epoch 2953/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5885 - accuracy: 0.6250 - val_loss: 3.5391 - val_accuracy: 0.1875\n",
"Epoch 2954/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7732 - accuracy: 0.5938 - val_loss: 3.6813 - val_accuracy: 0.1875\n",
"Epoch 2955/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5120 - accuracy: 0.6250 - val_loss: 3.6304 - val_accuracy: 0.1875\n",
"Epoch 2956/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5447 - accuracy: 0.6250 - val_loss: 3.6857 - val_accuracy: 0.1875\n",
"Epoch 2957/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5314 - accuracy: 0.6562 - val_loss: 3.7657 - val_accuracy: 0.1875\n",
"Epoch 2958/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5491 - accuracy: 0.6562 - val_loss: 3.8051 - val_accuracy: 0.1875\n",
"Epoch 2959/5000\n",
"1/1 [==============================] - 0s 223ms/step - loss: 0.5154 - accuracy: 0.6875 - val_loss: 3.4278 - val_accuracy: 0.1875\n",
"Epoch 2960/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.7768 - accuracy: 0.5000 - val_loss: 4.0186 - val_accuracy: 0.1875\n",
"Epoch 2961/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6414 - accuracy: 0.6562 - val_loss: 3.3566 - val_accuracy: 0.1875\n",
"Epoch 2962/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7807 - accuracy: 0.5938 - val_loss: 4.2738 - val_accuracy: 0.2188\n",
"Epoch 2963/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.9690 - accuracy: 0.4688 - val_loss: 3.2295 - val_accuracy: 0.1250\n",
"Epoch 2964/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9250 - accuracy: 0.5000 - val_loss: 3.9286 - val_accuracy: 0.1875\n",
"Epoch 2965/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7189 - accuracy: 0.5000 - val_loss: 3.4940 - val_accuracy: 0.1875\n",
"Epoch 2966/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6208 - accuracy: 0.5938 - val_loss: 3.8630 - val_accuracy: 0.1875\n",
"Epoch 2967/5000\n",
"1/1 [==============================] - 0s 212ms/step - loss: 0.5886 - accuracy: 0.6562 - val_loss: 3.5421 - val_accuracy: 0.1875\n",
"Epoch 2968/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6965 - accuracy: 0.5938 - val_loss: 3.8252 - val_accuracy: 0.1875\n",
"Epoch 2969/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7280 - accuracy: 0.5312 - val_loss: 3.7554 - val_accuracy: 0.1875\n",
"Epoch 2970/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6031 - accuracy: 0.7188 - val_loss: 3.7137 - val_accuracy: 0.1875\n",
"Epoch 2971/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5166 - accuracy: 0.6875 - val_loss: 3.6786 - val_accuracy: 0.1875\n",
"Epoch 2972/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.6240 - accuracy: 0.6562 - val_loss: 3.9472 - val_accuracy: 0.1875\n",
"Epoch 2973/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5507 - accuracy: 0.6250 - val_loss: 3.6273 - val_accuracy: 0.1875\n",
"Epoch 2974/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6378 - accuracy: 0.5625 - val_loss: 4.0431 - val_accuracy: 0.1562\n",
"Epoch 2975/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6898 - accuracy: 0.6250 - val_loss: 3.7651 - val_accuracy: 0.1875\n",
"Epoch 2976/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5646 - accuracy: 0.5938 - val_loss: 3.8084 - val_accuracy: 0.1875\n",
"Epoch 2977/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6130 - accuracy: 0.6875 - val_loss: 3.6694 - val_accuracy: 0.1875\n",
"Epoch 2978/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6213 - accuracy: 0.6250 - val_loss: 3.8115 - val_accuracy: 0.1875\n",
"Epoch 2979/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5737 - accuracy: 0.6562 - val_loss: 3.7524 - val_accuracy: 0.1875\n",
"Epoch 2980/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5379 - accuracy: 0.7188 - val_loss: 3.7491 - val_accuracy: 0.1875\n",
"Epoch 2981/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5928 - accuracy: 0.5938 - val_loss: 3.7628 - val_accuracy: 0.1875\n",
"Epoch 2982/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6487 - accuracy: 0.6250 - val_loss: 3.7146 - val_accuracy: 0.1875\n",
"Epoch 2983/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5790 - accuracy: 0.5000 - val_loss: 3.8217 - val_accuracy: 0.1875\n",
"Epoch 2984/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6394 - accuracy: 0.6250 - val_loss: 3.6370 - val_accuracy: 0.1875\n",
"Epoch 2985/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6581 - accuracy: 0.5625 - val_loss: 3.6836 - val_accuracy: 0.1875\n",
"Epoch 2986/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6120 - accuracy: 0.4688 - val_loss: 3.6870 - val_accuracy: 0.1875\n",
"Epoch 2987/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4846 - accuracy: 0.7812 - val_loss: 3.8028 - val_accuracy: 0.1875\n",
"Epoch 2988/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6479 - accuracy: 0.6250 - val_loss: 3.6231 - val_accuracy: 0.1875\n",
"Epoch 2989/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6437 - accuracy: 0.6250 - val_loss: 3.7574 - val_accuracy: 0.1875\n",
"Epoch 2990/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5800 - accuracy: 0.7188 - val_loss: 3.6082 - val_accuracy: 0.1875\n",
"Epoch 2991/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4464 - accuracy: 0.7188 - val_loss: 3.5506 - val_accuracy: 0.1562\n",
"Epoch 2992/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6129 - accuracy: 0.6250 - val_loss: 4.0149 - val_accuracy: 0.1562\n",
"Epoch 2993/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5269 - accuracy: 0.6562 - val_loss: 3.6522 - val_accuracy: 0.1875\n",
"Epoch 2994/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6169 - accuracy: 0.5938 - val_loss: 3.8988 - val_accuracy: 0.1875\n",
"Epoch 2995/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5781 - accuracy: 0.5000 - val_loss: 3.5994 - val_accuracy: 0.1875\n",
"Epoch 2996/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5478 - accuracy: 0.6250 - val_loss: 3.8059 - val_accuracy: 0.1875\n",
"Epoch 2997/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6352 - accuracy: 0.6250 - val_loss: 3.5426 - val_accuracy: 0.1562\n",
"Epoch 2998/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5554 - accuracy: 0.5312 - val_loss: 3.6313 - val_accuracy: 0.1875\n",
"Epoch 2999/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5783 - accuracy: 0.5000 - val_loss: 3.6755 - val_accuracy: 0.1875\n",
"Epoch 3000/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5981 - accuracy: 0.6250 - val_loss: 3.7380 - val_accuracy: 0.1875\n",
"Epoch 3001/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6831 - accuracy: 0.5625 - val_loss: 3.8608 - val_accuracy: 0.1875\n",
"Epoch 3002/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5519 - accuracy: 0.6562 - val_loss: 3.5687 - val_accuracy: 0.1875\n",
"Epoch 3003/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5887 - accuracy: 0.6875 - val_loss: 3.9987 - val_accuracy: 0.1875\n",
"Epoch 3004/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6430 - accuracy: 0.7188 - val_loss: 3.6336 - val_accuracy: 0.1875\n",
"Epoch 3005/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5348 - accuracy: 0.6562 - val_loss: 3.7230 - val_accuracy: 0.1875\n",
"Epoch 3006/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5264 - accuracy: 0.6250 - val_loss: 3.6710 - val_accuracy: 0.1875\n",
"Epoch 3007/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5270 - accuracy: 0.5312 - val_loss: 3.8187 - val_accuracy: 0.1875\n",
"Epoch 3008/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5499 - accuracy: 0.6250 - val_loss: 3.6243 - val_accuracy: 0.1875\n",
"Epoch 3009/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6064 - accuracy: 0.6562 - val_loss: 3.7299 - val_accuracy: 0.1875\n",
"Epoch 3010/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5342 - accuracy: 0.5312 - val_loss: 3.7459 - val_accuracy: 0.1875\n",
"Epoch 3011/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5519 - accuracy: 0.6562 - val_loss: 3.8165 - val_accuracy: 0.1875\n",
"Epoch 3012/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5357 - accuracy: 0.6562 - val_loss: 3.7032 - val_accuracy: 0.1875\n",
"Epoch 3013/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5171 - accuracy: 0.8125 - val_loss: 3.6263 - val_accuracy: 0.1875\n",
"Epoch 3014/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5682 - accuracy: 0.6250 - val_loss: 3.8481 - val_accuracy: 0.1875\n",
"Epoch 3015/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6453 - accuracy: 0.5625 - val_loss: 3.5894 - val_accuracy: 0.1875\n",
"Epoch 3016/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6375 - accuracy: 0.4688 - val_loss: 4.0393 - val_accuracy: 0.1875\n",
"Epoch 3017/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6419 - accuracy: 0.5625 - val_loss: 3.5982 - val_accuracy: 0.1875\n",
"Epoch 3018/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6804 - accuracy: 0.5938 - val_loss: 4.0687 - val_accuracy: 0.1875\n",
"Epoch 3019/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5907 - accuracy: 0.6250 - val_loss: 3.5737 - val_accuracy: 0.1875\n",
"Epoch 3020/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4994 - accuracy: 0.6250 - val_loss: 3.8026 - val_accuracy: 0.1875\n",
"Epoch 3021/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6196 - accuracy: 0.6562 - val_loss: 3.6667 - val_accuracy: 0.1875\n",
"Epoch 3022/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5276 - accuracy: 0.6875 - val_loss: 3.6464 - val_accuracy: 0.1875\n",
"Epoch 3023/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5985 - accuracy: 0.5625 - val_loss: 3.6750 - val_accuracy: 0.1875\n",
"Epoch 3024/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5507 - accuracy: 0.7188 - val_loss: 3.7424 - val_accuracy: 0.1875\n",
"Epoch 3025/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5631 - accuracy: 0.6562 - val_loss: 3.7739 - val_accuracy: 0.1875\n",
"Epoch 3026/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5567 - accuracy: 0.6562 - val_loss: 3.7669 - val_accuracy: 0.1875\n",
"Epoch 3027/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5842 - accuracy: 0.6875 - val_loss: 3.3978 - val_accuracy: 0.1875\n",
"Epoch 3028/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.1105 - accuracy: 0.5000 - val_loss: 7.3265 - val_accuracy: 0.0312\n",
"Epoch 3029/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 4.8794 - accuracy: 0.0938 - val_loss: 3.6433 - val_accuracy: 0.2500\n",
"Epoch 3030/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 1.0435 - accuracy: 0.2812 - val_loss: 3.8207 - val_accuracy: 0.1875\n",
"Epoch 3031/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7663 - accuracy: 0.5625 - val_loss: 3.5941 - val_accuracy: 0.2188\n",
"Epoch 3032/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7030 - accuracy: 0.5312 - val_loss: 3.6919 - val_accuracy: 0.2188\n",
"Epoch 3033/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5752 - accuracy: 0.6250 - val_loss: 3.5750 - val_accuracy: 0.1875\n",
"Epoch 3034/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5612 - accuracy: 0.5625 - val_loss: 3.5795 - val_accuracy: 0.1875\n",
"Epoch 3035/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6458 - accuracy: 0.5625 - val_loss: 3.6201 - val_accuracy: 0.1875\n",
"Epoch 3036/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5790 - accuracy: 0.5312 - val_loss: 3.5947 - val_accuracy: 0.1875\n",
"Epoch 3037/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5801 - accuracy: 0.6250 - val_loss: 3.5831 - val_accuracy: 0.1875\n",
"Epoch 3038/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5518 - accuracy: 0.6875 - val_loss: 3.7321 - val_accuracy: 0.1875\n",
"Epoch 3039/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5550 - accuracy: 0.5938 - val_loss: 3.5860 - val_accuracy: 0.1875\n",
"Epoch 3040/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5478 - accuracy: 0.6875 - val_loss: 3.6389 - val_accuracy: 0.1875\n",
"Epoch 3041/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6047 - accuracy: 0.5625 - val_loss: 3.5967 - val_accuracy: 0.1875\n",
"Epoch 3042/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6492 - accuracy: 0.6562 - val_loss: 3.6008 - val_accuracy: 0.1875\n",
"Epoch 3043/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6009 - accuracy: 0.5625 - val_loss: 3.5508 - val_accuracy: 0.1562\n",
"Epoch 3044/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5419 - accuracy: 0.6562 - val_loss: 3.6573 - val_accuracy: 0.1875\n",
"Epoch 3045/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6780 - accuracy: 0.5938 - val_loss: 3.6619 - val_accuracy: 0.1875\n",
"Epoch 3046/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5686 - accuracy: 0.6875 - val_loss: 3.5511 - val_accuracy: 0.1562\n",
"Epoch 3047/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6692 - accuracy: 0.6250 - val_loss: 3.7036 - val_accuracy: 0.1875\n",
"Epoch 3048/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5315 - accuracy: 0.7500 - val_loss: 3.5687 - val_accuracy: 0.1875\n",
"Epoch 3049/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5687 - accuracy: 0.6562 - val_loss: 3.6743 - val_accuracy: 0.1875\n",
"Epoch 3050/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5349 - accuracy: 0.7188 - val_loss: 3.6039 - val_accuracy: 0.1875\n",
"Epoch 3051/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5041 - accuracy: 0.6562 - val_loss: 3.7246 - val_accuracy: 0.1875\n",
"Epoch 3052/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6433 - accuracy: 0.7500 - val_loss: 3.7014 - val_accuracy: 0.1875\n",
"Epoch 3053/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6206 - accuracy: 0.5312 - val_loss: 3.7065 - val_accuracy: 0.1875\n",
"Epoch 3054/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5442 - accuracy: 0.6875 - val_loss: 3.6298 - val_accuracy: 0.1875\n",
"Epoch 3055/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5197 - accuracy: 0.7188 - val_loss: 3.7872 - val_accuracy: 0.1875\n",
"Epoch 3056/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6194 - accuracy: 0.5625 - val_loss: 3.5190 - val_accuracy: 0.1562\n",
"Epoch 3057/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5869 - accuracy: 0.5938 - val_loss: 3.6680 - val_accuracy: 0.1875\n",
"Epoch 3058/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7759 - accuracy: 0.6562 - val_loss: 3.6370 - val_accuracy: 0.2188\n",
"Epoch 3059/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5653 - accuracy: 0.6562 - val_loss: 3.7645 - val_accuracy: 0.1875\n",
"Epoch 3060/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.5794 - accuracy: 0.7500 - val_loss: 3.6157 - val_accuracy: 0.2188\n",
"Epoch 3061/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6498 - accuracy: 0.6250 - val_loss: 3.6353 - val_accuracy: 0.1875\n",
"Epoch 3062/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5520 - accuracy: 0.6250 - val_loss: 3.7739 - val_accuracy: 0.1875\n",
"Epoch 3063/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5317 - accuracy: 0.7188 - val_loss: 3.5535 - val_accuracy: 0.1562\n",
"Epoch 3064/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.5390 - accuracy: 0.6875 - val_loss: 3.7090 - val_accuracy: 0.1875\n",
"Epoch 3065/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.5166 - accuracy: 0.7500 - val_loss: 3.5854 - val_accuracy: 0.1875\n",
"Epoch 3066/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6000 - accuracy: 0.6250 - val_loss: 3.6485 - val_accuracy: 0.1875\n",
"Epoch 3067/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5953 - accuracy: 0.6875 - val_loss: 3.7707 - val_accuracy: 0.1875\n",
"Epoch 3068/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7535 - accuracy: 0.6562 - val_loss: 3.3487 - val_accuracy: 0.1562\n",
"Epoch 3069/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9220 - accuracy: 0.4688 - val_loss: 6.4002 - val_accuracy: 0.1562\n",
"Epoch 3070/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 4.5987 - accuracy: 0.1250 - val_loss: 3.8555 - val_accuracy: 0.2812\n",
"Epoch 3071/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 13.8107 - accuracy: 0.2500 - val_loss: 5.3134 - val_accuracy: 0.0312\n",
"Epoch 3072/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 6.2475 - accuracy: 0.0625 - val_loss: 3.1437 - val_accuracy: 0.1250\n",
"Epoch 3073/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.8176 - accuracy: 0.1562 - val_loss: 2.7828 - val_accuracy: 0.0625\n",
"Epoch 3074/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 3.5620 - accuracy: 0.1875 - val_loss: 3.2814 - val_accuracy: 0.0312\n",
"Epoch 3075/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 2.5421 - accuracy: 0.0625 - val_loss: 3.1358 - val_accuracy: 0.0312\n",
"Epoch 3076/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 2.5260 - accuracy: 0.1250 - val_loss: 2.7796 - val_accuracy: 0.1250\n",
"Epoch 3077/5000\n",
"1/1 [==============================] - 0s 207ms/step - loss: 2.7882 - accuracy: 0.1562 - val_loss: 2.8525 - val_accuracy: 0.0938\n",
"Epoch 3078/5000\n",
"1/1 [==============================] - 0s 244ms/step - loss: 2.0417 - accuracy: 0.1250 - val_loss: 2.9665 - val_accuracy: 0.0625\n",
"Epoch 3079/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 2.1876 - accuracy: 0.0625 - val_loss: 3.0498 - val_accuracy: 0.0312\n",
"Epoch 3080/5000\n",
"1/1 [==============================] - 0s 212ms/step - loss: 2.5467 - accuracy: 0.0938 - val_loss: 2.9174 - val_accuracy: 0.0625\n",
"Epoch 3081/5000\n",
"1/1 [==============================] - 0s 204ms/step - loss: 2.1165 - accuracy: 0.1562 - val_loss: 3.0716 - val_accuracy: 0.0312\n",
"Epoch 3082/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 2.0179 - accuracy: 0.1250 - val_loss: 2.9405 - val_accuracy: 0.0000e+00\n",
"Epoch 3083/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.0828 - accuracy: 0.1562 - val_loss: 3.3164 - val_accuracy: 0.0312\n",
"Epoch 3084/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 2.0376 - accuracy: 0.2188 - val_loss: 3.0128 - val_accuracy: 0.0312\n",
"Epoch 3085/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.7155 - accuracy: 0.1875 - val_loss: 3.0716 - val_accuracy: 0.0000e+00\n",
"Epoch 3086/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 2.3769 - accuracy: 0.1250 - val_loss: 3.4054 - val_accuracy: 0.0000e+00\n",
"Epoch 3087/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.8900 - accuracy: 0.1250 - val_loss: 3.1445 - val_accuracy: 0.0000e+00\n",
"Epoch 3088/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 2.0741 - accuracy: 0.2500 - val_loss: 3.3398 - val_accuracy: 0.0000e+00\n",
"Epoch 3089/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 1.9983 - accuracy: 0.1562 - val_loss: 3.1069 - val_accuracy: 0.0312\n",
"Epoch 3090/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 1.9375 - accuracy: 0.1875 - val_loss: 3.2394 - val_accuracy: 0.0000e+00\n",
"Epoch 3091/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 1.9957 - accuracy: 0.1875 - val_loss: 3.2904 - val_accuracy: 0.0000e+00\n",
"Epoch 3092/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 1.5759 - accuracy: 0.1875 - val_loss: 3.1572 - val_accuracy: 0.0312\n",
"Epoch 3093/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.8272 - accuracy: 0.1250 - val_loss: 3.0465 - val_accuracy: 0.0312\n",
"Epoch 3094/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.5635 - accuracy: 0.1562 - val_loss: 3.1526 - val_accuracy: 0.0312\n",
"Epoch 3095/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.7410 - accuracy: 0.1250 - val_loss: 3.3183 - val_accuracy: 0.0312\n",
"Epoch 3096/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.7815 - accuracy: 0.1562 - val_loss: 3.2627 - val_accuracy: 0.0625\n",
"Epoch 3097/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.6273 - accuracy: 0.2188 - val_loss: 3.3291 - val_accuracy: 0.0312\n",
"Epoch 3098/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.5577 - accuracy: 0.1875 - val_loss: 3.3279 - val_accuracy: 0.0625\n",
"Epoch 3099/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.5263 - accuracy: 0.3125 - val_loss: 3.4255 - val_accuracy: 0.0625\n",
"Epoch 3100/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.9590 - accuracy: 0.1562 - val_loss: 3.2655 - val_accuracy: 0.0625\n",
"Epoch 3101/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.6370 - accuracy: 0.2500 - val_loss: 3.3977 - val_accuracy: 0.0312\n",
"Epoch 3102/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.0354 - accuracy: 0.2500 - val_loss: 3.5458 - val_accuracy: 0.0312\n",
"Epoch 3103/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.4500 - accuracy: 0.2500 - val_loss: 3.2844 - val_accuracy: 0.0625\n",
"Epoch 3104/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 1.8740 - accuracy: 0.2188 - val_loss: 3.2272 - val_accuracy: 0.0625\n",
"Epoch 3105/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.4881 - accuracy: 0.2188 - val_loss: 3.2963 - val_accuracy: 0.0625\n",
"Epoch 3106/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.4832 - accuracy: 0.2188 - val_loss: 3.3618 - val_accuracy: 0.0625\n",
"Epoch 3107/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.5334 - accuracy: 0.4688 - val_loss: 3.3192 - val_accuracy: 0.0625\n",
"Epoch 3108/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 2.1392 - accuracy: 0.2188 - val_loss: 3.6043 - val_accuracy: 0.0625\n",
"Epoch 3109/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.3282 - accuracy: 0.2500 - val_loss: 3.3702 - val_accuracy: 0.0938\n",
"Epoch 3110/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.3649 - accuracy: 0.2500 - val_loss: 3.2418 - val_accuracy: 0.0938\n",
"Epoch 3111/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.7690 - accuracy: 0.2812 - val_loss: 3.4353 - val_accuracy: 0.0625\n",
"Epoch 3112/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.4561 - accuracy: 0.1875 - val_loss: 3.3074 - val_accuracy: 0.0938\n",
"Epoch 3113/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.5716 - accuracy: 0.3750 - val_loss: 3.3647 - val_accuracy: 0.0938\n",
"Epoch 3114/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.7558 - accuracy: 0.3438 - val_loss: 3.4024 - val_accuracy: 0.0625\n",
"Epoch 3115/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.3117 - accuracy: 0.1875 - val_loss: 3.3279 - val_accuracy: 0.0938\n",
"Epoch 3116/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.6987 - accuracy: 0.3438 - val_loss: 3.3590 - val_accuracy: 0.1250\n",
"Epoch 3117/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.7206 - accuracy: 0.3750 - val_loss: 3.3901 - val_accuracy: 0.0938\n",
"Epoch 3118/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.6534 - accuracy: 0.2812 - val_loss: 4.0236 - val_accuracy: 0.0938\n",
"Epoch 3119/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.8178 - accuracy: 0.2188 - val_loss: 2.9727 - val_accuracy: 0.1250\n",
"Epoch 3120/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.6097 - accuracy: 0.3438 - val_loss: 3.1174 - val_accuracy: 0.1562\n",
"Epoch 3121/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.3359 - accuracy: 0.3438 - val_loss: 3.1953 - val_accuracy: 0.1562\n",
"Epoch 3122/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3470 - accuracy: 0.4062 - val_loss: 3.3596 - val_accuracy: 0.1562\n",
"Epoch 3123/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.7235 - accuracy: 0.3750 - val_loss: 3.3380 - val_accuracy: 0.0938\n",
"Epoch 3124/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.3009 - accuracy: 0.3125 - val_loss: 3.4338 - val_accuracy: 0.1562\n",
"Epoch 3125/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.5462 - accuracy: 0.3125 - val_loss: 3.2538 - val_accuracy: 0.1875\n",
"Epoch 3126/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.2166 - accuracy: 0.3438 - val_loss: 3.2817 - val_accuracy: 0.1562\n",
"Epoch 3127/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.6837 - accuracy: 0.3438 - val_loss: 3.6079 - val_accuracy: 0.1875\n",
"Epoch 3128/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.1563 - accuracy: 0.5000 - val_loss: 3.3645 - val_accuracy: 0.1562\n",
"Epoch 3129/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.2065 - accuracy: 0.2188 - val_loss: 3.4022 - val_accuracy: 0.1562\n",
"Epoch 3130/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9975 - accuracy: 0.3750 - val_loss: 3.3096 - val_accuracy: 0.1562\n",
"Epoch 3131/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.2991 - accuracy: 0.4375 - val_loss: 3.2336 - val_accuracy: 0.1875\n",
"Epoch 3132/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.0541 - accuracy: 0.3750 - val_loss: 3.3693 - val_accuracy: 0.2500\n",
"Epoch 3133/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.6350 - accuracy: 0.4062 - val_loss: 3.3966 - val_accuracy: 0.1562\n",
"Epoch 3134/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.0760 - accuracy: 0.5312 - val_loss: 3.3707 - val_accuracy: 0.1875\n",
"Epoch 3135/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.2092 - accuracy: 0.4375 - val_loss: 3.3373 - val_accuracy: 0.1562\n",
"Epoch 3136/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.2459 - accuracy: 0.5312 - val_loss: 3.4845 - val_accuracy: 0.1562\n",
"Epoch 3137/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.0697 - accuracy: 0.5000 - val_loss: 3.2547 - val_accuracy: 0.1250\n",
"Epoch 3138/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.5222 - accuracy: 0.3438 - val_loss: 3.3494 - val_accuracy: 0.0938\n",
"Epoch 3139/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.1412 - accuracy: 0.4062 - val_loss: 3.1555 - val_accuracy: 0.1562\n",
"Epoch 3140/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.1086 - accuracy: 0.4062 - val_loss: 3.1879 - val_accuracy: 0.1562\n",
"Epoch 3141/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.9940 - accuracy: 0.4688 - val_loss: 3.0999 - val_accuracy: 0.1562\n",
"Epoch 3142/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8515 - accuracy: 0.4375 - val_loss: 3.1258 - val_accuracy: 0.1875\n",
"Epoch 3143/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.1177 - accuracy: 0.3750 - val_loss: 3.0823 - val_accuracy: 0.1875\n",
"Epoch 3144/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.9849 - accuracy: 0.2812 - val_loss: 3.0411 - val_accuracy: 0.1875\n",
"Epoch 3145/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.7825 - accuracy: 0.5625 - val_loss: 3.0628 - val_accuracy: 0.1875\n",
"Epoch 3146/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.8330 - accuracy: 0.4688 - val_loss: 2.9501 - val_accuracy: 0.2188\n",
"Epoch 3147/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.9197 - accuracy: 0.4688 - val_loss: 3.0504 - val_accuracy: 0.2188\n",
"Epoch 3148/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7862 - accuracy: 0.6562 - val_loss: 3.1318 - val_accuracy: 0.2188\n",
"Epoch 3149/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.8377 - accuracy: 0.5938 - val_loss: 3.1546 - val_accuracy: 0.2188\n",
"Epoch 3150/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.8148 - accuracy: 0.5938 - val_loss: 3.1320 - val_accuracy: 0.2188\n",
"Epoch 3151/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7434 - accuracy: 0.6250 - val_loss: 3.0323 - val_accuracy: 0.2812\n",
"Epoch 3152/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.1471 - accuracy: 0.5938 - val_loss: 4.4804 - val_accuracy: 0.1875\n",
"Epoch 3153/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.3220 - accuracy: 0.3438 - val_loss: 2.9745 - val_accuracy: 0.2500\n",
"Epoch 3154/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.9952 - accuracy: 0.4688 - val_loss: 3.2942 - val_accuracy: 0.1875\n",
"Epoch 3155/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.8628 - accuracy: 0.5938 - val_loss: 3.2569 - val_accuracy: 0.1875\n",
"Epoch 3156/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9629 - accuracy: 0.6250 - val_loss: 3.1218 - val_accuracy: 0.1875\n",
"Epoch 3157/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9281 - accuracy: 0.4375 - val_loss: 3.2802 - val_accuracy: 0.1875\n",
"Epoch 3158/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7010 - accuracy: 0.6875 - val_loss: 3.2602 - val_accuracy: 0.1875\n",
"Epoch 3159/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.8384 - accuracy: 0.4688 - val_loss: 3.2559 - val_accuracy: 0.1875\n",
"Epoch 3160/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8554 - accuracy: 0.5000 - val_loss: 3.2824 - val_accuracy: 0.1875\n",
"Epoch 3161/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.1449 - accuracy: 0.5312 - val_loss: 3.9495 - val_accuracy: 0.2500\n",
"Epoch 3162/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.9344 - accuracy: 0.5312 - val_loss: 3.2180 - val_accuracy: 0.2500\n",
"Epoch 3163/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.8249 - accuracy: 0.6562 - val_loss: 3.3718 - val_accuracy: 0.1875\n",
"Epoch 3164/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7277 - accuracy: 0.5625 - val_loss: 3.5051 - val_accuracy: 0.1875\n",
"Epoch 3165/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6903 - accuracy: 0.5625 - val_loss: 3.3999 - val_accuracy: 0.1875\n",
"Epoch 3166/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6785 - accuracy: 0.5938 - val_loss: 3.4043 - val_accuracy: 0.1875\n",
"Epoch 3167/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7409 - accuracy: 0.5312 - val_loss: 3.3960 - val_accuracy: 0.1875\n",
"Epoch 3168/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6518 - accuracy: 0.7500 - val_loss: 3.3015 - val_accuracy: 0.1875\n",
"Epoch 3169/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.8008 - accuracy: 0.4375 - val_loss: 3.4365 - val_accuracy: 0.1875\n",
"Epoch 3170/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6487 - accuracy: 0.5000 - val_loss: 3.3664 - val_accuracy: 0.1875\n",
"Epoch 3171/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7035 - accuracy: 0.6875 - val_loss: 3.3500 - val_accuracy: 0.1875\n",
"Epoch 3172/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7135 - accuracy: 0.6562 - val_loss: 3.3701 - val_accuracy: 0.1875\n",
"Epoch 3173/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6265 - accuracy: 0.6562 - val_loss: 3.4492 - val_accuracy: 0.1875\n",
"Epoch 3174/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7963 - accuracy: 0.5938 - val_loss: 3.4252 - val_accuracy: 0.1875\n",
"Epoch 3175/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6851 - accuracy: 0.5938 - val_loss: 3.3925 - val_accuracy: 0.1875\n",
"Epoch 3176/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6537 - accuracy: 0.7188 - val_loss: 3.3825 - val_accuracy: 0.1875\n",
"Epoch 3177/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6690 - accuracy: 0.5938 - val_loss: 3.4007 - val_accuracy: 0.1875\n",
"Epoch 3178/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6588 - accuracy: 0.6562 - val_loss: 3.4082 - val_accuracy: 0.1875\n",
"Epoch 3179/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5237 - accuracy: 0.6875 - val_loss: 3.4228 - val_accuracy: 0.1875\n",
"Epoch 3180/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6858 - accuracy: 0.5938 - val_loss: 3.3628 - val_accuracy: 0.1875\n",
"Epoch 3181/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7245 - accuracy: 0.5312 - val_loss: 3.4173 - val_accuracy: 0.1875\n",
"Epoch 3182/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6971 - accuracy: 0.5625 - val_loss: 3.3800 - val_accuracy: 0.1875\n",
"Epoch 3183/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7064 - accuracy: 0.4688 - val_loss: 3.3687 - val_accuracy: 0.1875\n",
"Epoch 3184/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6327 - accuracy: 0.5625 - val_loss: 3.4065 - val_accuracy: 0.1875\n",
"Epoch 3185/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7369 - accuracy: 0.5312 - val_loss: 3.4550 - val_accuracy: 0.1875\n",
"Epoch 3186/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6089 - accuracy: 0.6562 - val_loss: 3.4903 - val_accuracy: 0.1875\n",
"Epoch 3187/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6800 - accuracy: 0.5625 - val_loss: 3.3538 - val_accuracy: 0.1875\n",
"Epoch 3188/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7016 - accuracy: 0.5312 - val_loss: 3.4107 - val_accuracy: 0.1875\n",
"Epoch 3189/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5225 - accuracy: 0.7500 - val_loss: 3.5265 - val_accuracy: 0.1875\n",
"Epoch 3190/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6758 - accuracy: 0.5312 - val_loss: 3.3774 - val_accuracy: 0.1875\n",
"Epoch 3191/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5875 - accuracy: 0.6562 - val_loss: 3.3778 - val_accuracy: 0.1875\n",
"Epoch 3192/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7143 - accuracy: 0.5312 - val_loss: 3.4240 - val_accuracy: 0.1875\n",
"Epoch 3193/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6550 - accuracy: 0.6562 - val_loss: 3.6261 - val_accuracy: 0.1875\n",
"Epoch 3194/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6460 - accuracy: 0.6250 - val_loss: 3.3532 - val_accuracy: 0.1875\n",
"Epoch 3195/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8774 - accuracy: 0.6875 - val_loss: 4.5872 - val_accuracy: 0.1875\n",
"Epoch 3196/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.1018 - accuracy: 0.3438 - val_loss: 3.0476 - val_accuracy: 0.1875\n",
"Epoch 3197/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8008 - accuracy: 0.4688 - val_loss: 3.4080 - val_accuracy: 0.1875\n",
"Epoch 3198/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6248 - accuracy: 0.5938 - val_loss: 3.4293 - val_accuracy: 0.1875\n",
"Epoch 3199/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6344 - accuracy: 0.6250 - val_loss: 3.5054 - val_accuracy: 0.1875\n",
"Epoch 3200/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7804 - accuracy: 0.5938 - val_loss: 3.3603 - val_accuracy: 0.2500\n",
"Epoch 3201/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6530 - accuracy: 0.6250 - val_loss: 3.4730 - val_accuracy: 0.1875\n",
"Epoch 3202/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5242 - accuracy: 0.6250 - val_loss: 3.4709 - val_accuracy: 0.1875\n",
"Epoch 3203/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5855 - accuracy: 0.6562 - val_loss: 3.4686 - val_accuracy: 0.1875\n",
"Epoch 3204/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6274 - accuracy: 0.6875 - val_loss: 3.5205 - val_accuracy: 0.1562\n",
"Epoch 3205/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4904 - accuracy: 0.6562 - val_loss: 3.3909 - val_accuracy: 0.2500\n",
"Epoch 3206/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7204 - accuracy: 0.5312 - val_loss: 3.5566 - val_accuracy: 0.1875\n",
"Epoch 3207/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6377 - accuracy: 0.6875 - val_loss: 3.3850 - val_accuracy: 0.2500\n",
"Epoch 3208/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5407 - accuracy: 0.6250 - val_loss: 3.5009 - val_accuracy: 0.1875\n",
"Epoch 3209/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7694 - accuracy: 0.5312 - val_loss: 3.4585 - val_accuracy: 0.1562\n",
"Epoch 3210/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5978 - accuracy: 0.7812 - val_loss: 3.4829 - val_accuracy: 0.1875\n",
"Epoch 3211/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6569 - accuracy: 0.6250 - val_loss: 3.3081 - val_accuracy: 0.2188\n",
"Epoch 3212/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6976 - accuracy: 0.5938 - val_loss: 3.5385 - val_accuracy: 0.1875\n",
"Epoch 3213/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5205 - accuracy: 0.7500 - val_loss: 3.4082 - val_accuracy: 0.1875\n",
"Epoch 3214/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5646 - accuracy: 0.7188 - val_loss: 3.4331 - val_accuracy: 0.1875\n",
"Epoch 3215/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5502 - accuracy: 0.6250 - val_loss: 3.4570 - val_accuracy: 0.1875\n",
"Epoch 3216/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.9529 - accuracy: 0.6250 - val_loss: 3.1024 - val_accuracy: 0.1562\n",
"Epoch 3217/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7021 - accuracy: 0.5000 - val_loss: 3.7872 - val_accuracy: 0.1875\n",
"Epoch 3218/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7513 - accuracy: 0.6875 - val_loss: 3.5748 - val_accuracy: 0.1875\n",
"Epoch 3219/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5777 - accuracy: 0.6562 - val_loss: 3.4747 - val_accuracy: 0.1875\n",
"Epoch 3220/5000\n",
"1/1 [==============================] - 0s 231ms/step - loss: 0.6672 - accuracy: 0.6562 - val_loss: 3.6486 - val_accuracy: 0.1875\n",
"Epoch 3221/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6638 - accuracy: 0.6250 - val_loss: 3.5343 - val_accuracy: 0.1562\n",
"Epoch 3222/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6022 - accuracy: 0.6250 - val_loss: 3.5501 - val_accuracy: 0.1562\n",
"Epoch 3223/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5562 - accuracy: 0.5625 - val_loss: 3.5232 - val_accuracy: 0.1562\n",
"Epoch 3224/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6280 - accuracy: 0.5938 - val_loss: 3.5483 - val_accuracy: 0.1875\n",
"Epoch 3225/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5066 - accuracy: 0.7188 - val_loss: 3.6279 - val_accuracy: 0.1875\n",
"Epoch 3226/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6472 - accuracy: 0.6875 - val_loss: 3.5827 - val_accuracy: 0.1875\n",
"Epoch 3227/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6139 - accuracy: 0.6562 - val_loss: 3.5508 - val_accuracy: 0.1875\n",
"Epoch 3228/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5528 - accuracy: 0.6562 - val_loss: 3.7066 - val_accuracy: 0.1875\n",
"Epoch 3229/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5980 - accuracy: 0.6875 - val_loss: 3.5947 - val_accuracy: 0.1562\n",
"Epoch 3230/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.5704 - accuracy: 0.62 - 0s 165ms/step - loss: 0.5704 - accuracy: 0.6250 - val_loss: 3.5959 - val_accuracy: 0.1875\n",
"Epoch 3231/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6810 - accuracy: 0.6250 - val_loss: 3.6046 - val_accuracy: 0.1875\n",
"Epoch 3232/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6089 - accuracy: 0.6250 - val_loss: 3.5990 - val_accuracy: 0.1875\n",
"Epoch 3233/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5127 - accuracy: 0.7188 - val_loss: 3.5336 - val_accuracy: 0.1875\n",
"Epoch 3234/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5410 - accuracy: 0.6562 - val_loss: 3.6187 - val_accuracy: 0.1875\n",
"Epoch 3235/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6278 - accuracy: 0.6250 - val_loss: 3.7423 - val_accuracy: 0.1875\n",
"Epoch 3236/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6396 - accuracy: 0.5938 - val_loss: 3.5241 - val_accuracy: 0.1875\n",
"Epoch 3237/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5788 - accuracy: 0.6250 - val_loss: 3.8276 - val_accuracy: 0.1875\n",
"Epoch 3238/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7053 - accuracy: 0.5938 - val_loss: 3.5771 - val_accuracy: 0.1875\n",
"Epoch 3239/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6220 - accuracy: 0.6250 - val_loss: 3.6934 - val_accuracy: 0.1875\n",
"Epoch 3240/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5942 - accuracy: 0.5625 - val_loss: 3.5801 - val_accuracy: 0.1875\n",
"Epoch 3241/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5959 - accuracy: 0.5625 - val_loss: 3.5591 - val_accuracy: 0.1875\n",
"Epoch 3242/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6290 - accuracy: 0.5312 - val_loss: 3.5794 - val_accuracy: 0.1875\n",
"Epoch 3243/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6433 - accuracy: 0.6562 - val_loss: 3.6053 - val_accuracy: 0.1875\n",
"Epoch 3244/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5846 - accuracy: 0.7188 - val_loss: 3.5152 - val_accuracy: 0.1875\n",
"Epoch 3245/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6035 - accuracy: 0.6250 - val_loss: 3.5194 - val_accuracy: 0.1875\n",
"Epoch 3246/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.1902 - accuracy: 0.6562 - val_loss: 5.2713 - val_accuracy: 0.2188\n",
"Epoch 3247/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 1.1003 - accuracy: 0.3750 - val_loss: 3.2236 - val_accuracy: 0.1875\n",
"Epoch 3248/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8321 - accuracy: 0.5938 - val_loss: 3.7916 - val_accuracy: 0.2188\n",
"Epoch 3249/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6526 - accuracy: 0.6875 - val_loss: 3.7591 - val_accuracy: 0.1875\n",
"Epoch 3250/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5010 - accuracy: 0.7812 - val_loss: 3.8497 - val_accuracy: 0.1875\n",
"Epoch 3251/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.4833 - accuracy: 0.7812 - val_loss: 3.8892 - val_accuracy: 0.1875\n",
"Epoch 3252/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.4712 - accuracy: 0.7812 - val_loss: 3.8858 - val_accuracy: 0.1875\n",
"Epoch 3253/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5673 - accuracy: 0.7188 - val_loss: 3.7632 - val_accuracy: 0.2188\n",
"Epoch 3254/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5600 - accuracy: 0.5938 - val_loss: 3.6591 - val_accuracy: 0.2188\n",
"Epoch 3255/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5926 - accuracy: 0.5938 - val_loss: 4.0152 - val_accuracy: 0.1875\n",
"Epoch 3256/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5626 - accuracy: 0.6875 - val_loss: 3.6319 - val_accuracy: 0.1875\n",
"Epoch 3257/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5930 - accuracy: 0.6250 - val_loss: 3.8152 - val_accuracy: 0.1875\n",
"Epoch 3258/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5990 - accuracy: 0.7188 - val_loss: 3.8494 - val_accuracy: 0.1875\n",
"Epoch 3259/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6112 - accuracy: 0.6562 - val_loss: 3.6986 - val_accuracy: 0.1875\n",
"Epoch 3260/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9873 - accuracy: 0.6562 - val_loss: 3.7226 - val_accuracy: 0.2188\n",
"Epoch 3261/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6108 - accuracy: 0.6562 - val_loss: 3.8802 - val_accuracy: 0.1875\n",
"Epoch 3262/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6279 - accuracy: 0.6562 - val_loss: 3.7072 - val_accuracy: 0.1875\n",
"Epoch 3263/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5690 - accuracy: 0.7188 - val_loss: 3.6433 - val_accuracy: 0.1562\n",
"Epoch 3264/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6547 - accuracy: 0.6562 - val_loss: 3.9196 - val_accuracy: 0.2188\n",
"Epoch 3265/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6642 - accuracy: 0.5625 - val_loss: 3.7331 - val_accuracy: 0.1875\n",
"Epoch 3266/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6614 - accuracy: 0.5625 - val_loss: 3.7724 - val_accuracy: 0.1875\n",
"Epoch 3267/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5914 - accuracy: 0.5625 - val_loss: 3.7948 - val_accuracy: 0.1875\n",
"Epoch 3268/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6429 - accuracy: 0.5625 - val_loss: 3.8200 - val_accuracy: 0.1875\n",
"Epoch 3269/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5761 - accuracy: 0.6562 - val_loss: 3.7509 - val_accuracy: 0.1875\n",
"Epoch 3270/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5274 - accuracy: 0.7500 - val_loss: 3.6297 - val_accuracy: 0.1562\n",
"Epoch 3271/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5585 - accuracy: 0.6250 - val_loss: 3.8549 - val_accuracy: 0.1875\n",
"Epoch 3272/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4913 - accuracy: 0.7812 - val_loss: 3.8432 - val_accuracy: 0.1875\n",
"Epoch 3273/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5912 - accuracy: 0.6250 - val_loss: 3.8078 - val_accuracy: 0.1875\n",
"Epoch 3274/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6336 - accuracy: 0.6562 - val_loss: 3.6606 - val_accuracy: 0.1875\n",
"Epoch 3275/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6384 - accuracy: 0.6562 - val_loss: 4.2684 - val_accuracy: 0.1875\n",
"Epoch 3276/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7629 - accuracy: 0.4688 - val_loss: 3.6339 - val_accuracy: 0.1875\n",
"Epoch 3277/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6507 - accuracy: 0.5312 - val_loss: 3.9288 - val_accuracy: 0.1875\n",
"Epoch 3278/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6614 - accuracy: 0.5938 - val_loss: 3.6960 - val_accuracy: 0.1875\n",
"Epoch 3279/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4870 - accuracy: 0.7500 - val_loss: 3.8067 - val_accuracy: 0.1875\n",
"Epoch 3280/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6229 - accuracy: 0.6250 - val_loss: 3.8762 - val_accuracy: 0.1875\n",
"Epoch 3281/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6693 - accuracy: 0.6250 - val_loss: 4.0281 - val_accuracy: 0.1875\n",
"Epoch 3282/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.7144 - accuracy: 0.5312 - val_loss: 3.7081 - val_accuracy: 0.1875\n",
"Epoch 3283/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.5384 - accuracy: 0.7188 - val_loss: 3.7741 - val_accuracy: 0.1875\n",
"Epoch 3284/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5109 - accuracy: 0.7500 - val_loss: 3.6552 - val_accuracy: 0.1562\n",
"Epoch 3285/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5344 - accuracy: 0.6875 - val_loss: 3.7490 - val_accuracy: 0.1875\n",
"Epoch 3286/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4822 - accuracy: 0.7500 - val_loss: 3.7638 - val_accuracy: 0.1875\n",
"Epoch 3287/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5568 - accuracy: 0.7188 - val_loss: 3.8352 - val_accuracy: 0.1875\n",
"Epoch 3288/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4841 - accuracy: 0.6562 - val_loss: 3.7792 - val_accuracy: 0.1875\n",
"Epoch 3289/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4991 - accuracy: 0.7500 - val_loss: 3.6570 - val_accuracy: 0.1562\n",
"Epoch 3290/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5698 - accuracy: 0.6562 - val_loss: 3.8776 - val_accuracy: 0.1875\n",
"Epoch 3291/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5995 - accuracy: 0.6562 - val_loss: 3.7915 - val_accuracy: 0.1875\n",
"Epoch 3292/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5758 - accuracy: 0.5312 - val_loss: 3.6973 - val_accuracy: 0.1875\n",
"Epoch 3293/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.4902 - accuracy: 0.6875 - val_loss: 3.7206 - val_accuracy: 0.1875\n",
"Epoch 3294/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4978 - accuracy: 0.7500 - val_loss: 3.7272 - val_accuracy: 0.1875\n",
"Epoch 3295/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5642 - accuracy: 0.6875 - val_loss: 3.7895 - val_accuracy: 0.1875\n",
"Epoch 3296/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4044 - accuracy: 0.7500 - val_loss: 3.7566 - val_accuracy: 0.1875\n",
"Epoch 3297/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5499 - accuracy: 0.6250 - val_loss: 3.7834 - val_accuracy: 0.1875\n",
"Epoch 3298/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5739 - accuracy: 0.6562 - val_loss: 3.8439 - val_accuracy: 0.1875\n",
"Epoch 3299/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5324 - accuracy: 0.6562 - val_loss: 3.7532 - val_accuracy: 0.1875\n",
"Epoch 3300/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5694 - accuracy: 0.6562 - val_loss: 3.7355 - val_accuracy: 0.1875\n",
"Epoch 3301/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5783 - accuracy: 0.6562 - val_loss: 3.7340 - val_accuracy: 0.1875\n",
"Epoch 3302/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5166 - accuracy: 0.6250 - val_loss: 3.8575 - val_accuracy: 0.1875\n",
"Epoch 3303/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9357 - accuracy: 0.5938 - val_loss: 3.6588 - val_accuracy: 0.1875\n",
"Epoch 3304/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6943 - accuracy: 0.5938 - val_loss: 4.3087 - val_accuracy: 0.1250\n",
"Epoch 3305/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6838 - accuracy: 0.5625 - val_loss: 3.4351 - val_accuracy: 0.1875\n",
"Epoch 3306/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7178 - accuracy: 0.5938 - val_loss: 3.9461 - val_accuracy: 0.2188\n",
"Epoch 3307/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5703 - accuracy: 0.7188 - val_loss: 3.7700 - val_accuracy: 0.1875\n",
"Epoch 3308/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5740 - accuracy: 0.6875 - val_loss: 3.7858 - val_accuracy: 0.1875\n",
"Epoch 3309/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5802 - accuracy: 0.6562 - val_loss: 3.8743 - val_accuracy: 0.1875\n",
"Epoch 3310/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5489 - accuracy: 0.6875 - val_loss: 3.7038 - val_accuracy: 0.1875\n",
"Epoch 3311/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5524 - accuracy: 0.7188 - val_loss: 3.7463 - val_accuracy: 0.1875\n",
"Epoch 3312/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5075 - accuracy: 0.6875 - val_loss: 3.6984 - val_accuracy: 0.1875\n",
"Epoch 3313/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6536 - accuracy: 0.6250 - val_loss: 3.9556 - val_accuracy: 0.2188\n",
"Epoch 3314/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6109 - accuracy: 0.6562 - val_loss: 3.6600 - val_accuracy: 0.1875\n",
"Epoch 3315/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5788 - accuracy: 0.7188 - val_loss: 3.7072 - val_accuracy: 0.1875\n",
"Epoch 3316/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5995 - accuracy: 0.5000 - val_loss: 3.8783 - val_accuracy: 0.1875\n",
"Epoch 3317/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.6257 - accuracy: 0.6562 - val_loss: 3.7681 - val_accuracy: 0.1875\n",
"Epoch 3318/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5491 - accuracy: 0.6562 - val_loss: 3.7488 - val_accuracy: 0.1875\n",
"Epoch 3319/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5246 - accuracy: 0.6875 - val_loss: 3.6961 - val_accuracy: 0.1875\n",
"Epoch 3320/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5825 - accuracy: 0.6250 - val_loss: 3.9031 - val_accuracy: 0.1875\n",
"Epoch 3321/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5117 - accuracy: 0.7500 - val_loss: 3.7741 - val_accuracy: 0.1875\n",
"Epoch 3322/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6061 - accuracy: 0.6562 - val_loss: 3.7624 - val_accuracy: 0.1875\n",
"Epoch 3323/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5971 - accuracy: 0.6250 - val_loss: 3.9146 - val_accuracy: 0.1875\n",
"Epoch 3324/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.4843 - accuracy: 0.7812 - val_loss: 3.7967 - val_accuracy: 0.1875\n",
"Epoch 3325/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5628 - accuracy: 0.5312 - val_loss: 3.7906 - val_accuracy: 0.1875\n",
"Epoch 3326/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.4747 - accuracy: 0.6875 - val_loss: 3.7612 - val_accuracy: 0.1875\n",
"Epoch 3327/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5546 - accuracy: 0.6875 - val_loss: 3.9528 - val_accuracy: 0.1875\n",
"Epoch 3328/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5332 - accuracy: 0.6875 - val_loss: 3.9805 - val_accuracy: 0.1875\n",
"Epoch 3329/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5798 - accuracy: 0.6875 - val_loss: 3.7439 - val_accuracy: 0.1875\n",
"Epoch 3330/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5285 - accuracy: 0.6875 - val_loss: 3.8387 - val_accuracy: 0.1875\n",
"Epoch 3331/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5489 - accuracy: 0.6250 - val_loss: 3.9110 - val_accuracy: 0.1875\n",
"Epoch 3332/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5872 - accuracy: 0.7188 - val_loss: 3.7676 - val_accuracy: 0.1875\n",
"Epoch 3333/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6116 - accuracy: 0.6250 - val_loss: 4.2177 - val_accuracy: 0.2188\n",
"Epoch 3334/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6617 - accuracy: 0.5938 - val_loss: 3.6830 - val_accuracy: 0.1562\n",
"Epoch 3335/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5820 - accuracy: 0.5000 - val_loss: 3.9664 - val_accuracy: 0.1875\n",
"Epoch 3336/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5754 - accuracy: 0.6250 - val_loss: 3.8388 - val_accuracy: 0.1875\n",
"Epoch 3337/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6045 - accuracy: 0.6250 - val_loss: 3.9125 - val_accuracy: 0.1875\n",
"Epoch 3338/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4986 - accuracy: 0.7188 - val_loss: 3.8539 - val_accuracy: 0.1875\n",
"Epoch 3339/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5446 - accuracy: 0.5938 - val_loss: 3.6492 - val_accuracy: 0.1562\n",
"Epoch 3340/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6342 - accuracy: 0.5000 - val_loss: 3.9416 - val_accuracy: 0.1875\n",
"Epoch 3341/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5929 - accuracy: 0.6875 - val_loss: 3.7394 - val_accuracy: 0.1875\n",
"Epoch 3342/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6413 - accuracy: 0.5938 - val_loss: 4.0161 - val_accuracy: 0.1875\n",
"Epoch 3343/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5465 - accuracy: 0.6562 - val_loss: 3.9245 - val_accuracy: 0.1875\n",
"Epoch 3344/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5162 - accuracy: 0.6250 - val_loss: 3.8014 - val_accuracy: 0.1875\n",
"Epoch 3345/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6312 - accuracy: 0.5938 - val_loss: 3.9910 - val_accuracy: 0.1875\n",
"Epoch 3346/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5662 - accuracy: 0.6250 - val_loss: 3.6614 - val_accuracy: 0.1562\n",
"Epoch 3347/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5760 - accuracy: 0.6875 - val_loss: 4.3838 - val_accuracy: 0.1875\n",
"Epoch 3348/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6689 - accuracy: 0.5625 - val_loss: 3.6432 - val_accuracy: 0.2188\n",
"Epoch 3349/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5710 - accuracy: 0.6562 - val_loss: 4.0136 - val_accuracy: 0.1875\n",
"Epoch 3350/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5731 - accuracy: 0.5938 - val_loss: 3.6931 - val_accuracy: 0.1562\n",
"Epoch 3351/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5247 - accuracy: 0.6562 - val_loss: 3.8059 - val_accuracy: 0.1875\n",
"Epoch 3352/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5778 - accuracy: 0.6250 - val_loss: 3.9032 - val_accuracy: 0.1875\n",
"Epoch 3353/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5709 - accuracy: 0.6875 - val_loss: 4.0174 - val_accuracy: 0.1875\n",
"Epoch 3354/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4449 - accuracy: 0.7188 - val_loss: 3.7965 - val_accuracy: 0.2188\n",
"Epoch 3355/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5996 - accuracy: 0.5938 - val_loss: 3.9254 - val_accuracy: 0.1875\n",
"Epoch 3356/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5096 - accuracy: 0.6875 - val_loss: 3.8998 - val_accuracy: 0.1875\n",
"Epoch 3357/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8479 - accuracy: 0.4375 - val_loss: 3.7205 - val_accuracy: 0.2188\n",
"Epoch 3358/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6563 - accuracy: 0.4688 - val_loss: 4.1110 - val_accuracy: 0.2188\n",
"Epoch 3359/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4964 - accuracy: 0.7188 - val_loss: 3.6990 - val_accuracy: 0.1875\n",
"Epoch 3360/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5268 - accuracy: 0.6875 - val_loss: 3.8295 - val_accuracy: 0.1875\n",
"Epoch 3361/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5587 - accuracy: 0.6562 - val_loss: 4.0937 - val_accuracy: 0.1875\n",
"Epoch 3362/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5830 - accuracy: 0.5938 - val_loss: 3.6101 - val_accuracy: 0.1562\n",
"Epoch 3363/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7397 - accuracy: 0.5312 - val_loss: 4.1133 - val_accuracy: 0.1562\n",
"Epoch 3364/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5534 - accuracy: 0.7188 - val_loss: 3.6283 - val_accuracy: 0.1562\n",
"Epoch 3365/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7125 - accuracy: 0.5938 - val_loss: 4.2019 - val_accuracy: 0.1562\n",
"Epoch 3366/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6215 - accuracy: 0.6875 - val_loss: 3.7031 - val_accuracy: 0.1875\n",
"Epoch 3367/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7624 - accuracy: 0.5625 - val_loss: 4.2219 - val_accuracy: 0.2188\n",
"Epoch 3368/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6979 - accuracy: 0.5938 - val_loss: 3.6084 - val_accuracy: 0.2188\n",
"Epoch 3369/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6773 - accuracy: 0.5938 - val_loss: 4.3216 - val_accuracy: 0.2500\n",
"Epoch 3370/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5796 - accuracy: 0.6562 - val_loss: 3.5487 - val_accuracy: 0.2188\n",
"Epoch 3371/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6540 - accuracy: 0.6250 - val_loss: 4.1023 - val_accuracy: 0.2188\n",
"Epoch 3372/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5786 - accuracy: 0.5625 - val_loss: 3.8220 - val_accuracy: 0.1875\n",
"Epoch 3373/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6064 - accuracy: 0.62 - 0s 170ms/step - loss: 0.6064 - accuracy: 0.6250 - val_loss: 4.0200 - val_accuracy: 0.1875\n",
"Epoch 3374/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5572 - accuracy: 0.6562 - val_loss: 3.6243 - val_accuracy: 0.1875\n",
"Epoch 3375/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5231 - accuracy: 0.6875 - val_loss: 4.1742 - val_accuracy: 0.2188\n",
"Epoch 3376/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6747 - accuracy: 0.5938 - val_loss: 3.7145 - val_accuracy: 0.1875\n",
"Epoch 3377/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5834 - accuracy: 0.5938 - val_loss: 4.0435 - val_accuracy: 0.1875\n",
"Epoch 3378/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4679 - accuracy: 0.6250 - val_loss: 3.6305 - val_accuracy: 0.1562\n",
"Epoch 3379/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5677 - accuracy: 0.6250 - val_loss: 3.9831 - val_accuracy: 0.1875\n",
"Epoch 3380/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5430 - accuracy: 0.6875 - val_loss: 3.7811 - val_accuracy: 0.1875\n",
"Epoch 3381/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5358 - accuracy: 0.5938 - val_loss: 3.8385 - val_accuracy: 0.1875\n",
"Epoch 3382/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5817 - accuracy: 0.6562 - val_loss: 3.8308 - val_accuracy: 0.1875\n",
"Epoch 3383/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8138 - accuracy: 0.6875 - val_loss: 5.7631 - val_accuracy: 0.1250\n",
"Epoch 3384/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.5585 - accuracy: 0.3125 - val_loss: 3.0529 - val_accuracy: 0.1875\n",
"Epoch 3385/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.2130 - accuracy: 0.3750 - val_loss: 22.9035 - val_accuracy: 0.0312\n",
"Epoch 3386/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 26.0380 - accuracy: 0.0312 - val_loss: 2.9773 - val_accuracy: 0.0312\n",
"Epoch 3387/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.6775 - accuracy: 0.1562 - val_loss: 2.8661 - val_accuracy: 0.0312\n",
"Epoch 3388/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 3.0344 - accuracy: 0.1875 - val_loss: 2.7883 - val_accuracy: 0.0312\n",
"Epoch 3389/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.9039 - accuracy: 0.1250 - val_loss: 2.6745 - val_accuracy: 0.0312\n",
"Epoch 3390/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.7230 - accuracy: 0.0938 - val_loss: 2.6667 - val_accuracy: 0.0000e+00\n",
"Epoch 3391/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.5423 - accuracy: 0.2812 - val_loss: 2.8348 - val_accuracy: 0.0312\n",
"Epoch 3392/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.7232 - accuracy: 0.0938 - val_loss: 2.8501 - val_accuracy: 0.0000e+00\n",
"Epoch 3393/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 2.2672 - accuracy: 0.1250 - val_loss: 2.8410 - val_accuracy: 0.0312\n",
"Epoch 3394/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 2.5418 - accuracy: 0.1875 - val_loss: 2.7451 - val_accuracy: 0.0312\n",
"Epoch 3395/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.9293 - accuracy: 0.2500 - val_loss: 2.8464 - val_accuracy: 0.0312\n",
"Epoch 3396/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 2.1359 - accuracy: 0.2812 - val_loss: 2.9360 - val_accuracy: 0.0938\n",
"Epoch 3397/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.6789 - accuracy: 0.2188 - val_loss: 2.9740 - val_accuracy: 0.1562\n",
"Epoch 3398/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.7565 - accuracy: 0.2812 - val_loss: 3.0397 - val_accuracy: 0.0938\n",
"Epoch 3399/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.0718 - accuracy: 0.4062 - val_loss: 2.7237 - val_accuracy: 0.1875\n",
"Epoch 3400/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9401 - accuracy: 0.4375 - val_loss: 2.7698 - val_accuracy: 0.1875\n",
"Epoch 3401/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8811 - accuracy: 0.4688 - val_loss: 2.8526 - val_accuracy: 0.2188\n",
"Epoch 3402/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.9963 - accuracy: 0.5000 - val_loss: 2.9385 - val_accuracy: 0.1250\n",
"Epoch 3403/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.9062 - accuracy: 0.4062 - val_loss: 2.8384 - val_accuracy: 0.1875\n",
"Epoch 3404/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8595 - accuracy: 0.5000 - val_loss: 2.8632 - val_accuracy: 0.1875\n",
"Epoch 3405/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8044 - accuracy: 0.6250 - val_loss: 2.8605 - val_accuracy: 0.1875\n",
"Epoch 3406/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7643 - accuracy: 0.5625 - val_loss: 2.8168 - val_accuracy: 0.2188\n",
"Epoch 3407/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.8132 - accuracy: 0.5938 - val_loss: 2.7799 - val_accuracy: 0.2500\n",
"Epoch 3408/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8644 - accuracy: 0.5625 - val_loss: 2.8396 - val_accuracy: 0.1875\n",
"Epoch 3409/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8216 - accuracy: 0.6250 - val_loss: 2.8350 - val_accuracy: 0.2500\n",
"Epoch 3410/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7140 - accuracy: 0.5625 - val_loss: 2.8193 - val_accuracy: 0.2500\n",
"Epoch 3411/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.9904 - accuracy: 0.5312 - val_loss: 2.9752 - val_accuracy: 0.2500\n",
"Epoch 3412/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7897 - accuracy: 0.5000 - val_loss: 2.9489 - val_accuracy: 0.2500\n",
"Epoch 3413/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7449 - accuracy: 0.5000 - val_loss: 2.9550 - val_accuracy: 0.2500\n",
"Epoch 3414/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6770 - accuracy: 0.6562 - val_loss: 2.9450 - val_accuracy: 0.2500\n",
"Epoch 3415/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7395 - accuracy: 0.5625 - val_loss: 2.9466 - val_accuracy: 0.2500\n",
"Epoch 3416/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6852 - accuracy: 0.5938 - val_loss: 2.9514 - val_accuracy: 0.2500\n",
"Epoch 3417/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6110 - accuracy: 0.7812 - val_loss: 2.9450 - val_accuracy: 0.2500\n",
"Epoch 3418/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6599 - accuracy: 0.5938 - val_loss: 2.9558 - val_accuracy: 0.2500\n",
"Epoch 3419/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6728 - accuracy: 0.6250 - val_loss: 2.9525 - val_accuracy: 0.2500\n",
"Epoch 3420/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6678 - accuracy: 0.5625 - val_loss: 2.9540 - val_accuracy: 0.2500\n",
"Epoch 3421/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.6430 - accuracy: 0.7188 - val_loss: 2.9955 - val_accuracy: 0.2500\n",
"Epoch 3422/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6338 - accuracy: 0.5312 - val_loss: 2.9692 - val_accuracy: 0.2500\n",
"Epoch 3423/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6695 - accuracy: 0.7500 - val_loss: 2.9722 - val_accuracy: 0.2500\n",
"Epoch 3424/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6582 - accuracy: 0.5938 - val_loss: 3.0134 - val_accuracy: 0.2500\n",
"Epoch 3425/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6154 - accuracy: 0.6875 - val_loss: 2.9558 - val_accuracy: 0.2500\n",
"Epoch 3426/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.7094 - accuracy: 0.5938 - val_loss: 3.0579 - val_accuracy: 0.2500\n",
"Epoch 3427/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7220 - accuracy: 0.5625 - val_loss: 3.0427 - val_accuracy: 0.2500\n",
"Epoch 3428/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6757 - accuracy: 0.5312 - val_loss: 3.0056 - val_accuracy: 0.2500\n",
"Epoch 3429/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6380 - accuracy: 0.6562 - val_loss: 2.9447 - val_accuracy: 0.2500\n",
"Epoch 3430/5000\n",
"1/1 [==============================] - 0s 151ms/step - loss: 0.6168 - accuracy: 0.6875 - val_loss: 3.0019 - val_accuracy: 0.2500\n",
"Epoch 3431/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5614 - accuracy: 0.6875 - val_loss: 2.9821 - val_accuracy: 0.2500\n",
"Epoch 3432/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6908 - accuracy: 0.5000 - val_loss: 2.9790 - val_accuracy: 0.2500\n",
"Epoch 3433/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5605 - accuracy: 0.6875 - val_loss: 2.9852 - val_accuracy: 0.2500\n",
"Epoch 3434/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5391 - accuracy: 0.6875 - val_loss: 3.0111 - val_accuracy: 0.2500\n",
"Epoch 3435/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6736 - accuracy: 0.7188 - val_loss: 3.0774 - val_accuracy: 0.2188\n",
"Epoch 3436/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6576 - accuracy: 0.6562 - val_loss: 3.0549 - val_accuracy: 0.2500\n",
"Epoch 3437/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6407 - accuracy: 0.6250 - val_loss: 3.0109 - val_accuracy: 0.2500\n",
"Epoch 3438/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6173 - accuracy: 0.6875 - val_loss: 3.1098 - val_accuracy: 0.1875\n",
"Epoch 3439/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6048 - accuracy: 0.5938 - val_loss: 3.0238 - val_accuracy: 0.2500\n",
"Epoch 3440/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6476 - accuracy: 0.5938 - val_loss: 3.1411 - val_accuracy: 0.1875\n",
"Epoch 3441/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6135 - accuracy: 0.5312 - val_loss: 3.0618 - val_accuracy: 0.2500\n",
"Epoch 3442/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7270 - accuracy: 0.6250 - val_loss: 3.1243 - val_accuracy: 0.2500\n",
"Epoch 3443/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5952 - accuracy: 0.6250 - val_loss: 3.0652 - val_accuracy: 0.2188\n",
"Epoch 3444/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6164 - accuracy: 0.6875 - val_loss: 3.0673 - val_accuracy: 0.2188\n",
"Epoch 3445/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6295 - accuracy: 0.6250 - val_loss: 3.1451 - val_accuracy: 0.1875\n",
"Epoch 3446/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6393 - accuracy: 0.6562 - val_loss: 3.0172 - val_accuracy: 0.2188\n",
"Epoch 3447/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6911 - accuracy: 0.5312 - val_loss: 3.1023 - val_accuracy: 0.2188\n",
"Epoch 3448/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.5662 - accuracy: 0.6562 - val_loss: 3.0682 - val_accuracy: 0.1875\n",
"Epoch 3449/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5433 - accuracy: 0.6562 - val_loss: 3.0638 - val_accuracy: 0.2188\n",
"Epoch 3450/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6414 - accuracy: 0.5312 - val_loss: 3.1315 - val_accuracy: 0.1875\n",
"Epoch 3451/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5621 - accuracy: 0.6250 - val_loss: 3.0629 - val_accuracy: 0.1875\n",
"Epoch 3452/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6436 - accuracy: 0.7188 - val_loss: 3.0284 - val_accuracy: 0.2188\n",
"Epoch 3453/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6468 - accuracy: 0.5625 - val_loss: 3.1580 - val_accuracy: 0.1875\n",
"Epoch 3454/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6243 - accuracy: 0.6562 - val_loss: 3.0220 - val_accuracy: 0.2188\n",
"Epoch 3455/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5323 - accuracy: 0.7188 - val_loss: 3.1683 - val_accuracy: 0.1875\n",
"Epoch 3456/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6237 - accuracy: 0.6562 - val_loss: 3.1319 - val_accuracy: 0.1875\n",
"Epoch 3457/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5251 - accuracy: 0.7500 - val_loss: 3.1020 - val_accuracy: 0.1562\n",
"Epoch 3458/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5724 - accuracy: 0.7188 - val_loss: 3.1625 - val_accuracy: 0.1875\n",
"Epoch 3459/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6252 - accuracy: 0.5938 - val_loss: 3.1474 - val_accuracy: 0.1875\n",
"Epoch 3460/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5641 - accuracy: 0.7500 - val_loss: 3.1711 - val_accuracy: 0.1875\n",
"Epoch 3461/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5333 - accuracy: 0.6875 - val_loss: 3.1658 - val_accuracy: 0.1875\n",
"Epoch 3462/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5756 - accuracy: 0.6875 - val_loss: 3.1679 - val_accuracy: 0.1875\n",
"Epoch 3463/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5975 - accuracy: 0.6875 - val_loss: 3.2126 - val_accuracy: 0.1875\n",
"Epoch 3464/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5751 - accuracy: 0.6875 - val_loss: 3.2054 - val_accuracy: 0.1875\n",
"Epoch 3465/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6040 - accuracy: 0.6875 - val_loss: 3.2675 - val_accuracy: 0.1875\n",
"Epoch 3466/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5662 - accuracy: 0.7188 - val_loss: 3.1693 - val_accuracy: 0.1875\n",
"Epoch 3467/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5452 - accuracy: 0.6250 - val_loss: 3.2025 - val_accuracy: 0.1875\n",
"Epoch 3468/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6285 - accuracy: 0.6250 - val_loss: 3.1961 - val_accuracy: 0.1875\n",
"Epoch 3469/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9168 - accuracy: 0.6875 - val_loss: 3.4736 - val_accuracy: 0.1250\n",
"Epoch 3470/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7138 - accuracy: 0.5312 - val_loss: 3.2118 - val_accuracy: 0.1562\n",
"Epoch 3471/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5638 - accuracy: 0.6562 - val_loss: 3.2981 - val_accuracy: 0.1875\n",
"Epoch 3472/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5185 - accuracy: 0.6875 - val_loss: 3.2676 - val_accuracy: 0.1562\n",
"Epoch 3473/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7310 - accuracy: 0.6250 - val_loss: 3.3192 - val_accuracy: 0.1875\n",
"Epoch 3474/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6089 - accuracy: 0.6875 - val_loss: 3.3181 - val_accuracy: 0.1875\n",
"Epoch 3475/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5974 - accuracy: 0.6562 - val_loss: 3.2927 - val_accuracy: 0.1562\n",
"Epoch 3476/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5499 - accuracy: 0.7812 - val_loss: 3.2903 - val_accuracy: 0.1562\n",
"Epoch 3477/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5888 - accuracy: 0.6250 - val_loss: 3.2864 - val_accuracy: 0.1875\n",
"Epoch 3478/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.5852 - accuracy: 0.5625 - val_loss: 3.3610 - val_accuracy: 0.1875\n",
"Epoch 3479/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6122 - accuracy: 0.6562 - val_loss: 3.2457 - val_accuracy: 0.1875\n",
"Epoch 3480/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6428 - accuracy: 0.6562 - val_loss: 3.4083 - val_accuracy: 0.1875\n",
"Epoch 3481/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6407 - accuracy: 0.5938 - val_loss: 3.2953 - val_accuracy: 0.1875\n",
"Epoch 3482/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5513 - accuracy: 0.7188 - val_loss: 3.2744 - val_accuracy: 0.1562\n",
"Epoch 3483/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.5944 - accuracy: 0.7500 - val_loss: 3.3510 - val_accuracy: 0.1875\n",
"Epoch 3484/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5447 - accuracy: 0.6562 - val_loss: 3.2713 - val_accuracy: 0.1562\n",
"Epoch 3485/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5181 - accuracy: 0.7500 - val_loss: 3.2940 - val_accuracy: 0.1562\n",
"Epoch 3486/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.5943 - accuracy: 0.6562 - val_loss: 3.2251 - val_accuracy: 0.1875\n",
"Epoch 3487/5000\n",
"1/1 [==============================] - 0s 204ms/step - loss: 0.6063 - accuracy: 0.5312 - val_loss: 3.2832 - val_accuracy: 0.1562\n",
"Epoch 3488/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.5246 - accuracy: 0.6250 - val_loss: 3.3342 - val_accuracy: 0.1875\n",
"Epoch 3489/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4604 - accuracy: 0.7500 - val_loss: 3.2903 - val_accuracy: 0.1562\n",
"Epoch 3490/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6352 - accuracy: 0.5625 - val_loss: 3.3544 - val_accuracy: 0.1875\n",
"Epoch 3491/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6126 - accuracy: 0.59 - 0s 163ms/step - loss: 0.6126 - accuracy: 0.5938 - val_loss: 3.2818 - val_accuracy: 0.1875\n",
"Epoch 3492/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5359 - accuracy: 0.7500 - val_loss: 3.3392 - val_accuracy: 0.1875\n",
"Epoch 3493/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.6495 - accuracy: 0.5938 - val_loss: 3.3571 - val_accuracy: 0.1875\n",
"Epoch 3494/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5537 - accuracy: 0.7500 - val_loss: 3.2680 - val_accuracy: 0.2188\n",
"Epoch 3495/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5493 - accuracy: 0.6562 - val_loss: 3.4156 - val_accuracy: 0.1875\n",
"Epoch 3496/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5745 - accuracy: 0.6875 - val_loss: 3.2874 - val_accuracy: 0.1875\n",
"Epoch 3497/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6008 - accuracy: 0.6562 - val_loss: 3.4144 - val_accuracy: 0.1875\n",
"Epoch 3498/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5243 - accuracy: 0.7188 - val_loss: 3.3373 - val_accuracy: 0.1875\n",
"Epoch 3499/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5838 - accuracy: 0.8125 - val_loss: 3.4383 - val_accuracy: 0.2188\n",
"Epoch 3500/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6020 - accuracy: 0.6250 - val_loss: 3.3411 - val_accuracy: 0.1875\n",
"Epoch 3501/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5101 - accuracy: 0.6562 - val_loss: 3.4589 - val_accuracy: 0.1875\n",
"Epoch 3502/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6825 - accuracy: 0.6250 - val_loss: 3.3377 - val_accuracy: 0.1875\n",
"Epoch 3503/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6842 - accuracy: 0.5625 - val_loss: 3.4407 - val_accuracy: 0.1875\n",
"Epoch 3504/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5002 - accuracy: 0.7500 - val_loss: 3.3900 - val_accuracy: 0.1875\n",
"Epoch 3505/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6318 - accuracy: 0.5938 - val_loss: 3.3964 - val_accuracy: 0.1875\n",
"Epoch 3506/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5254 - accuracy: 0.6875 - val_loss: 3.3917 - val_accuracy: 0.1875\n",
"Epoch 3507/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6925 - accuracy: 0.6250 - val_loss: 3.3985 - val_accuracy: 0.1875\n",
"Epoch 3508/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5570 - accuracy: 0.6562 - val_loss: 3.4751 - val_accuracy: 0.1875\n",
"Epoch 3509/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5547 - accuracy: 0.6875 - val_loss: 3.4603 - val_accuracy: 0.1875\n",
"Epoch 3510/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.5677 - accuracy: 0.6250 - val_loss: 3.3981 - val_accuracy: 0.1875\n",
"Epoch 3511/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5835 - accuracy: 0.6250 - val_loss: 3.4157 - val_accuracy: 0.1875\n",
"Epoch 3512/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5928 - accuracy: 0.6562 - val_loss: 3.5923 - val_accuracy: 0.2188\n",
"Epoch 3513/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5858 - accuracy: 0.5938 - val_loss: 3.5003 - val_accuracy: 0.1875\n",
"Epoch 3514/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5473 - accuracy: 0.7188 - val_loss: 3.4510 - val_accuracy: 0.1875\n",
"Epoch 3515/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.5246 - accuracy: 0.6875 - val_loss: 3.5003 - val_accuracy: 0.1875\n",
"Epoch 3516/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.5069 - accuracy: 0.6562 - val_loss: 3.5377 - val_accuracy: 0.1875\n",
"Epoch 3517/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5817 - accuracy: 0.5938 - val_loss: 3.4949 - val_accuracy: 0.1875\n",
"Epoch 3518/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5659 - accuracy: 0.6250 - val_loss: 3.6037 - val_accuracy: 0.1875\n",
"Epoch 3519/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6036 - accuracy: 0.6250 - val_loss: 3.4992 - val_accuracy: 0.1875\n",
"Epoch 3520/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6771 - accuracy: 0.5312 - val_loss: 3.3606 - val_accuracy: 0.1875\n",
"Epoch 3521/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.1149 - accuracy: 0.5625 - val_loss: 3.3182 - val_accuracy: 0.1250\n",
"Epoch 3522/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8930 - accuracy: 0.4688 - val_loss: 4.1717 - val_accuracy: 0.1562\n",
"Epoch 3523/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.8259 - accuracy: 0.3750 - val_loss: 3.2474 - val_accuracy: 0.1562\n",
"Epoch 3524/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6578 - accuracy: 0.5938 - val_loss: 3.7151 - val_accuracy: 0.1875\n",
"Epoch 3525/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5984 - accuracy: 0.5938 - val_loss: 3.3823 - val_accuracy: 0.1875\n",
"Epoch 3526/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5877 - accuracy: 0.6562 - val_loss: 3.4189 - val_accuracy: 0.1875\n",
"Epoch 3527/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6629 - accuracy: 0.5625 - val_loss: 3.5557 - val_accuracy: 0.2188\n",
"Epoch 3528/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5867 - accuracy: 0.5938 - val_loss: 3.3708 - val_accuracy: 0.1562\n",
"Epoch 3529/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5575 - accuracy: 0.6562 - val_loss: 3.5291 - val_accuracy: 0.1875\n",
"Epoch 3530/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4862 - accuracy: 0.6562 - val_loss: 3.4760 - val_accuracy: 0.1875\n",
"Epoch 3531/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4445 - accuracy: 0.7500 - val_loss: 3.3903 - val_accuracy: 0.2188\n",
"Epoch 3532/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5061 - accuracy: 0.6562 - val_loss: 3.5062 - val_accuracy: 0.1875\n",
"Epoch 3533/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.6758 - accuracy: 0.5312 - val_loss: 3.4418 - val_accuracy: 0.1875\n",
"Epoch 3534/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4840 - accuracy: 0.7188 - val_loss: 3.4418 - val_accuracy: 0.1875\n",
"Epoch 3535/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5276 - accuracy: 0.6875 - val_loss: 3.4998 - val_accuracy: 0.1875\n",
"Epoch 3536/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5070 - accuracy: 0.6875 - val_loss: 3.4601 - val_accuracy: 0.1562\n",
"Epoch 3537/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5299 - accuracy: 0.6250 - val_loss: 3.4821 - val_accuracy: 0.1875\n",
"Epoch 3538/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4876 - accuracy: 0.6875 - val_loss: 3.5150 - val_accuracy: 0.1875\n",
"Epoch 3539/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6430 - accuracy: 0.5625 - val_loss: 3.4555 - val_accuracy: 0.1875\n",
"Epoch 3540/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5665 - accuracy: 0.6250 - val_loss: 3.5629 - val_accuracy: 0.1875\n",
"Epoch 3541/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.5449 - accuracy: 0.6875 - val_loss: 3.4246 - val_accuracy: 0.1562\n",
"Epoch 3542/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.6134 - accuracy: 0.6250 - val_loss: 3.6292 - val_accuracy: 0.1875\n",
"Epoch 3543/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6218 - accuracy: 0.6250 - val_loss: 3.2582 - val_accuracy: 0.2188\n",
"Epoch 3544/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6947 - accuracy: 0.5625 - val_loss: 3.5797 - val_accuracy: 0.1875\n",
"Epoch 3545/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6015 - accuracy: 0.5938 - val_loss: 3.4165 - val_accuracy: 0.1875\n",
"Epoch 3546/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5562 - accuracy: 0.6562 - val_loss: 3.5317 - val_accuracy: 0.1875\n",
"Epoch 3547/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4884 - accuracy: 0.7812 - val_loss: 3.4531 - val_accuracy: 0.1875\n",
"Epoch 3548/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5999 - accuracy: 0.6562 - val_loss: 3.5037 - val_accuracy: 0.1875\n",
"Epoch 3549/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7527 - accuracy: 0.5938 - val_loss: 3.9270 - val_accuracy: 0.2500\n",
"Epoch 3550/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6028 - accuracy: 0.5312 - val_loss: 3.5705 - val_accuracy: 0.2188\n",
"Epoch 3551/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5907 - accuracy: 0.6250 - val_loss: 3.6127 - val_accuracy: 0.2188\n",
"Epoch 3552/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5421 - accuracy: 0.6250 - val_loss: 3.5630 - val_accuracy: 0.1875\n",
"Epoch 3553/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5372 - accuracy: 0.8125 - val_loss: 3.4575 - val_accuracy: 0.2188\n",
"Epoch 3554/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6956 - accuracy: 0.5625 - val_loss: 3.7681 - val_accuracy: 0.2188\n",
"Epoch 3555/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5353 - accuracy: 0.6875 - val_loss: 3.4752 - val_accuracy: 0.1875\n",
"Epoch 3556/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5966 - accuracy: 0.5938 - val_loss: 3.6518 - val_accuracy: 0.1875\n",
"Epoch 3557/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6789 - accuracy: 0.6562 - val_loss: 3.3899 - val_accuracy: 0.1875\n",
"Epoch 3558/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6788 - accuracy: 0.5938 - val_loss: 3.9069 - val_accuracy: 0.1875\n",
"Epoch 3559/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7306 - accuracy: 0.5938 - val_loss: 3.3467 - val_accuracy: 0.2188\n",
"Epoch 3560/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6323 - accuracy: 0.5938 - val_loss: 3.9459 - val_accuracy: 0.1875\n",
"Epoch 3561/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6097 - accuracy: 0.6562 - val_loss: 3.4230 - val_accuracy: 0.1875\n",
"Epoch 3562/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6114 - accuracy: 0.5625 - val_loss: 3.5767 - val_accuracy: 0.1875\n",
"Epoch 3563/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5552 - accuracy: 0.7812 - val_loss: 3.5439 - val_accuracy: 0.1875\n",
"Epoch 3564/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5380 - accuracy: 0.6875 - val_loss: 3.5052 - val_accuracy: 0.2188\n",
"Epoch 3565/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.5917 - accuracy: 0.6875 - val_loss: 3.5334 - val_accuracy: 0.2188\n",
"Epoch 3566/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6130 - accuracy: 0.6250 - val_loss: 3.6229 - val_accuracy: 0.1875\n",
"Epoch 3567/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6209 - accuracy: 0.5938 - val_loss: 3.4228 - val_accuracy: 0.1875\n",
"Epoch 3568/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5448 - accuracy: 0.6875 - val_loss: 3.7945 - val_accuracy: 0.1875\n",
"Epoch 3569/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5861 - accuracy: 0.6250 - val_loss: 3.6054 - val_accuracy: 0.1875\n",
"Epoch 3570/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5254 - accuracy: 0.7188 - val_loss: 3.6613 - val_accuracy: 0.1875\n",
"Epoch 3571/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5013 - accuracy: 0.6562 - val_loss: 3.6131 - val_accuracy: 0.1875\n",
"Epoch 3572/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5679 - accuracy: 0.6562 - val_loss: 3.7814 - val_accuracy: 0.1875\n",
"Epoch 3573/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5663 - accuracy: 0.7500 - val_loss: 3.6196 - val_accuracy: 0.2188\n",
"Epoch 3574/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5098 - accuracy: 0.6562 - val_loss: 3.5997 - val_accuracy: 0.1875\n",
"Epoch 3575/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5019 - accuracy: 0.6562 - val_loss: 3.6271 - val_accuracy: 0.1875\n",
"Epoch 3576/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4950 - accuracy: 0.7500 - val_loss: 3.6549 - val_accuracy: 0.1875\n",
"Epoch 3577/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6190 - accuracy: 0.6562 - val_loss: 3.6870 - val_accuracy: 0.1875\n",
"Epoch 3578/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6488 - accuracy: 0.5312 - val_loss: 3.5507 - val_accuracy: 0.1875\n",
"Epoch 3579/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5057 - accuracy: 0.6875 - val_loss: 3.6397 - val_accuracy: 0.1875\n",
"Epoch 3580/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5142 - accuracy: 0.7500 - val_loss: 3.5575 - val_accuracy: 0.1875\n",
"Epoch 3581/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7404 - accuracy: 0.6562 - val_loss: 3.6804 - val_accuracy: 0.1875\n",
"Epoch 3582/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6733 - accuracy: 0.6875 - val_loss: 3.3185 - val_accuracy: 0.1875\n",
"Epoch 3583/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8382 - accuracy: 0.4062 - val_loss: 4.1071 - val_accuracy: 0.1562\n",
"Epoch 3584/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7468 - accuracy: 0.4688 - val_loss: 3.2381 - val_accuracy: 0.1875\n",
"Epoch 3585/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.3080 - accuracy: 0.5625 - val_loss: 8.6543 - val_accuracy: 0.0312\n",
"Epoch 3586/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 4.9133 - accuracy: 0.0625 - val_loss: 3.1949 - val_accuracy: 0.1562\n",
"Epoch 3587/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.7222 - accuracy: 0.5625 - val_loss: 3.2937 - val_accuracy: 0.1562\n",
"Epoch 3588/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.7144 - accuracy: 0.5000 - val_loss: 3.3462 - val_accuracy: 0.1562\n",
"Epoch 3589/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6493 - accuracy: 0.6562 - val_loss: 3.2036 - val_accuracy: 0.1875\n",
"Epoch 3590/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6732 - accuracy: 0.6250 - val_loss: 3.3840 - val_accuracy: 0.1875\n",
"Epoch 3591/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7278 - accuracy: 0.5938 - val_loss: 3.3067 - val_accuracy: 0.1562\n",
"Epoch 3592/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5790 - accuracy: 0.6250 - val_loss: 3.3423 - val_accuracy: 0.1875\n",
"Epoch 3593/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6432 - accuracy: 0.6562 - val_loss: 3.4791 - val_accuracy: 0.2188\n",
"Epoch 3594/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5975 - accuracy: 0.6250 - val_loss: 3.3973 - val_accuracy: 0.2188\n",
"Epoch 3595/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6377 - accuracy: 0.5625 - val_loss: 3.4032 - val_accuracy: 0.1875\n",
"Epoch 3596/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5598 - accuracy: 0.7188 - val_loss: 3.4126 - val_accuracy: 0.1562\n",
"Epoch 3597/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6655 - accuracy: 0.5938 - val_loss: 3.2962 - val_accuracy: 0.2188\n",
"Epoch 3598/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7027 - accuracy: 0.5312 - val_loss: 3.4550 - val_accuracy: 0.1875\n",
"Epoch 3599/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6668 - accuracy: 0.6250 - val_loss: 3.3961 - val_accuracy: 0.1875\n",
"Epoch 3600/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5749 - accuracy: 0.6250 - val_loss: 3.4337 - val_accuracy: 0.1875\n",
"Epoch 3601/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6363 - accuracy: 0.6250 - val_loss: 3.3478 - val_accuracy: 0.1562\n",
"Epoch 3602/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4641 - accuracy: 0.7500 - val_loss: 3.4007 - val_accuracy: 0.1562\n",
"Epoch 3603/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.6317 - accuracy: 0.6562 - val_loss: 3.3365 - val_accuracy: 0.1875\n",
"Epoch 3604/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 0.5314 - accuracy: 0.6562 - val_loss: 3.3708 - val_accuracy: 0.2188\n",
"Epoch 3605/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.5479 - accuracy: 0.7188 - val_loss: 3.3992 - val_accuracy: 0.1875\n",
"Epoch 3606/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5509 - accuracy: 0.6875 - val_loss: 3.4132 - val_accuracy: 0.1875\n",
"Epoch 3607/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5887 - accuracy: 0.7188 - val_loss: 3.4381 - val_accuracy: 0.1875\n",
"Epoch 3608/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5418 - accuracy: 0.7500 - val_loss: 3.3650 - val_accuracy: 0.1875\n",
"Epoch 3609/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5509 - accuracy: 0.6250 - val_loss: 3.4546 - val_accuracy: 0.2188\n",
"Epoch 3610/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.5932 - accuracy: 0.68 - 0s 172ms/step - loss: 0.5932 - accuracy: 0.6875 - val_loss: 3.4575 - val_accuracy: 0.2188\n",
"Epoch 3611/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5998 - accuracy: 0.6562 - val_loss: 3.4645 - val_accuracy: 0.1875\n",
"Epoch 3612/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4912 - accuracy: 0.6562 - val_loss: 3.5120 - val_accuracy: 0.1875\n",
"Epoch 3613/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5294 - accuracy: 0.6875 - val_loss: 3.3386 - val_accuracy: 0.1875\n",
"Epoch 3614/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6251 - accuracy: 0.6875 - val_loss: 3.5942 - val_accuracy: 0.1875\n",
"Epoch 3615/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6428 - accuracy: 0.6250 - val_loss: 3.3375 - val_accuracy: 0.2188\n",
"Epoch 3616/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5379 - accuracy: 0.5938 - val_loss: 3.5263 - val_accuracy: 0.1875\n",
"Epoch 3617/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5673 - accuracy: 0.7500 - val_loss: 3.3875 - val_accuracy: 0.2188\n",
"Epoch 3618/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5748 - accuracy: 0.6562 - val_loss: 3.3752 - val_accuracy: 0.1875\n",
"Epoch 3619/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5392 - accuracy: 0.6562 - val_loss: 3.5115 - val_accuracy: 0.1875\n",
"Epoch 3620/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6179 - accuracy: 0.5938 - val_loss: 3.3844 - val_accuracy: 0.1562\n",
"Epoch 3621/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5940 - accuracy: 0.6250 - val_loss: 3.3907 - val_accuracy: 0.1875\n",
"Epoch 3622/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4975 - accuracy: 0.7500 - val_loss: 3.4699 - val_accuracy: 0.1875\n",
"Epoch 3623/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4379 - accuracy: 0.7188 - val_loss: 3.4539 - val_accuracy: 0.1875\n",
"Epoch 3624/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5417 - accuracy: 0.6562 - val_loss: 3.4303 - val_accuracy: 0.1875\n",
"Epoch 3625/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5756 - accuracy: 0.5938 - val_loss: 3.4740 - val_accuracy: 0.1875\n",
"Epoch 3626/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.3518 - accuracy: 0.6562 - val_loss: 3.1204 - val_accuracy: 0.1875\n",
"Epoch 3627/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.8273 - accuracy: 0.5312 - val_loss: 3.8338 - val_accuracy: 0.1562\n",
"Epoch 3628/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.8260 - accuracy: 0.4688 - val_loss: 3.1681 - val_accuracy: 0.1562\n",
"Epoch 3629/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.7698 - accuracy: 0.4062 - val_loss: 3.7469 - val_accuracy: 0.1562\n",
"Epoch 3630/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8499 - accuracy: 0.5000 - val_loss: 3.2508 - val_accuracy: 0.1562\n",
"Epoch 3631/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6983 - accuracy: 0.5625 - val_loss: 3.6482 - val_accuracy: 0.1562\n",
"Epoch 3632/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5898 - accuracy: 0.6250 - val_loss: 3.3308 - val_accuracy: 0.1875\n",
"Epoch 3633/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5338 - accuracy: 0.6250 - val_loss: 3.3787 - val_accuracy: 0.1875\n",
"Epoch 3634/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5838 - accuracy: 0.5625 - val_loss: 3.4743 - val_accuracy: 0.1875\n",
"Epoch 3635/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5410 - accuracy: 0.7188 - val_loss: 3.4511 - val_accuracy: 0.1875\n",
"Epoch 3636/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.6226 - accuracy: 0.6875 - val_loss: 3.4252 - val_accuracy: 0.2188\n",
"Epoch 3637/5000\n",
"1/1 [==============================] - 0s 209ms/step - loss: 0.4785 - accuracy: 0.7812 - val_loss: 3.4534 - val_accuracy: 0.1875\n",
"Epoch 3638/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.4943 - accuracy: 0.7188 - val_loss: 3.4879 - val_accuracy: 0.1875\n",
"Epoch 3639/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6406 - accuracy: 0.6250 - val_loss: 3.4636 - val_accuracy: 0.1875\n",
"Epoch 3640/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5719 - accuracy: 0.5938 - val_loss: 3.4953 - val_accuracy: 0.2188\n",
"Epoch 3641/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5787 - accuracy: 0.7188 - val_loss: 3.4506 - val_accuracy: 0.1875\n",
"Epoch 3642/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4856 - accuracy: 0.7500 - val_loss: 3.5355 - val_accuracy: 0.1875\n",
"Epoch 3643/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5105 - accuracy: 0.6562 - val_loss: 3.3899 - val_accuracy: 0.2188\n",
"Epoch 3644/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7653 - accuracy: 0.5000 - val_loss: 3.7670 - val_accuracy: 0.2188\n",
"Epoch 3645/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6123 - accuracy: 0.6250 - val_loss: 3.5578 - val_accuracy: 0.2188\n",
"Epoch 3646/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5394 - accuracy: 0.6875 - val_loss: 3.5051 - val_accuracy: 0.2188\n",
"Epoch 3647/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6269 - accuracy: 0.5625 - val_loss: 3.6306 - val_accuracy: 0.1875\n",
"Epoch 3648/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4983 - accuracy: 0.6875 - val_loss: 3.5828 - val_accuracy: 0.2188\n",
"Epoch 3649/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4975 - accuracy: 0.7188 - val_loss: 3.6053 - val_accuracy: 0.1875\n",
"Epoch 3650/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5538 - accuracy: 0.6875 - val_loss: 3.5685 - val_accuracy: 0.2188\n",
"Epoch 3651/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5426 - accuracy: 0.6250 - val_loss: 3.5020 - val_accuracy: 0.2188\n",
"Epoch 3652/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.3848 - accuracy: 0.7500 - val_loss: 3.6021 - val_accuracy: 0.2188\n",
"Epoch 3653/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.4825 - accuracy: 0.8125 - val_loss: 3.4876 - val_accuracy: 0.1875\n",
"Epoch 3654/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5329 - accuracy: 0.7188 - val_loss: 3.6117 - val_accuracy: 0.2188\n",
"Epoch 3655/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4945 - accuracy: 0.7188 - val_loss: 3.4545 - val_accuracy: 0.1875\n",
"Epoch 3656/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5672 - accuracy: 0.6875 - val_loss: 3.6476 - val_accuracy: 0.2188\n",
"Epoch 3657/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6298 - accuracy: 0.62 - 0s 163ms/step - loss: 0.6298 - accuracy: 0.6250 - val_loss: 3.4941 - val_accuracy: 0.1875\n",
"Epoch 3658/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4941 - accuracy: 0.5938 - val_loss: 3.5697 - val_accuracy: 0.2188\n",
"Epoch 3659/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.4471 - accuracy: 0.7188 - val_loss: 3.6262 - val_accuracy: 0.2188\n",
"Epoch 3660/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7136 - accuracy: 0.6250 - val_loss: 3.5495 - val_accuracy: 0.2188\n",
"Epoch 3661/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4824 - accuracy: 0.7500 - val_loss: 3.5355 - val_accuracy: 0.2188\n",
"Epoch 3662/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5418 - accuracy: 0.7188 - val_loss: 3.6265 - val_accuracy: 0.2188\n",
"Epoch 3663/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.5077 - accuracy: 0.6250 - val_loss: 3.5795 - val_accuracy: 0.2188\n",
"Epoch 3664/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5560 - accuracy: 0.6250 - val_loss: 3.4974 - val_accuracy: 0.2188\n",
"Epoch 3665/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7036 - accuracy: 0.5625 - val_loss: 3.7454 - val_accuracy: 0.2188\n",
"Epoch 3666/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.5435 - accuracy: 0.6875 - val_loss: 3.5030 - val_accuracy: 0.2188\n",
"Epoch 3667/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.4316 - accuracy: 0.7188 - val_loss: 3.6036 - val_accuracy: 0.2188\n",
"Epoch 3668/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.4723 - accuracy: 0.7188 - val_loss: 3.5154 - val_accuracy: 0.2188\n",
"Epoch 3669/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5326 - accuracy: 0.7188 - val_loss: 3.6788 - val_accuracy: 0.2188\n",
"Epoch 3670/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6578 - accuracy: 0.6250 - val_loss: 3.5112 - val_accuracy: 0.1875\n",
"Epoch 3671/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5488 - accuracy: 0.6875 - val_loss: 3.8242 - val_accuracy: 0.1562\n",
"Epoch 3672/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5811 - accuracy: 0.6250 - val_loss: 3.5229 - val_accuracy: 0.1875\n",
"Epoch 3673/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5525 - accuracy: 0.6875 - val_loss: 3.6793 - val_accuracy: 0.2188\n",
"Epoch 3674/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6073 - accuracy: 0.7500 - val_loss: 3.5463 - val_accuracy: 0.2188\n",
"Epoch 3675/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.6876 - accuracy: 0.4688 - val_loss: 3.9034 - val_accuracy: 0.2188\n",
"Epoch 3676/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5768 - accuracy: 0.6562 - val_loss: 3.5429 - val_accuracy: 0.1875\n",
"Epoch 3677/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5729 - accuracy: 0.5938 - val_loss: 3.8450 - val_accuracy: 0.1875\n",
"Epoch 3678/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6134 - accuracy: 0.6875 - val_loss: 3.4327 - val_accuracy: 0.2188\n",
"Epoch 3679/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5996 - accuracy: 0.5000 - val_loss: 3.7758 - val_accuracy: 0.2188\n",
"Epoch 3680/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6610 - accuracy: 0.5938 - val_loss: 3.6193 - val_accuracy: 0.1875\n",
"Epoch 3681/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4591 - accuracy: 0.6250 - val_loss: 3.6278 - val_accuracy: 0.1875\n",
"Epoch 3682/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4664 - accuracy: 0.7812 - val_loss: 3.6705 - val_accuracy: 0.1875\n",
"Epoch 3683/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5627 - accuracy: 0.6250 - val_loss: 3.7079 - val_accuracy: 0.1875\n",
"Epoch 3684/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5564 - accuracy: 0.5625 - val_loss: 3.5077 - val_accuracy: 0.1562\n",
"Epoch 3685/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6109 - accuracy: 0.5938 - val_loss: 3.9201 - val_accuracy: 0.1875\n",
"Epoch 3686/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6046 - accuracy: 0.5938 - val_loss: 3.4652 - val_accuracy: 0.1875\n",
"Epoch 3687/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5889 - accuracy: 0.6250 - val_loss: 3.6985 - val_accuracy: 0.1875\n",
"Epoch 3688/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4758 - accuracy: 0.7188 - val_loss: 3.6024 - val_accuracy: 0.2188\n",
"Epoch 3689/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5208 - accuracy: 0.6875 - val_loss: 3.8458 - val_accuracy: 0.1875\n",
"Epoch 3690/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.5542 - accuracy: 0.6875 - val_loss: 3.4558 - val_accuracy: 0.1875\n",
"Epoch 3691/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6362 - accuracy: 0.6562 - val_loss: 3.8072 - val_accuracy: 0.2188\n",
"Epoch 3692/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5873 - accuracy: 0.6562 - val_loss: 3.5742 - val_accuracy: 0.1875\n",
"Epoch 3693/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4476 - accuracy: 0.6875 - val_loss: 3.7036 - val_accuracy: 0.1875\n",
"Epoch 3694/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5413 - accuracy: 0.6562 - val_loss: 3.5688 - val_accuracy: 0.1875\n",
"Epoch 3695/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5409 - accuracy: 0.5938 - val_loss: 3.6057 - val_accuracy: 0.1875\n",
"Epoch 3696/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5496 - accuracy: 0.6875 - val_loss: 3.7466 - val_accuracy: 0.1875\n",
"Epoch 3697/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.5451 - accuracy: 0.7500 - val_loss: 3.5973 - val_accuracy: 0.1875\n",
"Epoch 3698/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4952 - accuracy: 0.7812 - val_loss: 3.5869 - val_accuracy: 0.1875\n",
"Epoch 3699/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4992 - accuracy: 0.7500 - val_loss: 3.6365 - val_accuracy: 0.1875\n",
"Epoch 3700/5000\n",
"1/1 [==============================] - 0s 207ms/step - loss: 0.6163 - accuracy: 0.5625 - val_loss: 3.6123 - val_accuracy: 0.1875\n",
"Epoch 3701/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.4681 - accuracy: 0.6562 - val_loss: 3.7214 - val_accuracy: 0.1875\n",
"Epoch 3702/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9997 - accuracy: 0.6250 - val_loss: 3.6214 - val_accuracy: 0.2188\n",
"Epoch 3703/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.5472 - accuracy: 0.5938 - val_loss: 3.7703 - val_accuracy: 0.1875\n",
"Epoch 3704/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5322 - accuracy: 0.5938 - val_loss: 3.7298 - val_accuracy: 0.1875\n",
"Epoch 3705/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4788 - accuracy: 0.7188 - val_loss: 3.7178 - val_accuracy: 0.2188\n",
"Epoch 3706/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6125 - accuracy: 0.6562 - val_loss: 3.6964 - val_accuracy: 0.2188\n",
"Epoch 3707/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5357 - accuracy: 0.6250 - val_loss: 3.7612 - val_accuracy: 0.1875\n",
"Epoch 3708/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6003 - accuracy: 0.7188 - val_loss: 3.6305 - val_accuracy: 0.1875\n",
"Epoch 3709/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5134 - accuracy: 0.6562 - val_loss: 3.8866 - val_accuracy: 0.2188\n",
"Epoch 3710/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4970 - accuracy: 0.7500 - val_loss: 3.6237 - val_accuracy: 0.2188\n",
"Epoch 3711/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5025 - accuracy: 0.8125 - val_loss: 4.0063 - val_accuracy: 0.1875\n",
"Epoch 3712/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6338 - accuracy: 0.6562 - val_loss: 3.4935 - val_accuracy: 0.2188\n",
"Epoch 3713/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5830 - accuracy: 0.6250 - val_loss: 3.8865 - val_accuracy: 0.1875\n",
"Epoch 3714/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5955 - accuracy: 0.6875 - val_loss: 3.5799 - val_accuracy: 0.1875\n",
"Epoch 3715/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5651 - accuracy: 0.6250 - val_loss: 3.9864 - val_accuracy: 0.1562\n",
"Epoch 3716/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5161 - accuracy: 0.5312 - val_loss: 3.5939 - val_accuracy: 0.1875\n",
"Epoch 3717/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6560 - accuracy: 0.6562 - val_loss: 3.9715 - val_accuracy: 0.1562\n",
"Epoch 3718/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.7222 - accuracy: 0.5000 - val_loss: 3.6257 - val_accuracy: 0.2188\n",
"Epoch 3719/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6601 - accuracy: 0.5312 - val_loss: 3.7678 - val_accuracy: 0.1875\n",
"Epoch 3720/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5404 - accuracy: 0.6562 - val_loss: 3.5352 - val_accuracy: 0.1875\n",
"Epoch 3721/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4903 - accuracy: 0.6562 - val_loss: 3.6698 - val_accuracy: 0.2188\n",
"Epoch 3722/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4507 - accuracy: 0.7812 - val_loss: 3.7112 - val_accuracy: 0.1875\n",
"Epoch 3723/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4453 - accuracy: 0.6875 - val_loss: 3.7434 - val_accuracy: 0.1875\n",
"Epoch 3724/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4504 - accuracy: 0.8438 - val_loss: 3.6957 - val_accuracy: 0.1875\n",
"Epoch 3725/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5677 - accuracy: 0.6562 - val_loss: 3.8726 - val_accuracy: 0.1875\n",
"Epoch 3726/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6174 - accuracy: 0.4375 - val_loss: 3.5854 - val_accuracy: 0.2188\n",
"Epoch 3727/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5765 - accuracy: 0.6250 - val_loss: 3.6716 - val_accuracy: 0.2188\n",
"Epoch 3728/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5634 - accuracy: 0.6250 - val_loss: 3.5680 - val_accuracy: 0.1875\n",
"Epoch 3729/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.5589 - accuracy: 0.8125 - val_loss: 3.7778 - val_accuracy: 0.1875\n",
"Epoch 3730/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5004 - accuracy: 0.7188 - val_loss: 3.6530 - val_accuracy: 0.1875\n",
"Epoch 3731/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5659 - accuracy: 0.6562 - val_loss: 3.8696 - val_accuracy: 0.1562\n",
"Epoch 3732/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.6882 - accuracy: 0.5625 - val_loss: 3.7058 - val_accuracy: 0.2188\n",
"Epoch 3733/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.5834 - accuracy: 0.6250 - val_loss: 3.9456 - val_accuracy: 0.1875\n",
"Epoch 3734/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5948 - accuracy: 0.6250 - val_loss: 3.5489 - val_accuracy: 0.1875\n",
"Epoch 3735/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5849 - accuracy: 0.6250 - val_loss: 4.2536 - val_accuracy: 0.2188\n",
"Epoch 3736/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.7155 - accuracy: 0.5938 - val_loss: 3.4540 - val_accuracy: 0.1875\n",
"Epoch 3737/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6010 - accuracy: 0.6250 - val_loss: 4.0185 - val_accuracy: 0.1875\n",
"Epoch 3738/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5659 - accuracy: 0.6875 - val_loss: 3.6136 - val_accuracy: 0.2188\n",
"Epoch 3739/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6969 - accuracy: 0.6250 - val_loss: 3.7589 - val_accuracy: 0.1875\n",
"Epoch 3740/5000\n",
"1/1 [==============================] - 0s 209ms/step - loss: 0.5993 - accuracy: 0.6875 - val_loss: 3.7993 - val_accuracy: 0.1875\n",
"Epoch 3741/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5588 - accuracy: 0.6250 - val_loss: 3.6298 - val_accuracy: 0.2188\n",
"Epoch 3742/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5835 - accuracy: 0.5938 - val_loss: 3.7544 - val_accuracy: 0.1875\n",
"Epoch 3743/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5181 - accuracy: 0.7500 - val_loss: 3.5496 - val_accuracy: 0.1875\n",
"Epoch 3744/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7052 - accuracy: 0.5938 - val_loss: 3.7614 - val_accuracy: 0.1875\n",
"Epoch 3745/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.5011 - accuracy: 0.6562 - val_loss: 3.6310 - val_accuracy: 0.2188\n",
"Epoch 3746/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.4441 - accuracy: 0.6562 - val_loss: 3.7006 - val_accuracy: 0.2188\n",
"Epoch 3747/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5640 - accuracy: 0.7500 - val_loss: 3.6900 - val_accuracy: 0.2188\n",
"Epoch 3748/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4998 - accuracy: 0.6562 - val_loss: 3.5913 - val_accuracy: 0.2188\n",
"Epoch 3749/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5137 - accuracy: 0.7812 - val_loss: 3.7830 - val_accuracy: 0.1875\n",
"Epoch 3750/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5400 - accuracy: 0.6875 - val_loss: 3.6947 - val_accuracy: 0.2188\n",
"Epoch 3751/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5928 - accuracy: 0.6562 - val_loss: 3.9141 - val_accuracy: 0.1875\n",
"Epoch 3752/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5797 - accuracy: 0.6250 - val_loss: 3.5893 - val_accuracy: 0.1875\n",
"Epoch 3753/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5366 - accuracy: 0.5938 - val_loss: 3.9877 - val_accuracy: 0.1875\n",
"Epoch 3754/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6978 - accuracy: 0.5312 - val_loss: 3.4417 - val_accuracy: 0.1875\n",
"Epoch 3755/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.4787 - accuracy: 0.6875 - val_loss: 3.6864 - val_accuracy: 0.2188\n",
"Epoch 3756/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5412 - accuracy: 0.6250 - val_loss: 3.6416 - val_accuracy: 0.2188\n",
"Epoch 3757/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.4464 - accuracy: 0.6875 - val_loss: 3.6703 - val_accuracy: 0.1875\n",
"Epoch 3758/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5680 - accuracy: 0.5938 - val_loss: 4.0207 - val_accuracy: 0.1875\n",
"Epoch 3759/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6953 - accuracy: 0.6250 - val_loss: 3.4566 - val_accuracy: 0.1562\n",
"Epoch 3760/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6720 - accuracy: 0.5625 - val_loss: 4.4367 - val_accuracy: 0.1562\n",
"Epoch 3761/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.8931 - accuracy: 0.4062 - val_loss: 3.3141 - val_accuracy: 0.1250\n",
"Epoch 3762/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 2.9899 - accuracy: 0.4062 - val_loss: 28.6592 - val_accuracy: 0.0312\n",
"Epoch 3763/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 37.9601 - accuracy: 0.0312 - val_loss: 2.9029 - val_accuracy: 0.0312\n",
"Epoch 3764/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 3.9908 - accuracy: 0.0938 - val_loss: 2.7925 - val_accuracy: 0.0312\n",
"Epoch 3765/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.5082 - accuracy: 0.1875 - val_loss: 2.8712 - val_accuracy: 0.0312\n",
"Epoch 3766/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 3.8185 - accuracy: 0.0625 - val_loss: 2.8738 - val_accuracy: 0.0312\n",
"Epoch 3767/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.8743 - accuracy: 0.1250 - val_loss: 2.8000 - val_accuracy: 0.0312\n",
"Epoch 3768/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.9025 - accuracy: 0.0938 - val_loss: 2.6880 - val_accuracy: 0.0312\n",
"Epoch 3769/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.7257 - accuracy: 0.1562 - val_loss: 2.7228 - val_accuracy: 0.0312\n",
"Epoch 3770/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 2.5374 - accuracy: 0.1250 - val_loss: 2.7117 - val_accuracy: 0.0312\n",
"Epoch 3771/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 3.5820 - accuracy: 0.0312 - val_loss: 2.6647 - val_accuracy: 0.0312\n",
"Epoch 3772/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 2.3930 - accuracy: 0.1250 - val_loss: 2.5565 - val_accuracy: 0.0625\n",
"Epoch 3773/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 2.4248 - accuracy: 0.1250 - val_loss: 2.5777 - val_accuracy: 0.0625\n",
"Epoch 3774/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 2.1525 - accuracy: 0.1562 - val_loss: 2.6037 - val_accuracy: 0.0312\n",
"Epoch 3775/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 2.2078 - accuracy: 0.1562 - val_loss: 2.6574 - val_accuracy: 0.0000e+00\n",
"Epoch 3776/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 2.2127 - accuracy: 0.2500 - val_loss: 2.7113 - val_accuracy: 0.0000e+00\n",
"Epoch 3777/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 2.0256 - accuracy: 0.1562 - val_loss: 2.7050 - val_accuracy: 0.0312\n",
"Epoch 3778/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 2.1554 - accuracy: 0.2812 - val_loss: 2.6630 - val_accuracy: 0.0625\n",
"Epoch 3779/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.1874 - accuracy: 0.2812 - val_loss: 2.7240 - val_accuracy: 0.0625\n",
"Epoch 3780/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.8397 - accuracy: 0.3438 - val_loss: 2.8065 - val_accuracy: 0.0625\n",
"Epoch 3781/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.8268 - accuracy: 0.3438 - val_loss: 2.7569 - val_accuracy: 0.0938\n",
"Epoch 3782/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.0786 - accuracy: 0.3750 - val_loss: 2.7655 - val_accuracy: 0.0625\n",
"Epoch 3783/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 2.0206 - accuracy: 0.2500 - val_loss: 2.6897 - val_accuracy: 0.0938\n",
"Epoch 3784/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.9286 - accuracy: 0.2812 - val_loss: 2.7437 - val_accuracy: 0.0312\n",
"Epoch 3785/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.7711 - accuracy: 0.3750 - val_loss: 2.7756 - val_accuracy: 0.0312\n",
"Epoch 3786/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.8939 - accuracy: 0.3125 - val_loss: 2.7025 - val_accuracy: 0.0312\n",
"Epoch 3787/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.7883 - accuracy: 0.3750 - val_loss: 2.7313 - val_accuracy: 0.0000e+00\n",
"Epoch 3788/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.0000 - accuracy: 0.2188 - val_loss: 2.7168 - val_accuracy: 0.0312\n",
"Epoch 3789/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 2.0937 - accuracy: 0.4062 - val_loss: 2.7147 - val_accuracy: 0.0625\n",
"Epoch 3790/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.4874 - accuracy: 0.3750 - val_loss: 2.7482 - val_accuracy: 0.0312\n",
"Epoch 3791/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.7425 - accuracy: 0.3750 - val_loss: 2.9117 - val_accuracy: 0.0938\n",
"Epoch 3792/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 1.8128 - accuracy: 0.3438 - val_loss: 2.8464 - val_accuracy: 0.0625\n",
"Epoch 3793/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.8223 - accuracy: 0.3438 - val_loss: 2.7660 - val_accuracy: 0.0625\n",
"Epoch 3794/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.7240 - accuracy: 0.3750 - val_loss: 2.8195 - val_accuracy: 0.0938\n",
"Epoch 3795/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 1.7001 - accuracy: 0.2500 - val_loss: 2.8630 - val_accuracy: 0.1562\n",
"Epoch 3796/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.0086 - accuracy: 0.4688 - val_loss: 2.7768 - val_accuracy: 0.1250\n",
"Epoch 3797/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.7009 - accuracy: 0.3750 - val_loss: 2.8567 - val_accuracy: 0.1250\n",
"Epoch 3798/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.3238 - accuracy: 0.3125 - val_loss: 2.6674 - val_accuracy: 0.2188\n",
"Epoch 3799/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.2179 - accuracy: 0.4062 - val_loss: 2.6674 - val_accuracy: 0.2188\n",
"Epoch 3800/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.9524 - accuracy: 0.4375 - val_loss: 2.6588 - val_accuracy: 0.2188\n",
"Epoch 3801/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.0247 - accuracy: 0.3750 - val_loss: 2.6298 - val_accuracy: 0.2500\n",
"Epoch 3802/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.9452 - accuracy: 0.5312 - val_loss: 2.6052 - val_accuracy: 0.2500\n",
"Epoch 3803/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9610 - accuracy: 0.4688 - val_loss: 2.6204 - val_accuracy: 0.2500\n",
"Epoch 3804/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8683 - accuracy: 0.5938 - val_loss: 2.6150 - val_accuracy: 0.2812\n",
"Epoch 3805/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8915 - accuracy: 0.5625 - val_loss: 2.5779 - val_accuracy: 0.2812\n",
"Epoch 3806/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9823 - accuracy: 0.5312 - val_loss: 2.6144 - val_accuracy: 0.2812\n",
"Epoch 3807/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.8504 - accuracy: 0.5625 - val_loss: 2.5880 - val_accuracy: 0.2812\n",
"Epoch 3808/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8340 - accuracy: 0.5625 - val_loss: 2.5853 - val_accuracy: 0.2812\n",
"Epoch 3809/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.9419 - accuracy: 0.5938 - val_loss: 2.6528 - val_accuracy: 0.2812\n",
"Epoch 3810/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8839 - accuracy: 0.6562 - val_loss: 2.6785 - val_accuracy: 0.2812\n",
"Epoch 3811/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.8348 - accuracy: 0.5312 - val_loss: 2.6350 - val_accuracy: 0.2812\n",
"Epoch 3812/5000\n",
"1/1 [==============================] - 0s 235ms/step - loss: 0.8737 - accuracy: 0.5625 - val_loss: 2.6722 - val_accuracy: 0.2812\n",
"Epoch 3813/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.9584 - accuracy: 0.5000 - val_loss: 2.7298 - val_accuracy: 0.2188\n",
"Epoch 3814/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.8891 - accuracy: 0.5625 - val_loss: 2.7467 - val_accuracy: 0.2500\n",
"Epoch 3815/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.7953 - accuracy: 0.5000 - val_loss: 2.7408 - val_accuracy: 0.2500\n",
"Epoch 3816/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 0.7860 - accuracy: 0.5312 - val_loss: 2.7017 - val_accuracy: 0.2500\n",
"Epoch 3817/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.7919 - accuracy: 0.5938 - val_loss: 2.7434 - val_accuracy: 0.2500\n",
"Epoch 3818/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.9262 - accuracy: 0.5625 - val_loss: 2.8252 - val_accuracy: 0.2188\n",
"Epoch 3819/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.7368 - accuracy: 0.5312 - val_loss: 2.7812 - val_accuracy: 0.2500\n",
"Epoch 3820/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.7044 - accuracy: 0.6562 - val_loss: 2.7630 - val_accuracy: 0.2812\n",
"Epoch 3821/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.7117 - accuracy: 0.5938 - val_loss: 2.7669 - val_accuracy: 0.2500\n",
"Epoch 3822/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.8142 - accuracy: 0.6250 - val_loss: 2.8511 - val_accuracy: 0.2188\n",
"Epoch 3823/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.8151 - accuracy: 0.5000 - val_loss: 2.8422 - val_accuracy: 0.2188\n",
"Epoch 3824/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6401 - accuracy: 0.6250 - val_loss: 2.8016 - val_accuracy: 0.2500\n",
"Epoch 3825/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 1.1947 - accuracy: 0.6875 - val_loss: 2.9217 - val_accuracy: 0.2188\n",
"Epoch 3826/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7646 - accuracy: 0.6250 - val_loss: 2.8567 - val_accuracy: 0.2500\n",
"Epoch 3827/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.7175 - accuracy: 0.6250 - val_loss: 2.8424 - val_accuracy: 0.2500\n",
"Epoch 3828/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6575 - accuracy: 0.6250 - val_loss: 2.8379 - val_accuracy: 0.2500\n",
"Epoch 3829/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.7753 - accuracy: 0.4688 - val_loss: 2.8644 - val_accuracy: 0.2188\n",
"Epoch 3830/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.7491 - accuracy: 0.5938 - val_loss: 2.8508 - val_accuracy: 0.2188\n",
"Epoch 3831/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6955 - accuracy: 0.5000 - val_loss: 2.8454 - val_accuracy: 0.2188\n",
"Epoch 3832/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.6621 - accuracy: 0.7188 - val_loss: 2.9073 - val_accuracy: 0.2188\n",
"Epoch 3833/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8062 - accuracy: 0.5625 - val_loss: 2.9056 - val_accuracy: 0.2188\n",
"Epoch 3834/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6928 - accuracy: 0.6875 - val_loss: 2.9107 - val_accuracy: 0.2188\n",
"Epoch 3835/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6500 - accuracy: 0.6875 - val_loss: 2.8666 - val_accuracy: 0.2188\n",
"Epoch 3836/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6168 - accuracy: 0.6562 - val_loss: 2.8648 - val_accuracy: 0.2188\n",
"Epoch 3837/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6263 - accuracy: 0.6250 - val_loss: 2.8894 - val_accuracy: 0.2188\n",
"Epoch 3838/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7083 - accuracy: 0.6250 - val_loss: 2.8628 - val_accuracy: 0.2188\n",
"Epoch 3839/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6510 - accuracy: 0.5938 - val_loss: 2.9118 - val_accuracy: 0.2188\n",
"Epoch 3840/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6518 - accuracy: 0.7188 - val_loss: 2.8994 - val_accuracy: 0.2188\n",
"Epoch 3841/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6520 - accuracy: 0.5938 - val_loss: 2.9311 - val_accuracy: 0.2188\n",
"Epoch 3842/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7219 - accuracy: 0.5938 - val_loss: 3.0120 - val_accuracy: 0.2188\n",
"Epoch 3843/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5840 - accuracy: 0.6562 - val_loss: 2.9512 - val_accuracy: 0.2188\n",
"Epoch 3844/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5939 - accuracy: 0.6250 - val_loss: 2.9695 - val_accuracy: 0.2188\n",
"Epoch 3845/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7929 - accuracy: 0.6250 - val_loss: 3.1517 - val_accuracy: 0.1875\n",
"Epoch 3846/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6023 - accuracy: 0.7188 - val_loss: 3.0667 - val_accuracy: 0.2188\n",
"Epoch 3847/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5682 - accuracy: 0.7500 - val_loss: 3.0682 - val_accuracy: 0.2188\n",
"Epoch 3848/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5783 - accuracy: 0.6250 - val_loss: 3.0277 - val_accuracy: 0.2188\n",
"Epoch 3849/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6168 - accuracy: 0.6875 - val_loss: 3.0585 - val_accuracy: 0.2188\n",
"Epoch 3850/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6481 - accuracy: 0.6562 - val_loss: 3.0530 - val_accuracy: 0.2188\n",
"Epoch 3851/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6350 - accuracy: 0.6875 - val_loss: 3.0510 - val_accuracy: 0.2188\n",
"Epoch 3852/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5766 - accuracy: 0.6562 - val_loss: 2.9833 - val_accuracy: 0.2188\n",
"Epoch 3853/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7058 - accuracy: 0.6250 - val_loss: 3.1114 - val_accuracy: 0.2188\n",
"Epoch 3854/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6709 - accuracy: 0.6562 - val_loss: 3.0799 - val_accuracy: 0.2188\n",
"Epoch 3855/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.5751 - accuracy: 0.6562 - val_loss: 3.0999 - val_accuracy: 0.2188\n",
"Epoch 3856/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6348 - accuracy: 0.6250 - val_loss: 3.0747 - val_accuracy: 0.2188\n",
"Epoch 3857/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6655 - accuracy: 0.6250 - val_loss: 3.0672 - val_accuracy: 0.2188\n",
"Epoch 3858/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.9156 - accuracy: 0.6875 - val_loss: 3.1469 - val_accuracy: 0.2188\n",
"Epoch 3859/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5995 - accuracy: 0.6250 - val_loss: 3.1131 - val_accuracy: 0.2188\n",
"Epoch 3860/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.5486 - accuracy: 0.6875 - val_loss: 3.1389 - val_accuracy: 0.2188\n",
"Epoch 3861/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6084 - accuracy: 0.7188 - val_loss: 3.1426 - val_accuracy: 0.2188\n",
"Epoch 3862/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6060 - accuracy: 0.7188 - val_loss: 3.1156 - val_accuracy: 0.2188\n",
"Epoch 3863/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5553 - accuracy: 0.8125 - val_loss: 3.1306 - val_accuracy: 0.2188\n",
"Epoch 3864/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.6722 - accuracy: 0.6562 - val_loss: 3.1492 - val_accuracy: 0.2188\n",
"Epoch 3865/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.6251 - accuracy: 0.6562 - val_loss: 3.1089 - val_accuracy: 0.2188\n",
"Epoch 3866/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6124 - accuracy: 0.6250 - val_loss: 3.1128 - val_accuracy: 0.2188\n",
"Epoch 3867/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5912 - accuracy: 0.7188 - val_loss: 3.1128 - val_accuracy: 0.2188\n",
"Epoch 3868/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6693 - accuracy: 0.6562 - val_loss: 3.1696 - val_accuracy: 0.2188\n",
"Epoch 3869/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5569 - accuracy: 0.7188 - val_loss: 3.2123 - val_accuracy: 0.1875\n",
"Epoch 3870/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6380 - accuracy: 0.6562 - val_loss: 3.1452 - val_accuracy: 0.2188\n",
"Epoch 3871/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5588 - accuracy: 0.7188 - val_loss: 3.1378 - val_accuracy: 0.2188\n",
"Epoch 3872/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6568 - accuracy: 0.5938 - val_loss: 3.2033 - val_accuracy: 0.1562\n",
"Epoch 3873/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5552 - accuracy: 0.6562 - val_loss: 3.1587 - val_accuracy: 0.1875\n",
"Epoch 3874/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6093 - accuracy: 0.6875 - val_loss: 3.1893 - val_accuracy: 0.1875\n",
"Epoch 3875/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5039 - accuracy: 0.7500 - val_loss: 3.2148 - val_accuracy: 0.1875\n",
"Epoch 3876/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6569 - accuracy: 0.5938 - val_loss: 3.2013 - val_accuracy: 0.1562\n",
"Epoch 3877/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4559 - accuracy: 0.7500 - val_loss: 3.1088 - val_accuracy: 0.2188\n",
"Epoch 3878/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5578 - accuracy: 0.7188 - val_loss: 3.1731 - val_accuracy: 0.1562\n",
"Epoch 3879/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5436 - accuracy: 0.6875 - val_loss: 3.2122 - val_accuracy: 0.1875\n",
"Epoch 3880/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6284 - accuracy: 0.6250 - val_loss: 3.1439 - val_accuracy: 0.1562\n",
"Epoch 3881/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5136 - accuracy: 0.6875 - val_loss: 3.1440 - val_accuracy: 0.1562\n",
"Epoch 3882/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5158 - accuracy: 0.7500 - val_loss: 3.2015 - val_accuracy: 0.1562\n",
"Epoch 3883/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5055 - accuracy: 0.7500 - val_loss: 3.2058 - val_accuracy: 0.1875\n",
"Epoch 3884/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6478 - accuracy: 0.5938 - val_loss: 3.2189 - val_accuracy: 0.1562\n",
"Epoch 3885/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5429 - accuracy: 0.6875 - val_loss: 3.2706 - val_accuracy: 0.1875\n",
"Epoch 3886/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6276 - accuracy: 0.7188 - val_loss: 3.2603 - val_accuracy: 0.1875\n",
"Epoch 3887/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5401 - accuracy: 0.7812 - val_loss: 3.2112 - val_accuracy: 0.1562\n",
"Epoch 3888/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5101 - accuracy: 0.7188 - val_loss: 3.2185 - val_accuracy: 0.1562\n",
"Epoch 3889/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5636 - accuracy: 0.7188 - val_loss: 3.1432 - val_accuracy: 0.1562\n",
"Epoch 3890/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4726 - accuracy: 0.7188 - val_loss: 3.1871 - val_accuracy: 0.1562\n",
"Epoch 3891/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6319 - accuracy: 0.5312 - val_loss: 3.1996 - val_accuracy: 0.1562\n",
"Epoch 3892/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5339 - accuracy: 0.7500 - val_loss: 3.2656 - val_accuracy: 0.1562\n",
"Epoch 3893/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5482 - accuracy: 0.7188 - val_loss: 3.1769 - val_accuracy: 0.1562\n",
"Epoch 3894/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5997 - accuracy: 0.7188 - val_loss: 3.2101 - val_accuracy: 0.1562\n",
"Epoch 3895/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5536 - accuracy: 0.6562 - val_loss: 3.3299 - val_accuracy: 0.1875\n",
"Epoch 3896/5000\n",
"1/1 [==============================] - 0s 151ms/step - loss: 0.5703 - accuracy: 0.6562 - val_loss: 3.2758 - val_accuracy: 0.1875\n",
"Epoch 3897/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5446 - accuracy: 0.8125 - val_loss: 3.2527 - val_accuracy: 0.2188\n",
"Epoch 3898/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4773 - accuracy: 0.7500 - val_loss: 3.3092 - val_accuracy: 0.1875\n",
"Epoch 3899/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5486 - accuracy: 0.6875 - val_loss: 3.2592 - val_accuracy: 0.1875\n",
"Epoch 3900/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5838 - accuracy: 0.5938 - val_loss: 3.3754 - val_accuracy: 0.1875\n",
"Epoch 3901/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5826 - accuracy: 0.6562 - val_loss: 3.2477 - val_accuracy: 0.1875\n",
"Epoch 3902/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6079 - accuracy: 0.6875 - val_loss: 3.2705 - val_accuracy: 0.2188\n",
"Epoch 3903/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5604 - accuracy: 0.6562 - val_loss: 3.2801 - val_accuracy: 0.2188\n",
"Epoch 3904/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4990 - accuracy: 0.7188 - val_loss: 3.3721 - val_accuracy: 0.1875\n",
"Epoch 3905/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5763 - accuracy: 0.7500 - val_loss: 3.2306 - val_accuracy: 0.1875\n",
"Epoch 3906/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5302 - accuracy: 0.7500 - val_loss: 3.2919 - val_accuracy: 0.2188\n",
"Epoch 3907/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4564 - accuracy: 0.7812 - val_loss: 3.3139 - val_accuracy: 0.2188\n",
"Epoch 3908/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5992 - accuracy: 0.5938 - val_loss: 3.2653 - val_accuracy: 0.1875\n",
"Epoch 3909/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6040 - accuracy: 0.6562 - val_loss: 3.3098 - val_accuracy: 0.2188\n",
"Epoch 3910/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6192 - accuracy: 0.6250 - val_loss: 3.3117 - val_accuracy: 0.1875\n",
"Epoch 3911/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5672 - accuracy: 0.5938 - val_loss: 3.3113 - val_accuracy: 0.1875\n",
"Epoch 3912/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5685 - accuracy: 0.5938 - val_loss: 3.3246 - val_accuracy: 0.2188\n",
"Epoch 3913/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5432 - accuracy: 0.6250 - val_loss: 3.2923 - val_accuracy: 0.2188\n",
"Epoch 3914/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6372 - accuracy: 0.5938 - val_loss: 3.3769 - val_accuracy: 0.1875\n",
"Epoch 3915/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6309 - accuracy: 0.6562 - val_loss: 3.2951 - val_accuracy: 0.2188\n",
"Epoch 3916/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5199 - accuracy: 0.7188 - val_loss: 3.2972 - val_accuracy: 0.2188\n",
"Epoch 3917/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5310 - accuracy: 0.6562 - val_loss: 3.2937 - val_accuracy: 0.1875\n",
"Epoch 3918/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5123 - accuracy: 0.7500 - val_loss: 3.2683 - val_accuracy: 0.2188\n",
"Epoch 3919/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5411 - accuracy: 0.6875 - val_loss: 3.3814 - val_accuracy: 0.1875\n",
"Epoch 3920/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5747 - accuracy: 0.6562 - val_loss: 3.3415 - val_accuracy: 0.2188\n",
"Epoch 3921/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4828 - accuracy: 0.6562 - val_loss: 3.3186 - val_accuracy: 0.2188\n",
"Epoch 3922/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7165 - accuracy: 0.6562 - val_loss: 3.3531 - val_accuracy: 0.2188\n",
"Epoch 3923/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5227 - accuracy: 0.6875 - val_loss: 3.3767 - val_accuracy: 0.2188\n",
"Epoch 3924/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5823 - accuracy: 0.6250 - val_loss: 3.3916 - val_accuracy: 0.1875\n",
"Epoch 3925/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.5500 - accuracy: 0.6562 - val_loss: 3.3728 - val_accuracy: 0.2188\n",
"Epoch 3926/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5270 - accuracy: 0.6562 - val_loss: 3.3268 - val_accuracy: 0.1875\n",
"Epoch 3927/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5952 - accuracy: 0.6562 - val_loss: 3.5383 - val_accuracy: 0.1562\n",
"Epoch 3928/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5837 - accuracy: 0.6250 - val_loss: 3.3068 - val_accuracy: 0.1875\n",
"Epoch 3929/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5563 - accuracy: 0.6562 - val_loss: 3.3681 - val_accuracy: 0.2188\n",
"Epoch 3930/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5426 - accuracy: 0.5938 - val_loss: 3.3245 - val_accuracy: 0.2188\n",
"Epoch 3931/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4943 - accuracy: 0.6562 - val_loss: 3.5341 - val_accuracy: 0.1875\n",
"Epoch 3932/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6139 - accuracy: 0.6562 - val_loss: 3.3517 - val_accuracy: 0.1875\n",
"Epoch 3933/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5604 - accuracy: 0.5312 - val_loss: 3.4216 - val_accuracy: 0.1875\n",
"Epoch 3934/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5440 - accuracy: 0.6562 - val_loss: 3.2719 - val_accuracy: 0.1875\n",
"Epoch 3935/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5398 - accuracy: 0.7188 - val_loss: 3.4534 - val_accuracy: 0.2188\n",
"Epoch 3936/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6209 - accuracy: 0.5938 - val_loss: 3.3040 - val_accuracy: 0.1875\n",
"Epoch 3937/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6557 - accuracy: 0.6875 - val_loss: 3.5759 - val_accuracy: 0.1875\n",
"Epoch 3938/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5572 - accuracy: 0.6250 - val_loss: 3.3338 - val_accuracy: 0.1875\n",
"Epoch 3939/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5221 - accuracy: 0.6875 - val_loss: 3.4248 - val_accuracy: 0.2188\n",
"Epoch 3940/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5656 - accuracy: 0.6562 - val_loss: 3.3743 - val_accuracy: 0.1875\n",
"Epoch 3941/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.4928 - accuracy: 0.6562 - val_loss: 3.3700 - val_accuracy: 0.1875\n",
"Epoch 3942/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4651 - accuracy: 0.7188 - val_loss: 3.4236 - val_accuracy: 0.2188\n",
"Epoch 3943/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5702 - accuracy: 0.5312 - val_loss: 3.4929 - val_accuracy: 0.1875\n",
"Epoch 3944/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6076 - accuracy: 0.6562 - val_loss: 3.3502 - val_accuracy: 0.1875\n",
"Epoch 3945/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5277 - accuracy: 0.6875 - val_loss: 3.4919 - val_accuracy: 0.1875\n",
"Epoch 3946/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6552 - accuracy: 0.7188 - val_loss: 3.2968 - val_accuracy: 0.1875\n",
"Epoch 3947/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6483 - accuracy: 0.5938 - val_loss: 3.6466 - val_accuracy: 0.2188\n",
"Epoch 3948/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6008 - accuracy: 0.6562 - val_loss: 3.3428 - val_accuracy: 0.1875\n",
"Epoch 3949/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.6293 - accuracy: 0.5625 - val_loss: 3.5646 - val_accuracy: 0.1875\n",
"Epoch 3950/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5009 - accuracy: 0.6562 - val_loss: 3.3929 - val_accuracy: 0.1562\n",
"Epoch 3951/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6117 - accuracy: 0.6250 - val_loss: 3.4239 - val_accuracy: 0.2188\n",
"Epoch 3952/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.5479 - accuracy: 0.6250 - val_loss: 3.4318 - val_accuracy: 0.1875\n",
"Epoch 3953/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.7116 - accuracy: 0.5312 - val_loss: 3.3778 - val_accuracy: 0.2188\n",
"Epoch 3954/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.5486 - accuracy: 0.6562 - val_loss: 3.3609 - val_accuracy: 0.2188\n",
"Epoch 3955/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5383 - accuracy: 0.7812 - val_loss: 3.3887 - val_accuracy: 0.1875\n",
"Epoch 3956/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5545 - accuracy: 0.6875 - val_loss: 3.5138 - val_accuracy: 0.1875\n",
"Epoch 3957/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5032 - accuracy: 0.6562 - val_loss: 3.3394 - val_accuracy: 0.1875\n",
"Epoch 3958/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5132 - accuracy: 0.7188 - val_loss: 3.4442 - val_accuracy: 0.1875\n",
"Epoch 3959/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6055 - accuracy: 0.6562 - val_loss: 3.3718 - val_accuracy: 0.1875\n",
"Epoch 3960/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4952 - accuracy: 0.7812 - val_loss: 3.4444 - val_accuracy: 0.1875\n",
"Epoch 3961/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5765 - accuracy: 0.6562 - val_loss: 3.3740 - val_accuracy: 0.1875\n",
"Epoch 3962/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6187 - accuracy: 0.5625 - val_loss: 3.4943 - val_accuracy: 0.1875\n",
"Epoch 3963/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5401 - accuracy: 0.7188 - val_loss: 3.4001 - val_accuracy: 0.1875\n",
"Epoch 3964/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5431 - accuracy: 0.7500 - val_loss: 3.4552 - val_accuracy: 0.1875\n",
"Epoch 3965/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5545 - accuracy: 0.5938 - val_loss: 3.4210 - val_accuracy: 0.1875\n",
"Epoch 3966/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5132 - accuracy: 0.6875 - val_loss: 3.4435 - val_accuracy: 0.1875\n",
"Epoch 3967/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5180 - accuracy: 0.7188 - val_loss: 3.4442 - val_accuracy: 0.2188\n",
"Epoch 3968/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4567 - accuracy: 0.6562 - val_loss: 3.3614 - val_accuracy: 0.2188\n",
"Epoch 3969/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5043 - accuracy: 0.7188 - val_loss: 3.4435 - val_accuracy: 0.1875\n",
"Epoch 3970/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5147 - accuracy: 0.6250 - val_loss: 3.3976 - val_accuracy: 0.1875\n",
"Epoch 3971/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.4352 - accuracy: 0.7812 - val_loss: 3.4651 - val_accuracy: 0.1875\n",
"Epoch 3972/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4841 - accuracy: 0.6875 - val_loss: 3.5252 - val_accuracy: 0.1875\n",
"Epoch 3973/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4263 - accuracy: 0.7500 - val_loss: 3.4409 - val_accuracy: 0.1875\n",
"Epoch 3974/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4906 - accuracy: 0.6875 - val_loss: 3.3902 - val_accuracy: 0.1875\n",
"Epoch 3975/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5756 - accuracy: 0.6562 - val_loss: 3.4603 - val_accuracy: 0.2188\n",
"Epoch 3976/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5564 - accuracy: 0.6250 - val_loss: 3.4700 - val_accuracy: 0.1875\n",
"Epoch 3977/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4274 - accuracy: 0.7500 - val_loss: 3.4783 - val_accuracy: 0.2188\n",
"Epoch 3978/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4788 - accuracy: 0.6875 - val_loss: 3.5821 - val_accuracy: 0.1875\n",
"Epoch 3979/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4765 - accuracy: 0.7500 - val_loss: 3.5100 - val_accuracy: 0.2188\n",
"Epoch 3980/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6456 - accuracy: 0.6250 - val_loss: 3.4046 - val_accuracy: 0.2188\n",
"Epoch 3981/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6086 - accuracy: 0.6562 - val_loss: 3.5943 - val_accuracy: 0.1875\n",
"Epoch 3982/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.5471 - accuracy: 0.6562 - val_loss: 3.2332 - val_accuracy: 0.1875\n",
"Epoch 3983/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6185 - accuracy: 0.7188 - val_loss: 3.5501 - val_accuracy: 0.1875\n",
"Epoch 3984/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5064 - accuracy: 0.6562 - val_loss: 3.4737 - val_accuracy: 0.2188\n",
"Epoch 3985/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5592 - accuracy: 0.7188 - val_loss: 3.5082 - val_accuracy: 0.2188\n",
"Epoch 3986/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5179 - accuracy: 0.6875 - val_loss: 3.5342 - val_accuracy: 0.1875\n",
"Epoch 3987/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6111 - accuracy: 0.6875 - val_loss: 3.5356 - val_accuracy: 0.1875\n",
"Epoch 3988/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5844 - accuracy: 0.6250 - val_loss: 3.4748 - val_accuracy: 0.1562\n",
"Epoch 3989/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4936 - accuracy: 0.6875 - val_loss: 3.7116 - val_accuracy: 0.1875\n",
"Epoch 3990/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7200 - accuracy: 0.5938 - val_loss: 3.3472 - val_accuracy: 0.1875\n",
"Epoch 3991/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6299 - accuracy: 0.5938 - val_loss: 3.7727 - val_accuracy: 0.1875\n",
"Epoch 3992/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6958 - accuracy: 0.4375 - val_loss: 3.3097 - val_accuracy: 0.1875\n",
"Epoch 3993/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5556 - accuracy: 0.6875 - val_loss: 3.6925 - val_accuracy: 0.1875\n",
"Epoch 3994/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6801 - accuracy: 0.5938 - val_loss: 3.3665 - val_accuracy: 0.2188\n",
"Epoch 3995/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6744 - accuracy: 0.6562 - val_loss: 3.6903 - val_accuracy: 0.1875\n",
"Epoch 3996/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6260 - accuracy: 0.6250 - val_loss: 3.4817 - val_accuracy: 0.1562\n",
"Epoch 3997/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4990 - accuracy: 0.6875 - val_loss: 3.5543 - val_accuracy: 0.1875\n",
"Epoch 3998/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4525 - accuracy: 0.6250 - val_loss: 3.5447 - val_accuracy: 0.2188\n",
"Epoch 3999/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5336 - accuracy: 0.5938 - val_loss: 3.6053 - val_accuracy: 0.1875\n",
"Epoch 4000/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4866 - accuracy: 0.7188 - val_loss: 3.5524 - val_accuracy: 0.1875\n",
"Epoch 4001/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4244 - accuracy: 0.7812 - val_loss: 3.5189 - val_accuracy: 0.1875\n",
"Epoch 4002/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6514 - accuracy: 0.6250 - val_loss: 3.6175 - val_accuracy: 0.1875\n",
"Epoch 4003/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5924 - accuracy: 0.6250 - val_loss: 3.4291 - val_accuracy: 0.1562\n",
"Epoch 4004/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5697 - accuracy: 0.6875 - val_loss: 3.6390 - val_accuracy: 0.1875\n",
"Epoch 4005/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5961 - accuracy: 0.7188 - val_loss: 3.4288 - val_accuracy: 0.1562\n",
"Epoch 4006/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.5740 - accuracy: 0.6875 - val_loss: 3.5782 - val_accuracy: 0.1875\n",
"Epoch 4007/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4365 - accuracy: 0.7500 - val_loss: 3.5020 - val_accuracy: 0.1875\n",
"Epoch 4008/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5269 - accuracy: 0.7188 - val_loss: 3.5869 - val_accuracy: 0.1875\n",
"Epoch 4009/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5964 - accuracy: 0.5938 - val_loss: 3.4143 - val_accuracy: 0.1875\n",
"Epoch 4010/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5066 - accuracy: 0.6250 - val_loss: 3.6105 - val_accuracy: 0.1875\n",
"Epoch 4011/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.6136 - accuracy: 0.6875 - val_loss: 3.4823 - val_accuracy: 0.1875\n",
"Epoch 4012/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6172 - accuracy: 0.6250 - val_loss: 3.9193 - val_accuracy: 0.2188\n",
"Epoch 4013/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.6233 - accuracy: 0.5625 - val_loss: 3.4542 - val_accuracy: 0.1875\n",
"Epoch 4014/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.5115 - accuracy: 0.6562 - val_loss: 3.7544 - val_accuracy: 0.2188\n",
"Epoch 4015/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5837 - accuracy: 0.5938 - val_loss: 3.3994 - val_accuracy: 0.1875\n",
"Epoch 4016/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5369 - accuracy: 0.6562 - val_loss: 3.6969 - val_accuracy: 0.1875\n",
"Epoch 4017/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6205 - accuracy: 0.5000 - val_loss: 3.4783 - val_accuracy: 0.2188\n",
"Epoch 4018/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5189 - accuracy: 0.6250 - val_loss: 3.5253 - val_accuracy: 0.2188\n",
"Epoch 4019/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5711 - accuracy: 0.6875 - val_loss: 3.4988 - val_accuracy: 0.1875\n",
"Epoch 4020/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5709 - accuracy: 0.6250 - val_loss: 3.3932 - val_accuracy: 0.1875\n",
"Epoch 4021/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.4670 - accuracy: 0.8125 - val_loss: 3.5701 - val_accuracy: 0.1875\n",
"Epoch 4022/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5581 - accuracy: 0.6562 - val_loss: 3.4646 - val_accuracy: 0.2188\n",
"Epoch 4023/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4574 - accuracy: 0.6250 - val_loss: 3.6073 - val_accuracy: 0.1875\n",
"Epoch 4024/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.3935 - accuracy: 0.8125 - val_loss: 3.4811 - val_accuracy: 0.1875\n",
"Epoch 4025/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5559 - accuracy: 0.7188 - val_loss: 3.6630 - val_accuracy: 0.1875\n",
"Epoch 4026/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.4053 - accuracy: 0.7188 - val_loss: 3.5321 - val_accuracy: 0.1562\n",
"Epoch 4027/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5380 - accuracy: 0.5625 - val_loss: 3.5459 - val_accuracy: 0.1875\n",
"Epoch 4028/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4837 - accuracy: 0.7500 - val_loss: 3.5722 - val_accuracy: 0.1875\n",
"Epoch 4029/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5176 - accuracy: 0.6562 - val_loss: 3.6161 - val_accuracy: 0.1875\n",
"Epoch 4030/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6028 - accuracy: 0.5625 - val_loss: 3.5477 - val_accuracy: 0.2188\n",
"Epoch 4031/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5656 - accuracy: 0.6562 - val_loss: 3.5794 - val_accuracy: 0.2188\n",
"Epoch 4032/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.6075 - accuracy: 0.7500 - val_loss: 3.5087 - val_accuracy: 0.1875\n",
"Epoch 4033/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4982 - accuracy: 0.6562 - val_loss: 3.6661 - val_accuracy: 0.1875\n",
"Epoch 4034/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5131 - accuracy: 0.7188 - val_loss: 3.6263 - val_accuracy: 0.2188\n",
"Epoch 4035/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5278 - accuracy: 0.6875 - val_loss: 3.6066 - val_accuracy: 0.2188\n",
"Epoch 4036/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4618 - accuracy: 0.7500 - val_loss: 3.6313 - val_accuracy: 0.2188\n",
"Epoch 4037/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.4600 - accuracy: 0.7188 - val_loss: 3.5366 - val_accuracy: 0.2188\n",
"Epoch 4038/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6078 - accuracy: 0.5312 - val_loss: 3.6264 - val_accuracy: 0.1875\n",
"Epoch 4039/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5299 - accuracy: 0.6875 - val_loss: 3.5963 - val_accuracy: 0.2188\n",
"Epoch 4040/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5627 - accuracy: 0.7188 - val_loss: 3.6891 - val_accuracy: 0.1875\n",
"Epoch 4041/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5102 - accuracy: 0.6250 - val_loss: 3.6416 - val_accuracy: 0.2188\n",
"Epoch 4042/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.4992 - accuracy: 0.6250 - val_loss: 3.6133 - val_accuracy: 0.1875\n",
"Epoch 4043/5000\n",
"1/1 [==============================] - 0s 215ms/step - loss: 0.5662 - accuracy: 0.6562 - val_loss: 3.8114 - val_accuracy: 0.1875\n",
"Epoch 4044/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.5982 - accuracy: 0.6562 - val_loss: 3.5255 - val_accuracy: 0.1875\n",
"Epoch 4045/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5470 - accuracy: 0.6562 - val_loss: 3.6878 - val_accuracy: 0.1875\n",
"Epoch 4046/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6546 - accuracy: 0.6562 - val_loss: 3.5481 - val_accuracy: 0.2188\n",
"Epoch 4047/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.4582 - accuracy: 0.7188 - val_loss: 3.6233 - val_accuracy: 0.1875\n",
"Epoch 4048/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5088 - accuracy: 0.5938 - val_loss: 3.5035 - val_accuracy: 0.1875\n",
"Epoch 4049/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4835 - accuracy: 0.6250 - val_loss: 3.8595 - val_accuracy: 0.1562\n",
"Epoch 4050/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5174 - accuracy: 0.5938 - val_loss: 3.5009 - val_accuracy: 0.2188\n",
"Epoch 4051/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5580 - accuracy: 0.6875 - val_loss: 3.8223 - val_accuracy: 0.1562\n",
"Epoch 4052/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6351 - accuracy: 0.5312 - val_loss: 3.4633 - val_accuracy: 0.1875\n",
"Epoch 4053/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5642 - accuracy: 0.6562 - val_loss: 3.9120 - val_accuracy: 0.1875\n",
"Epoch 4054/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6110 - accuracy: 0.6250 - val_loss: 3.5191 - val_accuracy: 0.1875\n",
"Epoch 4055/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6484 - accuracy: 0.5625 - val_loss: 3.9285 - val_accuracy: 0.1875\n",
"Epoch 4056/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6407 - accuracy: 0.5625 - val_loss: 3.5648 - val_accuracy: 0.2188\n",
"Epoch 4057/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5467 - accuracy: 0.6875 - val_loss: 3.6603 - val_accuracy: 0.1875\n",
"Epoch 4058/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5333 - accuracy: 0.6875 - val_loss: 3.4765 - val_accuracy: 0.1875\n",
"Epoch 4059/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6244 - accuracy: 0.7188 - val_loss: 3.8347 - val_accuracy: 0.1562\n",
"Epoch 4060/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5707 - accuracy: 0.6875 - val_loss: 3.4247 - val_accuracy: 0.1875\n",
"Epoch 4061/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6048 - accuracy: 0.6562 - val_loss: 3.9400 - val_accuracy: 0.2188\n",
"Epoch 4062/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5190 - accuracy: 0.6250 - val_loss: 3.5281 - val_accuracy: 0.1875\n",
"Epoch 4063/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5967 - accuracy: 0.5312 - val_loss: 3.6024 - val_accuracy: 0.2188\n",
"Epoch 4064/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4335 - accuracy: 0.7812 - val_loss: 3.5871 - val_accuracy: 0.2188\n",
"Epoch 4065/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4708 - accuracy: 0.6562 - val_loss: 3.6867 - val_accuracy: 0.1875\n",
"Epoch 4066/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.4073 - accuracy: 0.8438 - val_loss: 3.6053 - val_accuracy: 0.2188\n",
"Epoch 4067/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5527 - accuracy: 0.6250 - val_loss: 3.6905 - val_accuracy: 0.2188\n",
"Epoch 4068/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5354 - accuracy: 0.6875 - val_loss: 3.6122 - val_accuracy: 0.1875\n",
"Epoch 4069/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.4960 - accuracy: 0.7188 - val_loss: 3.6243 - val_accuracy: 0.2188\n",
"Epoch 4070/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5707 - accuracy: 0.5000 - val_loss: 3.6637 - val_accuracy: 0.1875\n",
"Epoch 4071/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.4867 - accuracy: 0.6875 - val_loss: 3.6349 - val_accuracy: 0.1875\n",
"Epoch 4072/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4523 - accuracy: 0.6562 - val_loss: 3.5801 - val_accuracy: 0.2188\n",
"Epoch 4073/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4440 - accuracy: 0.7812 - val_loss: 3.7109 - val_accuracy: 0.1875\n",
"Epoch 4074/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5158 - accuracy: 0.6875 - val_loss: 3.7306 - val_accuracy: 0.1875\n",
"Epoch 4075/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5563 - accuracy: 0.6250 - val_loss: 3.6216 - val_accuracy: 0.1875\n",
"Epoch 4076/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.4204 - accuracy: 0.7188 - val_loss: 3.6387 - val_accuracy: 0.2188\n",
"Epoch 4077/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4504 - accuracy: 0.6875 - val_loss: 3.8092 - val_accuracy: 0.1875\n",
"Epoch 4078/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5797 - accuracy: 0.5625 - val_loss: 3.6628 - val_accuracy: 0.2188\n",
"Epoch 4079/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6105 - accuracy: 0.5938 - val_loss: 3.9594 - val_accuracy: 0.1875\n",
"Epoch 4080/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6420 - accuracy: 0.5312 - val_loss: 3.4115 - val_accuracy: 0.2188\n",
"Epoch 4081/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5407 - accuracy: 0.6250 - val_loss: 3.9405 - val_accuracy: 0.1875\n",
"Epoch 4082/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5979 - accuracy: 0.5312 - val_loss: 3.5358 - val_accuracy: 0.1875\n",
"Epoch 4083/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6746 - accuracy: 0.6562 - val_loss: 4.0978 - val_accuracy: 0.2500\n",
"Epoch 4084/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6956 - accuracy: 0.5938 - val_loss: 3.3675 - val_accuracy: 0.1875\n",
"Epoch 4085/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6320 - accuracy: 0.6562 - val_loss: 3.7699 - val_accuracy: 0.1875\n",
"Epoch 4086/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5358 - accuracy: 0.6250 - val_loss: 3.5454 - val_accuracy: 0.1562\n",
"Epoch 4087/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6326 - accuracy: 0.5625 - val_loss: 3.5359 - val_accuracy: 0.1875\n",
"Epoch 4088/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.5582 - accuracy: 0.6875 - val_loss: 3.6768 - val_accuracy: 0.1875\n",
"Epoch 4089/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5352 - accuracy: 0.6875 - val_loss: 3.5891 - val_accuracy: 0.1875\n",
"Epoch 4090/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5295 - accuracy: 0.5938 - val_loss: 3.7567 - val_accuracy: 0.1875\n",
"Epoch 4091/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5269 - accuracy: 0.5938 - val_loss: 3.6523 - val_accuracy: 0.1875\n",
"Epoch 4092/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6442 - accuracy: 0.5938 - val_loss: 3.6296 - val_accuracy: 0.1875\n",
"Epoch 4093/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5578 - accuracy: 0.8125 - val_loss: 3.5099 - val_accuracy: 0.1875\n",
"Epoch 4094/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4654 - accuracy: 0.7188 - val_loss: 3.6729 - val_accuracy: 0.1875\n",
"Epoch 4095/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.8763 - accuracy: 0.6250 - val_loss: 3.7464 - val_accuracy: 0.2188\n",
"Epoch 4096/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5149 - accuracy: 0.6250 - val_loss: 3.6067 - val_accuracy: 0.2188\n",
"Epoch 4097/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6011 - accuracy: 0.5938 - val_loss: 3.8539 - val_accuracy: 0.1875\n",
"Epoch 4098/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5485 - accuracy: 0.5938 - val_loss: 3.5896 - val_accuracy: 0.1875\n",
"Epoch 4099/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5197 - accuracy: 0.6562 - val_loss: 3.7052 - val_accuracy: 0.1875\n",
"Epoch 4100/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5674 - accuracy: 0.6250 - val_loss: 3.6987 - val_accuracy: 0.2188\n",
"Epoch 4101/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6218 - accuracy: 0.6875 - val_loss: 3.6865 - val_accuracy: 0.1875\n",
"Epoch 4102/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.4288 - accuracy: 0.6562 - val_loss: 3.6693 - val_accuracy: 0.1875\n",
"Epoch 4103/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4657 - accuracy: 0.6875 - val_loss: 3.7847 - val_accuracy: 0.1875\n",
"Epoch 4104/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6127 - accuracy: 0.5625 - val_loss: 3.7157 - val_accuracy: 0.2188\n",
"Epoch 4105/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4894 - accuracy: 0.6562 - val_loss: 3.6756 - val_accuracy: 0.2188\n",
"Epoch 4106/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5422 - accuracy: 0.7188 - val_loss: 3.9678 - val_accuracy: 0.1875\n",
"Epoch 4107/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6334 - accuracy: 0.5938 - val_loss: 3.5213 - val_accuracy: 0.1875\n",
"Epoch 4108/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5630 - accuracy: 0.7500 - val_loss: 3.8983 - val_accuracy: 0.1875\n",
"Epoch 4109/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.6011 - accuracy: 0.5625 - val_loss: 3.5311 - val_accuracy: 0.1562\n",
"Epoch 4110/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6465 - accuracy: 0.6875 - val_loss: 4.2415 - val_accuracy: 0.1875\n",
"Epoch 4111/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8763 - accuracy: 0.5000 - val_loss: 3.3430 - val_accuracy: 0.1562\n",
"Epoch 4112/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8520 - accuracy: 0.3750 - val_loss: 4.2922 - val_accuracy: 0.1562\n",
"Epoch 4113/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8707 - accuracy: 0.4062 - val_loss: 3.3052 - val_accuracy: 0.1875\n",
"Epoch 4114/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.8106 - accuracy: 0.5312 - val_loss: 3.9093 - val_accuracy: 0.1562\n",
"Epoch 4115/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6426 - accuracy: 0.5312 - val_loss: 3.4471 - val_accuracy: 0.1875\n",
"Epoch 4116/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.4744 - accuracy: 0.6562 - val_loss: 3.5616 - val_accuracy: 0.1875\n",
"Epoch 4117/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4979 - accuracy: 0.6875 - val_loss: 3.6408 - val_accuracy: 0.1875\n",
"Epoch 4118/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6032 - accuracy: 0.5625 - val_loss: 3.5549 - val_accuracy: 0.1875\n",
"Epoch 4119/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5325 - accuracy: 0.6250 - val_loss: 3.6713 - val_accuracy: 0.1875\n",
"Epoch 4120/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5964 - accuracy: 0.6875 - val_loss: 3.5599 - val_accuracy: 0.2188\n",
"Epoch 4121/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4243 - accuracy: 0.7500 - val_loss: 3.6556 - val_accuracy: 0.2188\n",
"Epoch 4122/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.3998 - accuracy: 0.7188 - val_loss: 3.5913 - val_accuracy: 0.2188\n",
"Epoch 4123/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5462 - accuracy: 0.5312 - val_loss: 3.7052 - val_accuracy: 0.1875\n",
"Epoch 4124/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4782 - accuracy: 0.7188 - val_loss: 3.5502 - val_accuracy: 0.2188\n",
"Epoch 4125/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4743 - accuracy: 0.6250 - val_loss: 3.6882 - val_accuracy: 0.1875\n",
"Epoch 4126/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5020 - accuracy: 0.6250 - val_loss: 3.7077 - val_accuracy: 0.1875\n",
"Epoch 4127/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4375 - accuracy: 0.6875 - val_loss: 3.6547 - val_accuracy: 0.1875\n",
"Epoch 4128/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5176 - accuracy: 0.6250 - val_loss: 3.6187 - val_accuracy: 0.1875\n",
"Epoch 4129/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4280 - accuracy: 0.7812 - val_loss: 3.6109 - val_accuracy: 0.1562\n",
"Epoch 4130/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.4724 - accuracy: 0.7812 - val_loss: 3.7081 - val_accuracy: 0.1875\n",
"Epoch 4131/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6575 - accuracy: 0.6562 - val_loss: 3.7226 - val_accuracy: 0.1875\n",
"Epoch 4132/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.4394 - accuracy: 0.7500 - val_loss: 3.6755 - val_accuracy: 0.1875\n",
"Epoch 4133/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5440 - accuracy: 0.7500 - val_loss: 3.7538 - val_accuracy: 0.1875\n",
"Epoch 4134/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5273 - accuracy: 0.7188 - val_loss: 3.5866 - val_accuracy: 0.1562\n",
"Epoch 4135/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5007 - accuracy: 0.6562 - val_loss: 3.7024 - val_accuracy: 0.1875\n",
"Epoch 4136/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4295 - accuracy: 0.7500 - val_loss: 3.6603 - val_accuracy: 0.1875\n",
"Epoch 4137/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4297 - accuracy: 0.7500 - val_loss: 3.7161 - val_accuracy: 0.1875\n",
"Epoch 4138/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.4449 - accuracy: 0.7188 - val_loss: 3.6518 - val_accuracy: 0.1875\n",
"Epoch 4139/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.4675 - accuracy: 0.7500 - val_loss: 3.6248 - val_accuracy: 0.1875\n",
"Epoch 4140/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6213 - accuracy: 0.5625 - val_loss: 3.8510 - val_accuracy: 0.1562\n",
"Epoch 4141/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6286 - accuracy: 0.5625 - val_loss: 3.4512 - val_accuracy: 0.1562\n",
"Epoch 4142/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4667 - accuracy: 0.8125 - val_loss: 3.7930 - val_accuracy: 0.1875\n",
"Epoch 4143/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5090 - accuracy: 0.6562 - val_loss: 3.6044 - val_accuracy: 0.1875\n",
"Epoch 4144/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5745 - accuracy: 0.5938 - val_loss: 3.9671 - val_accuracy: 0.1875\n",
"Epoch 4145/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5282 - accuracy: 0.6250 - val_loss: 3.4307 - val_accuracy: 0.1562\n",
"Epoch 4146/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6347 - accuracy: 0.5625 - val_loss: 3.8769 - val_accuracy: 0.2188\n",
"Epoch 4147/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5374 - accuracy: 0.6250 - val_loss: 3.4359 - val_accuracy: 0.1875\n",
"Epoch 4148/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6140 - accuracy: 0.6562 - val_loss: 3.9057 - val_accuracy: 0.2188\n",
"Epoch 4149/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5265 - accuracy: 0.7188 - val_loss: 3.4780 - val_accuracy: 0.1562\n",
"Epoch 4150/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5523 - accuracy: 0.6250 - val_loss: 3.9878 - val_accuracy: 0.1875\n",
"Epoch 4151/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6650 - accuracy: 0.5312 - val_loss: 3.4275 - val_accuracy: 0.1875\n",
"Epoch 4152/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6928 - accuracy: 0.5938 - val_loss: 4.3675 - val_accuracy: 0.1875\n",
"Epoch 4153/5000\n",
"1/1 [==============================] - 0s 151ms/step - loss: 0.8317 - accuracy: 0.4375 - val_loss: 3.4481 - val_accuracy: 0.1562\n",
"Epoch 4154/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6471 - accuracy: 0.6250 - val_loss: 4.2791 - val_accuracy: 0.1875\n",
"Epoch 4155/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8431 - accuracy: 0.4062 - val_loss: 3.4160 - val_accuracy: 0.1562\n",
"Epoch 4156/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6027 - accuracy: 0.6562 - val_loss: 3.9241 - val_accuracy: 0.2188\n",
"Epoch 4157/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5741 - accuracy: 0.5938 - val_loss: 3.4976 - val_accuracy: 0.1875\n",
"Epoch 4158/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5737 - accuracy: 0.6250 - val_loss: 3.8435 - val_accuracy: 0.2188\n",
"Epoch 4159/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5785 - accuracy: 0.6875 - val_loss: 3.5933 - val_accuracy: 0.1875\n",
"Epoch 4160/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5603 - accuracy: 0.6875 - val_loss: 3.7779 - val_accuracy: 0.1875\n",
"Epoch 4161/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5855 - accuracy: 0.7188 - val_loss: 3.6052 - val_accuracy: 0.2188\n",
"Epoch 4162/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4533 - accuracy: 0.7188 - val_loss: 3.7258 - val_accuracy: 0.1875\n",
"Epoch 4163/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4937 - accuracy: 0.7188 - val_loss: 3.6738 - val_accuracy: 0.1875\n",
"Epoch 4164/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.4565 - accuracy: 0.6875 - val_loss: 3.6966 - val_accuracy: 0.1875\n",
"Epoch 4165/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4516 - accuracy: 0.7500 - val_loss: 3.7078 - val_accuracy: 0.1875\n",
"Epoch 4166/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5474 - accuracy: 0.7500 - val_loss: 3.7104 - val_accuracy: 0.1875\n",
"Epoch 4167/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4054 - accuracy: 0.8750 - val_loss: 3.7169 - val_accuracy: 0.1875\n",
"Epoch 4168/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5170 - accuracy: 0.7188 - val_loss: 3.6792 - val_accuracy: 0.1875\n",
"Epoch 4169/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5076 - accuracy: 0.6562 - val_loss: 3.6767 - val_accuracy: 0.1875\n",
"Epoch 4170/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.4255 - accuracy: 0.7812 - val_loss: 3.6730 - val_accuracy: 0.1875\n",
"Epoch 4171/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4049 - accuracy: 0.7812 - val_loss: 3.6386 - val_accuracy: 0.1875\n",
"Epoch 4172/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5315 - accuracy: 0.5938 - val_loss: 3.6653 - val_accuracy: 0.1875\n",
"Epoch 4173/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5619 - accuracy: 0.6250 - val_loss: 3.7274 - val_accuracy: 0.2188\n",
"Epoch 4174/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4606 - accuracy: 0.6562 - val_loss: 3.6605 - val_accuracy: 0.2188\n",
"Epoch 4175/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4587 - accuracy: 0.7500 - val_loss: 3.7817 - val_accuracy: 0.1875\n",
"Epoch 4176/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.4263 - accuracy: 0.6875 - val_loss: 3.6135 - val_accuracy: 0.1875\n",
"Epoch 4177/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.6315 - accuracy: 0.5938 - val_loss: 4.0076 - val_accuracy: 0.1875\n",
"Epoch 4178/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.6655 - accuracy: 0.5625 - val_loss: 3.3620 - val_accuracy: 0.1875\n",
"Epoch 4179/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5442 - accuracy: 0.6875 - val_loss: 3.7012 - val_accuracy: 0.1875\n",
"Epoch 4180/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.5377 - accuracy: 0.6875 - val_loss: 3.4832 - val_accuracy: 0.1562\n",
"Epoch 4181/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5586 - accuracy: 0.6562 - val_loss: 3.7613 - val_accuracy: 0.1875\n",
"Epoch 4182/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5710 - accuracy: 0.5938 - val_loss: 3.6055 - val_accuracy: 0.2188\n",
"Epoch 4183/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6091 - accuracy: 0.5938 - val_loss: 3.7333 - val_accuracy: 0.1875\n",
"Epoch 4184/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5011 - accuracy: 0.6562 - val_loss: 3.6148 - val_accuracy: 0.2188\n",
"Epoch 4185/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4826 - accuracy: 0.6875 - val_loss: 3.8242 - val_accuracy: 0.1875\n",
"Epoch 4186/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.5944 - accuracy: 0.5000 - val_loss: 3.5492 - val_accuracy: 0.2188\n",
"Epoch 4187/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5439 - accuracy: 0.6875 - val_loss: 3.7986 - val_accuracy: 0.1875\n",
"Epoch 4188/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4655 - accuracy: 0.7188 - val_loss: 3.5699 - val_accuracy: 0.2188\n",
"Epoch 4189/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4627 - accuracy: 0.6562 - val_loss: 3.7582 - val_accuracy: 0.1875\n",
"Epoch 4190/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6443 - accuracy: 0.6562 - val_loss: 3.6784 - val_accuracy: 0.1875\n",
"Epoch 4191/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4579 - accuracy: 0.7500 - val_loss: 3.6773 - val_accuracy: 0.1875\n",
"Epoch 4192/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.4664 - accuracy: 0.8125 - val_loss: 3.6617 - val_accuracy: 0.1875\n",
"Epoch 4193/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5128 - accuracy: 0.7188 - val_loss: 3.7079 - val_accuracy: 0.1875\n",
"Epoch 4194/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6185 - accuracy: 0.6250 - val_loss: 3.6097 - val_accuracy: 0.2188\n",
"Epoch 4195/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5917 - accuracy: 0.5938 - val_loss: 3.9132 - val_accuracy: 0.1562\n",
"Epoch 4196/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6450 - accuracy: 0.5938 - val_loss: 3.4125 - val_accuracy: 0.1562\n",
"Epoch 4197/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.7208 - accuracy: 0.5625 - val_loss: 4.2069 - val_accuracy: 0.1562\n",
"Epoch 4198/5000\n",
"1/1 [==============================] - 0s 151ms/step - loss: 0.9362 - accuracy: 0.4688 - val_loss: 3.6175 - val_accuracy: 0.1250\n",
"Epoch 4199/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 3.3301 - accuracy: 0.2500 - val_loss: 20.7450 - val_accuracy: 0.0312\n",
"Epoch 4200/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 28.6986 - accuracy: 0.0312 - val_loss: 2.9408 - val_accuracy: 0.0312\n",
"Epoch 4201/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 3.0854 - accuracy: 0.0938 - val_loss: 2.7312 - val_accuracy: 0.0312\n",
"Epoch 4202/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 4.2081 - accuracy: 0.0625 - val_loss: 2.6229 - val_accuracy: 0.0312\n",
"Epoch 4203/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 3.4196 - accuracy: 0.1250 - val_loss: 2.7709 - val_accuracy: 0.0312\n",
"Epoch 4204/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 3.1843 - accuracy: 0.0625 - val_loss: 2.8954 - val_accuracy: 0.0312\n",
"Epoch 4205/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.8939 - accuracy: 0.0938 - val_loss: 2.8357 - val_accuracy: 0.0312\n",
"Epoch 4206/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 2.5891 - accuracy: 0.0938 - val_loss: 2.7995 - val_accuracy: 0.0312\n",
"Epoch 4207/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.4785 - accuracy: 0.1250 - val_loss: 2.6912 - val_accuracy: 0.0312\n",
"Epoch 4208/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 4.2092 - accuracy: 0.0312 - val_loss: 2.5593 - val_accuracy: 0.0312\n",
"Epoch 4209/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 2.4156 - accuracy: 0.1250 - val_loss: 2.6584 - val_accuracy: 0.0312\n",
"Epoch 4210/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 2.4832 - accuracy: 0.0938 - val_loss: 2.6228 - val_accuracy: 0.0312\n",
"Epoch 4211/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.8312 - accuracy: 0.1250 - val_loss: 2.7955 - val_accuracy: 0.0312\n",
"Epoch 4212/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.5324 - accuracy: 0.1562 - val_loss: 2.7404 - val_accuracy: 0.0312\n",
"Epoch 4213/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.3881 - accuracy: 0.1250 - val_loss: 2.6338 - val_accuracy: 0.0938\n",
"Epoch 4214/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.5090 - accuracy: 0.2188 - val_loss: 2.6193 - val_accuracy: 0.0625\n",
"Epoch 4215/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.2858 - accuracy: 0.1875 - val_loss: 2.5528 - val_accuracy: 0.0625\n",
"Epoch 4216/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 2.2558 - accuracy: 0.1562 - val_loss: 2.8356 - val_accuracy: 0.0312\n",
"Epoch 4217/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.9065 - accuracy: 0.2188 - val_loss: 2.9048 - val_accuracy: 0.0625\n",
"Epoch 4218/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.5919 - accuracy: 0.1250 - val_loss: 3.0272 - val_accuracy: 0.0312\n",
"Epoch 4219/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.9122 - accuracy: 0.2500 - val_loss: 2.9872 - val_accuracy: 0.0312\n",
"Epoch 4220/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 2.5715 - accuracy: 0.1875 - val_loss: 2.8562 - val_accuracy: 0.0312\n",
"Epoch 4221/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 2.1058 - accuracy: 0.2500 - val_loss: 2.8581 - val_accuracy: 0.0312\n",
"Epoch 4222/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 1.9803 - accuracy: 0.2500 - val_loss: 2.7453 - val_accuracy: 0.0312\n",
"Epoch 4223/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.7199 - accuracy: 0.2188 - val_loss: 2.8227 - val_accuracy: 0.0625\n",
"Epoch 4224/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.8040 - accuracy: 0.3125 - val_loss: 2.7821 - val_accuracy: 0.0312\n",
"Epoch 4225/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 2.0619 - accuracy: 0.2500 - val_loss: 2.9169 - val_accuracy: 0.0312\n",
"Epoch 4226/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 1.8824 - accuracy: 0.2812 - val_loss: 2.8009 - val_accuracy: 0.0312\n",
"Epoch 4227/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.6215 - accuracy: 0.3125 - val_loss: 2.8865 - val_accuracy: 0.0312\n",
"Epoch 4228/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.4773 - accuracy: 0.2188 - val_loss: 2.7741 - val_accuracy: 0.0312\n",
"Epoch 4229/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.8206 - accuracy: 0.3125 - val_loss: 2.7846 - val_accuracy: 0.0625\n",
"Epoch 4230/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.7272 - accuracy: 0.3750 - val_loss: 2.7890 - val_accuracy: 0.0312\n",
"Epoch 4231/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.6826 - accuracy: 0.2188 - val_loss: 2.8678 - val_accuracy: 0.0312\n",
"Epoch 4232/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.7256 - accuracy: 0.2500 - val_loss: 2.8626 - val_accuracy: 0.0312\n",
"Epoch 4233/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 1.6437 - accuracy: 0.3125 - val_loss: 2.7654 - val_accuracy: 0.0312\n",
"Epoch 4234/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.4637 - accuracy: 0.3125 - val_loss: 2.7612 - val_accuracy: 0.0625\n",
"Epoch 4235/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 1.6576 - accuracy: 0.2812 - val_loss: 3.0166 - val_accuracy: 0.0625\n",
"Epoch 4236/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.7053 - accuracy: 0.2812 - val_loss: 2.8504 - val_accuracy: 0.1250\n",
"Epoch 4237/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.5633 - accuracy: 0.2500 - val_loss: 2.7512 - val_accuracy: 0.1562\n",
"Epoch 4238/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 1.5571 - accuracy: 0.3750 - val_loss: 2.8839 - val_accuracy: 0.0938\n",
"Epoch 4239/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.5124 - accuracy: 0.3438 - val_loss: 2.8093 - val_accuracy: 0.1875\n",
"Epoch 4240/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.9338 - accuracy: 0.4688 - val_loss: 2.7977 - val_accuracy: 0.1250\n",
"Epoch 4241/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.2597 - accuracy: 0.4062 - val_loss: 2.7489 - val_accuracy: 0.0938\n",
"Epoch 4242/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.6533 - accuracy: 0.4062 - val_loss: 2.7784 - val_accuracy: 0.0625\n",
"Epoch 4243/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 1.6096 - accuracy: 0.4062 - val_loss: 2.8393 - val_accuracy: 0.0938\n",
"Epoch 4244/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.3163 - accuracy: 0.3750 - val_loss: 2.8016 - val_accuracy: 0.1562\n",
"Epoch 4245/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.4810 - accuracy: 0.3438 - val_loss: 2.7582 - val_accuracy: 0.1562\n",
"Epoch 4246/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.4104 - accuracy: 0.3438 - val_loss: 2.8608 - val_accuracy: 0.1250\n",
"Epoch 4247/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 1.6269 - accuracy: 0.4688 - val_loss: 2.8962 - val_accuracy: 0.1562\n",
"Epoch 4248/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 1.7940 - accuracy: 0.3438 - val_loss: 2.9980 - val_accuracy: 0.0625\n",
"Epoch 4249/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 1.7975 - accuracy: 0.3125 - val_loss: 2.9165 - val_accuracy: 0.0625\n",
"Epoch 4250/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.3426 - accuracy: 0.2500 - val_loss: 2.8340 - val_accuracy: 0.0625\n",
"Epoch 4251/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.6368 - accuracy: 0.3750 - val_loss: 2.9842 - val_accuracy: 0.0938\n",
"Epoch 4252/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.4905 - accuracy: 0.2500 - val_loss: 2.8170 - val_accuracy: 0.0938\n",
"Epoch 4253/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.3267 - accuracy: 0.3125 - val_loss: 2.7754 - val_accuracy: 0.1562\n",
"Epoch 4254/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.1641 - accuracy: 0.4062 - val_loss: 2.6579 - val_accuracy: 0.2188\n",
"Epoch 4255/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.1330 - accuracy: 0.3750 - val_loss: 2.7604 - val_accuracy: 0.1875\n",
"Epoch 4256/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.0105 - accuracy: 0.4375 - val_loss: 2.6776 - val_accuracy: 0.2188\n",
"Epoch 4257/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8133 - accuracy: 0.6250 - val_loss: 2.6474 - val_accuracy: 0.2188\n",
"Epoch 4258/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.9214 - accuracy: 0.4688 - val_loss: 2.6854 - val_accuracy: 0.2188\n",
"Epoch 4259/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.8030 - accuracy: 0.5938 - val_loss: 2.6644 - val_accuracy: 0.2188\n",
"Epoch 4260/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.8479 - accuracy: 0.6250 - val_loss: 2.6492 - val_accuracy: 0.2812\n",
"Epoch 4261/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8692 - accuracy: 0.5625 - val_loss: 2.7020 - val_accuracy: 0.2812\n",
"Epoch 4262/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7661 - accuracy: 0.5625 - val_loss: 2.6627 - val_accuracy: 0.2812\n",
"Epoch 4263/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.7579 - accuracy: 0.6250 - val_loss: 2.6973 - val_accuracy: 0.2812\n",
"Epoch 4264/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.8317 - accuracy: 0.5312 - val_loss: 2.7060 - val_accuracy: 0.2500\n",
"Epoch 4265/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.8308 - accuracy: 0.4688 - val_loss: 2.7207 - val_accuracy: 0.2812\n",
"Epoch 4266/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 0.8164 - accuracy: 0.6250 - val_loss: 2.8213 - val_accuracy: 0.2812\n",
"Epoch 4267/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.8595 - accuracy: 0.4688 - val_loss: 2.7521 - val_accuracy: 0.2500\n",
"Epoch 4268/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.7644 - accuracy: 0.5625 - val_loss: 2.7701 - val_accuracy: 0.2812\n",
"Epoch 4269/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6961 - accuracy: 0.6250 - val_loss: 2.7387 - val_accuracy: 0.2812\n",
"Epoch 4270/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7462 - accuracy: 0.5938 - val_loss: 2.7380 - val_accuracy: 0.2812\n",
"Epoch 4271/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7370 - accuracy: 0.6250 - val_loss: 2.8074 - val_accuracy: 0.2500\n",
"Epoch 4272/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.7434 - accuracy: 0.6562 - val_loss: 2.8747 - val_accuracy: 0.2500\n",
"Epoch 4273/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.9134 - accuracy: 0.4688 - val_loss: 2.8735 - val_accuracy: 0.2500\n",
"Epoch 4274/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.7478 - accuracy: 0.5312 - val_loss: 2.8755 - val_accuracy: 0.2500\n",
"Epoch 4275/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6577 - accuracy: 0.6562 - val_loss: 2.8354 - val_accuracy: 0.2500\n",
"Epoch 4276/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.7230 - accuracy: 0.6250 - val_loss: 2.8285 - val_accuracy: 0.2812\n",
"Epoch 4277/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6206 - accuracy: 0.6250 - val_loss: 2.8821 - val_accuracy: 0.2188\n",
"Epoch 4278/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6872 - accuracy: 0.4688 - val_loss: 2.8915 - val_accuracy: 0.2500\n",
"Epoch 4279/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5346 - accuracy: 0.6875 - val_loss: 2.8604 - val_accuracy: 0.2188\n",
"Epoch 4280/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6440 - accuracy: 0.6875 - val_loss: 2.8585 - val_accuracy: 0.2188\n",
"Epoch 4281/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6335 - accuracy: 0.7812 - val_loss: 2.9806 - val_accuracy: 0.2188\n",
"Epoch 4282/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6877 - accuracy: 0.5312 - val_loss: 2.9420 - val_accuracy: 0.2188\n",
"Epoch 4283/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.7541 - accuracy: 0.5000 - val_loss: 2.9179 - val_accuracy: 0.2188\n",
"Epoch 4284/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.6992 - accuracy: 0.6250 - val_loss: 2.9453 - val_accuracy: 0.2188\n",
"Epoch 4285/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 0.6373 - accuracy: 0.5938 - val_loss: 2.8828 - val_accuracy: 0.2188\n",
"Epoch 4286/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.6164 - accuracy: 0.6562 - val_loss: 2.9556 - val_accuracy: 0.2188\n",
"Epoch 4287/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6865 - accuracy: 0.5938 - val_loss: 2.9859 - val_accuracy: 0.2188\n",
"Epoch 4288/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.7468 - accuracy: 0.5312 - val_loss: 2.9791 - val_accuracy: 0.2188\n",
"Epoch 4289/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6792 - accuracy: 0.6250 - val_loss: 2.9781 - val_accuracy: 0.2188\n",
"Epoch 4290/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.4813 - accuracy: 0.7188 - val_loss: 2.9742 - val_accuracy: 0.2188\n",
"Epoch 4291/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.7588 - accuracy: 0.6562 - val_loss: 3.0665 - val_accuracy: 0.2188\n",
"Epoch 4292/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6243 - accuracy: 0.6250 - val_loss: 2.9917 - val_accuracy: 0.2188\n",
"Epoch 4293/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6277 - accuracy: 0.5312 - val_loss: 3.0060 - val_accuracy: 0.2188\n",
"Epoch 4294/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5507 - accuracy: 0.7188 - val_loss: 3.0098 - val_accuracy: 0.2188\n",
"Epoch 4295/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5762 - accuracy: 0.5938 - val_loss: 3.0249 - val_accuracy: 0.2188\n",
"Epoch 4296/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5952 - accuracy: 0.6562 - val_loss: 2.9706 - val_accuracy: 0.2188\n",
"Epoch 4297/5000\n",
"1/1 [==============================] - 0s 203ms/step - loss: 0.7048 - accuracy: 0.6562 - val_loss: 3.0937 - val_accuracy: 0.2188\n",
"Epoch 4298/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.6578 - accuracy: 0.6250 - val_loss: 3.0798 - val_accuracy: 0.2188\n",
"Epoch 4299/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5592 - accuracy: 0.6562 - val_loss: 3.0893 - val_accuracy: 0.2188\n",
"Epoch 4300/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6124 - accuracy: 0.6250 - val_loss: 3.0747 - val_accuracy: 0.2188\n",
"Epoch 4301/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.7803 - accuracy: 0.6250 - val_loss: 3.3139 - val_accuracy: 0.2188\n",
"Epoch 4302/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5858 - accuracy: 0.6875 - val_loss: 3.0989 - val_accuracy: 0.1875\n",
"Epoch 4303/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.6958 - accuracy: 0.5625 - val_loss: 3.2347 - val_accuracy: 0.2188\n",
"Epoch 4304/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5105 - accuracy: 0.6875 - val_loss: 3.1890 - val_accuracy: 0.2188\n",
"Epoch 4305/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5916 - accuracy: 0.6562 - val_loss: 3.1882 - val_accuracy: 0.2188\n",
"Epoch 4306/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4736 - accuracy: 0.8125 - val_loss: 3.2205 - val_accuracy: 0.2188\n",
"Epoch 4307/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5688 - accuracy: 0.6875 - val_loss: 3.1173 - val_accuracy: 0.2188\n",
"Epoch 4308/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.6072 - accuracy: 0.6875 - val_loss: 3.1329 - val_accuracy: 0.2188\n",
"Epoch 4309/5000\n",
"1/1 [==============================] - 0s 198ms/step - loss: 0.4875 - accuracy: 0.6562 - val_loss: 3.1994 - val_accuracy: 0.2188\n",
"Epoch 4310/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.6111 - accuracy: 0.6250 - val_loss: 3.1967 - val_accuracy: 0.2188\n",
"Epoch 4311/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5921 - accuracy: 0.6562 - val_loss: 3.1978 - val_accuracy: 0.2188\n",
"Epoch 4312/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5156 - accuracy: 0.6250 - val_loss: 3.1470 - val_accuracy: 0.2188\n",
"Epoch 4313/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5226 - accuracy: 0.7188 - val_loss: 3.1462 - val_accuracy: 0.2188\n",
"Epoch 4314/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4797 - accuracy: 0.6250 - val_loss: 3.2015 - val_accuracy: 0.2188\n",
"Epoch 4315/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.5656 - accuracy: 0.71 - 0s 164ms/step - loss: 0.5656 - accuracy: 0.7188 - val_loss: 3.1785 - val_accuracy: 0.2188\n",
"Epoch 4316/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6034 - accuracy: 0.5625 - val_loss: 3.1620 - val_accuracy: 0.2188\n",
"Epoch 4317/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5376 - accuracy: 0.6250 - val_loss: 3.2151 - val_accuracy: 0.2188\n",
"Epoch 4318/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6004 - accuracy: 0.5938 - val_loss: 3.1625 - val_accuracy: 0.2188\n",
"Epoch 4319/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5580 - accuracy: 0.6562 - val_loss: 3.1705 - val_accuracy: 0.2188\n",
"Epoch 4320/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6146 - accuracy: 0.5625 - val_loss: 3.3086 - val_accuracy: 0.1875\n",
"Epoch 4321/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6019 - accuracy: 0.7500 - val_loss: 3.3242 - val_accuracy: 0.2188\n",
"Epoch 4322/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5428 - accuracy: 0.7188 - val_loss: 3.2456 - val_accuracy: 0.2188\n",
"Epoch 4323/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5386 - accuracy: 0.6562 - val_loss: 3.3154 - val_accuracy: 0.1875\n",
"Epoch 4324/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4958 - accuracy: 0.6875 - val_loss: 3.2579 - val_accuracy: 0.2188\n",
"Epoch 4325/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5294 - accuracy: 0.7188 - val_loss: 3.2697 - val_accuracy: 0.2188\n",
"Epoch 4326/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5810 - accuracy: 0.6250 - val_loss: 3.2943 - val_accuracy: 0.2188\n",
"Epoch 4327/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4909 - accuracy: 0.6875 - val_loss: 3.1995 - val_accuracy: 0.2188\n",
"Epoch 4328/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5361 - accuracy: 0.6875 - val_loss: 3.2369 - val_accuracy: 0.2188\n",
"Epoch 4329/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.6450 - accuracy: 0.7188 - val_loss: 3.3460 - val_accuracy: 0.1875\n",
"Epoch 4330/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.4917 - accuracy: 0.6562 - val_loss: 3.2492 - val_accuracy: 0.2188\n",
"Epoch 4331/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4690 - accuracy: 0.6875 - val_loss: 3.1676 - val_accuracy: 0.2188\n",
"Epoch 4332/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5475 - accuracy: 0.6250 - val_loss: 3.2371 - val_accuracy: 0.2188\n",
"Epoch 4333/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5187 - accuracy: 0.6562 - val_loss: 3.2806 - val_accuracy: 0.1875\n",
"Epoch 4334/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4380 - accuracy: 0.7188 - val_loss: 3.2900 - val_accuracy: 0.1875\n",
"Epoch 4335/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5380 - accuracy: 0.7500 - val_loss: 3.2960 - val_accuracy: 0.1875\n",
"Epoch 4336/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5707 - accuracy: 0.5625 - val_loss: 3.2427 - val_accuracy: 0.2188\n",
"Epoch 4337/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5393 - accuracy: 0.7500 - val_loss: 3.3178 - val_accuracy: 0.2188\n",
"Epoch 4338/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5573 - accuracy: 0.5312 - val_loss: 3.3890 - val_accuracy: 0.1875\n",
"Epoch 4339/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6215 - accuracy: 0.6562 - val_loss: 3.2854 - val_accuracy: 0.2188\n",
"Epoch 4340/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.4783 - accuracy: 0.6875 - val_loss: 3.3434 - val_accuracy: 0.2188\n",
"Epoch 4341/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4243 - accuracy: 0.7188 - val_loss: 3.3201 - val_accuracy: 0.1875\n",
"Epoch 4342/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5146 - accuracy: 0.6875 - val_loss: 3.3642 - val_accuracy: 0.1875\n",
"Epoch 4343/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5839 - accuracy: 0.6875 - val_loss: 3.2958 - val_accuracy: 0.1875\n",
"Epoch 4344/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5801 - accuracy: 0.5938 - val_loss: 3.3738 - val_accuracy: 0.2188\n",
"Epoch 4345/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4175 - accuracy: 0.7500 - val_loss: 3.3654 - val_accuracy: 0.2188\n",
"Epoch 4346/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4710 - accuracy: 0.6562 - val_loss: 3.2502 - val_accuracy: 0.1875\n",
"Epoch 4347/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5335 - accuracy: 0.5938 - val_loss: 3.3769 - val_accuracy: 0.2188\n",
"Epoch 4348/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.4445 - accuracy: 0.7500 - val_loss: 3.3501 - val_accuracy: 0.1875\n",
"Epoch 4349/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5033 - accuracy: 0.7188 - val_loss: 3.3282 - val_accuracy: 0.1875\n",
"Epoch 4350/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4547 - accuracy: 0.7812 - val_loss: 3.3564 - val_accuracy: 0.1875\n",
"Epoch 4351/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5615 - accuracy: 0.6875 - val_loss: 3.3627 - val_accuracy: 0.1875\n",
"Epoch 4352/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4886 - accuracy: 0.7500 - val_loss: 3.3385 - val_accuracy: 0.1875\n",
"Epoch 4353/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6285 - accuracy: 0.5625 - val_loss: 3.3495 - val_accuracy: 0.1875\n",
"Epoch 4354/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.4929 - accuracy: 0.7500 - val_loss: 3.3274 - val_accuracy: 0.1875\n",
"Epoch 4355/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4370 - accuracy: 0.7500 - val_loss: 3.3556 - val_accuracy: 0.1875\n",
"Epoch 4356/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4257 - accuracy: 0.7500 - val_loss: 3.3689 - val_accuracy: 0.1875\n",
"Epoch 4357/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4658 - accuracy: 0.6562 - val_loss: 3.3922 - val_accuracy: 0.1875\n",
"Epoch 4358/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4324 - accuracy: 0.8125 - val_loss: 3.3373 - val_accuracy: 0.1875\n",
"Epoch 4359/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5089 - accuracy: 0.6562 - val_loss: 3.4579 - val_accuracy: 0.1875\n",
"Epoch 4360/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.4326 - accuracy: 0.7188 - val_loss: 3.3334 - val_accuracy: 0.1875\n",
"Epoch 4361/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5380 - accuracy: 0.6562 - val_loss: 3.6072 - val_accuracy: 0.1875\n",
"Epoch 4362/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4504 - accuracy: 0.6875 - val_loss: 3.4164 - val_accuracy: 0.1875\n",
"Epoch 4363/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5990 - accuracy: 0.6875 - val_loss: 3.4690 - val_accuracy: 0.2188\n",
"Epoch 4364/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4730 - accuracy: 0.7500 - val_loss: 3.4468 - val_accuracy: 0.1875\n",
"Epoch 4365/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.4651 - accuracy: 0.6250 - val_loss: 3.3790 - val_accuracy: 0.1875\n",
"Epoch 4366/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5627 - accuracy: 0.6562 - val_loss: 3.4812 - val_accuracy: 0.1875\n",
"Epoch 4367/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5543 - accuracy: 0.6562 - val_loss: 3.3915 - val_accuracy: 0.1875\n",
"Epoch 4368/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5880 - accuracy: 0.6875 - val_loss: 3.4623 - val_accuracy: 0.1875\n",
"Epoch 4369/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.5815 - accuracy: 0.6250 - val_loss: 3.4525 - val_accuracy: 0.2188\n",
"Epoch 4370/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5981 - accuracy: 0.6562 - val_loss: 3.4566 - val_accuracy: 0.2188\n",
"Epoch 4371/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4926 - accuracy: 0.7188 - val_loss: 3.4277 - val_accuracy: 0.1875\n",
"Epoch 4372/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5746 - accuracy: 0.5938 - val_loss: 3.6931 - val_accuracy: 0.2500\n",
"Epoch 4373/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5806 - accuracy: 0.5938 - val_loss: 3.4415 - val_accuracy: 0.2188\n",
"Epoch 4374/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4323 - accuracy: 0.6875 - val_loss: 3.5836 - val_accuracy: 0.1875\n",
"Epoch 4375/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5417 - accuracy: 0.5938 - val_loss: 3.4401 - val_accuracy: 0.1875\n",
"Epoch 4376/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4513 - accuracy: 0.7500 - val_loss: 3.4836 - val_accuracy: 0.1875\n",
"Epoch 4377/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5180 - accuracy: 0.7812 - val_loss: 3.4937 - val_accuracy: 0.1875\n",
"Epoch 4378/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4245 - accuracy: 0.6562 - val_loss: 3.4824 - val_accuracy: 0.1875\n",
"Epoch 4379/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4514 - accuracy: 0.7500 - val_loss: 3.5058 - val_accuracy: 0.1875\n",
"Epoch 4380/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5193 - accuracy: 0.7188 - val_loss: 3.5225 - val_accuracy: 0.1875\n",
"Epoch 4381/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4698 - accuracy: 0.7188 - val_loss: 3.5612 - val_accuracy: 0.1875\n",
"Epoch 4382/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4439 - accuracy: 0.7188 - val_loss: 3.4936 - val_accuracy: 0.1875\n",
"Epoch 4383/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5208 - accuracy: 0.5938 - val_loss: 3.5361 - val_accuracy: 0.2188\n",
"Epoch 4384/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5438 - accuracy: 0.6250 - val_loss: 3.5474 - val_accuracy: 0.1875\n",
"Epoch 4385/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4846 - accuracy: 0.6562 - val_loss: 3.5591 - val_accuracy: 0.1875\n",
"Epoch 4386/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4733 - accuracy: 0.6875 - val_loss: 3.4959 - val_accuracy: 0.2188\n",
"Epoch 4387/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.6238 - accuracy: 0.5938 - val_loss: 3.5503 - val_accuracy: 0.1875\n",
"Epoch 4388/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6039 - accuracy: 0.6562 - val_loss: 3.4177 - val_accuracy: 0.1875\n",
"Epoch 4389/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5869 - accuracy: 0.6875 - val_loss: 3.5885 - val_accuracy: 0.1875\n",
"Epoch 4390/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5848 - accuracy: 0.5625 - val_loss: 3.4560 - val_accuracy: 0.1875\n",
"Epoch 4391/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.4209 - accuracy: 0.6875 - val_loss: 3.4086 - val_accuracy: 0.1875\n",
"Epoch 4392/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5853 - accuracy: 0.6562 - val_loss: 3.4335 - val_accuracy: 0.1875\n",
"Epoch 4393/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.4424 - accuracy: 0.6875 - val_loss: 3.4682 - val_accuracy: 0.1875\n",
"Epoch 4394/5000\n",
"1/1 [==============================] - 0s 225ms/step - loss: 0.5137 - accuracy: 0.6562 - val_loss: 3.4342 - val_accuracy: 0.2188\n",
"Epoch 4395/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.5015 - accuracy: 0.6875 - val_loss: 3.4199 - val_accuracy: 0.2188\n",
"Epoch 4396/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5420 - accuracy: 0.7500 - val_loss: 3.4390 - val_accuracy: 0.1875\n",
"Epoch 4397/5000\n",
"1/1 [==============================] - 0s 216ms/step - loss: 0.4754 - accuracy: 0.7188 - val_loss: 3.6135 - val_accuracy: 0.1875\n",
"Epoch 4398/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.4444 - accuracy: 0.7500 - val_loss: 3.4948 - val_accuracy: 0.2188\n",
"Epoch 4399/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.5559 - accuracy: 0.6250 - val_loss: 3.5959 - val_accuracy: 0.1875\n",
"Epoch 4400/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5317 - accuracy: 0.7188 - val_loss: 3.5638 - val_accuracy: 0.1875\n",
"Epoch 4401/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5903 - accuracy: 0.6250 - val_loss: 3.5673 - val_accuracy: 0.1875\n",
"Epoch 4402/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5216 - accuracy: 0.7188 - val_loss: 3.5618 - val_accuracy: 0.1875\n",
"Epoch 4403/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.5521 - accuracy: 0.6562 - val_loss: 3.6123 - val_accuracy: 0.1875\n",
"Epoch 4404/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5006 - accuracy: 0.7188 - val_loss: 3.5688 - val_accuracy: 0.1875\n",
"Epoch 4405/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5375 - accuracy: 0.6562 - val_loss: 3.4946 - val_accuracy: 0.2188\n",
"Epoch 4406/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4412 - accuracy: 0.7188 - val_loss: 3.4891 - val_accuracy: 0.1875\n",
"Epoch 4407/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5129 - accuracy: 0.5625 - val_loss: 3.5972 - val_accuracy: 0.1875\n",
"Epoch 4408/5000\n",
"1/1 [==============================] - 0s 203ms/step - loss: 0.6720 - accuracy: 0.6875 - val_loss: 3.4131 - val_accuracy: 0.1250\n",
"Epoch 4409/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.7225 - accuracy: 0.5625 - val_loss: 3.8466 - val_accuracy: 0.1562\n",
"Epoch 4410/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5837 - accuracy: 0.5938 - val_loss: 3.4269 - val_accuracy: 0.1875\n",
"Epoch 4411/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4163 - accuracy: 0.7188 - val_loss: 3.4866 - val_accuracy: 0.1875\n",
"Epoch 4412/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.4717 - accuracy: 0.6875 - val_loss: 3.5475 - val_accuracy: 0.2188\n",
"Epoch 4413/5000\n",
"1/1 [==============================] - 0s 196ms/step - loss: 0.5109 - accuracy: 0.6875 - val_loss: 3.4917 - val_accuracy: 0.1875\n",
"Epoch 4414/5000\n",
"1/1 [==============================] - 0s 284ms/step - loss: 0.5132 - accuracy: 0.6875 - val_loss: 3.6662 - val_accuracy: 0.1875\n",
"Epoch 4415/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5651 - accuracy: 0.5938 - val_loss: 3.4489 - val_accuracy: 0.2188\n",
"Epoch 4416/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 1.1200 - accuracy: 0.5938 - val_loss: 3.4114 - val_accuracy: 0.1250\n",
"Epoch 4417/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.8735 - accuracy: 0.5000 - val_loss: 4.5013 - val_accuracy: 0.1562\n",
"Epoch 4418/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 1.1701 - accuracy: 0.2812 - val_loss: 3.1103 - val_accuracy: 0.1562\n",
"Epoch 4419/5000\n",
"1/1 [==============================] - 0s 230ms/step - loss: 1.0450 - accuracy: 0.4375 - val_loss: 4.3032 - val_accuracy: 0.1562\n",
"Epoch 4420/5000\n",
"1/1 [==============================] - 0s 210ms/step - loss: 1.3007 - accuracy: 0.3750 - val_loss: 3.2669 - val_accuracy: 0.1562\n",
"Epoch 4421/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 5.5761 - accuracy: 0.2500 - val_loss: 13.6216 - val_accuracy: 0.0625\n",
"Epoch 4422/5000\n",
"1/1 [==============================] - 0s 223ms/step - loss: 16.8375 - accuracy: 0.0312 - val_loss: 3.2925 - val_accuracy: 0.0312\n",
"Epoch 4423/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 2.9088 - accuracy: 0.1875 - val_loss: 2.9475 - val_accuracy: 0.0312\n",
"Epoch 4424/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 2.3734 - accuracy: 0.1250 - val_loss: 2.7776 - val_accuracy: 0.0312\n",
"Epoch 4425/5000\n",
"1/1 [==============================] - 0s 257ms/step - loss: 2.3599 - accuracy: 0.1250 - val_loss: 2.6207 - val_accuracy: 0.0625\n",
"Epoch 4426/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 1.9787 - accuracy: 0.1875 - val_loss: 2.5689 - val_accuracy: 0.0625\n",
"Epoch 4427/5000\n",
"1/1 [==============================] - 0s 219ms/step - loss: 4.3683 - accuracy: 0.0938 - val_loss: 2.6876 - val_accuracy: 0.1250\n",
"Epoch 4428/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 1.8738 - accuracy: 0.1875 - val_loss: 2.7182 - val_accuracy: 0.1250\n",
"Epoch 4429/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 3.1879 - accuracy: 0.0938 - val_loss: 2.7110 - val_accuracy: 0.1250\n",
"Epoch 4430/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 1.9301 - accuracy: 0.2500 - val_loss: 2.6956 - val_accuracy: 0.1250\n",
"Epoch 4431/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.9752 - accuracy: 0.1562 - val_loss: 2.6986 - val_accuracy: 0.0938\n",
"Epoch 4432/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.6903 - accuracy: 0.1875 - val_loss: 2.6017 - val_accuracy: 0.2188\n",
"Epoch 4433/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 1.5610 - accuracy: 0.2500 - val_loss: 2.3817 - val_accuracy: 0.2188\n",
"Epoch 4434/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.9052 - accuracy: 0.5938 - val_loss: 2.3364 - val_accuracy: 0.1875\n",
"Epoch 4435/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 1.2971 - accuracy: 0.5000 - val_loss: 2.4487 - val_accuracy: 0.1875\n",
"Epoch 4436/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.8950 - accuracy: 0.5312 - val_loss: 2.4695 - val_accuracy: 0.1875\n",
"Epoch 4437/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.7583 - accuracy: 0.6562 - val_loss: 2.4434 - val_accuracy: 0.1875\n",
"Epoch 4438/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.8063 - accuracy: 0.4688 - val_loss: 2.4095 - val_accuracy: 0.1875\n",
"Epoch 4439/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.9274 - accuracy: 0.5312 - val_loss: 2.5078 - val_accuracy: 0.1875\n",
"Epoch 4440/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.0297 - accuracy: 0.6250 - val_loss: 2.6358 - val_accuracy: 0.2188\n",
"Epoch 4441/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.8337 - accuracy: 0.5625 - val_loss: 2.5822 - val_accuracy: 0.1875\n",
"Epoch 4442/5000\n",
"1/1 [==============================] - 0s 212ms/step - loss: 0.7360 - accuracy: 0.4688 - val_loss: 2.6017 - val_accuracy: 0.1875\n",
"Epoch 4443/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6517 - accuracy: 0.7188 - val_loss: 2.6285 - val_accuracy: 0.2188\n",
"Epoch 4444/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6817 - accuracy: 0.6562 - val_loss: 2.6423 - val_accuracy: 0.2188\n",
"Epoch 4445/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5868 - accuracy: 0.6875 - val_loss: 2.6523 - val_accuracy: 0.2188\n",
"Epoch 4446/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6792 - accuracy: 0.6250 - val_loss: 2.6438 - val_accuracy: 0.2188\n",
"Epoch 4447/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6696 - accuracy: 0.6562 - val_loss: 2.6643 - val_accuracy: 0.2188\n",
"Epoch 4448/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.6628 - accuracy: 0.5312 - val_loss: 2.6865 - val_accuracy: 0.2188\n",
"Epoch 4449/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5721 - accuracy: 0.6875 - val_loss: 2.6707 - val_accuracy: 0.2188\n",
"Epoch 4450/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6722 - accuracy: 0.6562 - val_loss: 2.6934 - val_accuracy: 0.2188\n",
"Epoch 4451/5000\n",
"1/1 [==============================] - 0s 209ms/step - loss: 0.6182 - accuracy: 0.6562 - val_loss: 2.7214 - val_accuracy: 0.2188\n",
"Epoch 4452/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6365 - accuracy: 0.6250 - val_loss: 2.7343 - val_accuracy: 0.2188\n",
"Epoch 4453/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.6082 - accuracy: 0.6562 - val_loss: 2.7402 - val_accuracy: 0.2188\n",
"Epoch 4454/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5978 - accuracy: 0.5938 - val_loss: 2.7429 - val_accuracy: 0.2188\n",
"Epoch 4455/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6180 - accuracy: 0.6875 - val_loss: 2.7522 - val_accuracy: 0.2188\n",
"Epoch 4456/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.6288 - accuracy: 0.6250 - val_loss: 2.7576 - val_accuracy: 0.2188\n",
"Epoch 4457/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6202 - accuracy: 0.6875 - val_loss: 2.7709 - val_accuracy: 0.2188\n",
"Epoch 4458/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5785 - accuracy: 0.6875 - val_loss: 2.8083 - val_accuracy: 0.2188\n",
"Epoch 4459/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5846 - accuracy: 0.6250 - val_loss: 2.8001 - val_accuracy: 0.2188\n",
"Epoch 4460/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6429 - accuracy: 0.5625 - val_loss: 2.8059 - val_accuracy: 0.2188\n",
"Epoch 4461/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5647 - accuracy: 0.7500 - val_loss: 2.8215 - val_accuracy: 0.2188\n",
"Epoch 4462/5000\n",
"1/1 [==============================] - 0s 212ms/step - loss: 0.5638 - accuracy: 0.7188 - val_loss: 2.8248 - val_accuracy: 0.2188\n",
"Epoch 4463/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.6681 - accuracy: 0.6562 - val_loss: 2.8218 - val_accuracy: 0.2188\n",
"Epoch 4464/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.7658 - accuracy: 0.6250 - val_loss: 2.9049 - val_accuracy: 0.2188\n",
"Epoch 4465/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5340 - accuracy: 0.6875 - val_loss: 2.8711 - val_accuracy: 0.2188\n",
"Epoch 4466/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5775 - accuracy: 0.6562 - val_loss: 2.8985 - val_accuracy: 0.2188\n",
"Epoch 4467/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6479 - accuracy: 0.6875 - val_loss: 2.9408 - val_accuracy: 0.2188\n",
"Epoch 4468/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.6615 - accuracy: 0.6250 - val_loss: 2.9340 - val_accuracy: 0.2188\n",
"Epoch 4469/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5080 - accuracy: 0.6562 - val_loss: 2.8982 - val_accuracy: 0.2188\n",
"Epoch 4470/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5533 - accuracy: 0.7188 - val_loss: 2.8863 - val_accuracy: 0.2188\n",
"Epoch 4471/5000\n",
"1/1 [==============================] - 0s 211ms/step - loss: 0.6022 - accuracy: 0.6250 - val_loss: 2.8970 - val_accuracy: 0.2188\n",
"Epoch 4472/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.6296 - accuracy: 0.7500 - val_loss: 2.9309 - val_accuracy: 0.2188\n",
"Epoch 4473/5000\n",
"1/1 [==============================] - 0s 210ms/step - loss: 0.6286 - accuracy: 0.6562 - val_loss: 2.9231 - val_accuracy: 0.2188\n",
"Epoch 4474/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5144 - accuracy: 0.7500 - val_loss: 2.9317 - val_accuracy: 0.2188\n",
"Epoch 4475/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6496 - accuracy: 0.6875 - val_loss: 2.9058 - val_accuracy: 0.2188\n",
"Epoch 4476/5000\n",
"1/1 [==============================] - 0s 213ms/step - loss: 0.5846 - accuracy: 0.7188 - val_loss: 2.9255 - val_accuracy: 0.2188\n",
"Epoch 4477/5000\n",
"1/1 [==============================] - 0s 203ms/step - loss: 0.5648 - accuracy: 0.5625 - val_loss: 2.9263 - val_accuracy: 0.2188\n",
"Epoch 4478/5000\n",
"1/1 [==============================] - 0s 211ms/step - loss: 0.5402 - accuracy: 0.5938 - val_loss: 2.9482 - val_accuracy: 0.2188\n",
"Epoch 4479/5000\n",
"1/1 [==============================] - 0s 222ms/step - loss: 0.5320 - accuracy: 0.7188 - val_loss: 2.9457 - val_accuracy: 0.2188\n",
"Epoch 4480/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5372 - accuracy: 0.7812 - val_loss: 2.9945 - val_accuracy: 0.2188\n",
"Epoch 4481/5000\n",
"1/1 [==============================] - 0s 210ms/step - loss: 0.5352 - accuracy: 0.6875 - val_loss: 2.9595 - val_accuracy: 0.2188\n",
"Epoch 4482/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.5237 - accuracy: 0.7812 - val_loss: 2.9679 - val_accuracy: 0.2188\n",
"Epoch 4483/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.6691 - accuracy: 0.6562 - val_loss: 2.9829 - val_accuracy: 0.2188\n",
"Epoch 4484/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5205 - accuracy: 0.6562 - val_loss: 2.9714 - val_accuracy: 0.2188\n",
"Epoch 4485/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5511 - accuracy: 0.5938 - val_loss: 2.9699 - val_accuracy: 0.2188\n",
"Epoch 4486/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6490 - accuracy: 0.5938 - val_loss: 2.9678 - val_accuracy: 0.2188\n",
"Epoch 4487/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.6029 - accuracy: 0.5938 - val_loss: 3.0312 - val_accuracy: 0.2188\n",
"Epoch 4488/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4944 - accuracy: 0.6875 - val_loss: 2.9595 - val_accuracy: 0.2188\n",
"Epoch 4489/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5962 - accuracy: 0.5938 - val_loss: 2.9991 - val_accuracy: 0.2188\n",
"Epoch 4490/5000\n",
"1/1 [==============================] - 0s 203ms/step - loss: 0.7091 - accuracy: 0.6250 - val_loss: 3.1493 - val_accuracy: 0.2188\n",
"Epoch 4491/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.8121 - accuracy: 0.5312 - val_loss: 3.1677 - val_accuracy: 0.2188\n",
"Epoch 4492/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6395 - accuracy: 0.6562 - val_loss: 3.0811 - val_accuracy: 0.2188\n",
"Epoch 4493/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.6491 - accuracy: 0.5938 - val_loss: 3.1548 - val_accuracy: 0.2188\n",
"Epoch 4494/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6301 - accuracy: 0.5312 - val_loss: 3.0468 - val_accuracy: 0.2188\n",
"Epoch 4495/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4704 - accuracy: 0.7812 - val_loss: 3.0751 - val_accuracy: 0.2188\n",
"Epoch 4496/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.5527 - accuracy: 0.6250 - val_loss: 3.0849 - val_accuracy: 0.2188\n",
"Epoch 4497/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.3932 - accuracy: 0.8438 - val_loss: 3.1158 - val_accuracy: 0.2188\n",
"Epoch 4498/5000\n",
"1/1 [==============================] - 0s 223ms/step - loss: 0.5267 - accuracy: 0.7500 - val_loss: 3.0832 - val_accuracy: 0.2188\n",
"Epoch 4499/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.5673 - accuracy: 0.6875 - val_loss: 3.0949 - val_accuracy: 0.1875\n",
"Epoch 4500/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.3922 - accuracy: 0.7500 - val_loss: 3.0780 - val_accuracy: 0.2188\n",
"Epoch 4501/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 0.4817 - accuracy: 0.6875 - val_loss: 3.0960 - val_accuracy: 0.1875\n",
"Epoch 4502/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.5575 - accuracy: 0.6875 - val_loss: 3.0581 - val_accuracy: 0.2188\n",
"Epoch 4503/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5456 - accuracy: 0.7188 - val_loss: 3.1034 - val_accuracy: 0.2188\n",
"Epoch 4504/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5561 - accuracy: 0.6562 - val_loss: 3.1054 - val_accuracy: 0.2188\n",
"Epoch 4505/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6179 - accuracy: 0.5938 - val_loss: 3.1526 - val_accuracy: 0.2188\n",
"Epoch 4506/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.4590 - accuracy: 0.6562 - val_loss: 3.1566 - val_accuracy: 0.2188\n",
"Epoch 4507/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.5831 - accuracy: 0.6875 - val_loss: 3.1608 - val_accuracy: 0.2188\n",
"Epoch 4508/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 0.5032 - accuracy: 0.7188 - val_loss: 3.1212 - val_accuracy: 0.2188\n",
"Epoch 4509/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.5653 - accuracy: 0.7188 - val_loss: 3.2578 - val_accuracy: 0.2188\n",
"Epoch 4510/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5137 - accuracy: 0.6875 - val_loss: 3.1497 - val_accuracy: 0.2188\n",
"Epoch 4511/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5616 - accuracy: 0.7500 - val_loss: 3.1582 - val_accuracy: 0.2188\n",
"Epoch 4512/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5006 - accuracy: 0.8438 - val_loss: 3.2215 - val_accuracy: 0.2188\n",
"Epoch 4513/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5333 - accuracy: 0.7188 - val_loss: 3.2006 - val_accuracy: 0.1875\n",
"Epoch 4514/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5325 - accuracy: 0.6875 - val_loss: 3.2310 - val_accuracy: 0.2188\n",
"Epoch 4515/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5878 - accuracy: 0.7188 - val_loss: 3.2025 - val_accuracy: 0.1875\n",
"Epoch 4516/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5780 - accuracy: 0.6250 - val_loss: 3.2474 - val_accuracy: 0.2188\n",
"Epoch 4517/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.4248 - accuracy: 0.8125 - val_loss: 3.1862 - val_accuracy: 0.2188\n",
"Epoch 4518/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.4461 - accuracy: 0.6875 - val_loss: 3.2558 - val_accuracy: 0.2188\n",
"Epoch 4519/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5072 - accuracy: 0.7812 - val_loss: 3.1780 - val_accuracy: 0.1875\n",
"Epoch 4520/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5434 - accuracy: 0.6875 - val_loss: 3.2159 - val_accuracy: 0.2188\n",
"Epoch 4521/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5655 - accuracy: 0.6875 - val_loss: 3.2390 - val_accuracy: 0.2188\n",
"Epoch 4522/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5337 - accuracy: 0.7188 - val_loss: 3.2271 - val_accuracy: 0.1875\n",
"Epoch 4523/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5522 - accuracy: 0.5938 - val_loss: 3.2503 - val_accuracy: 0.2188\n",
"Epoch 4524/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5279 - accuracy: 0.7188 - val_loss: 3.2044 - val_accuracy: 0.2188\n",
"Epoch 4525/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5831 - accuracy: 0.5938 - val_loss: 3.2519 - val_accuracy: 0.2188\n",
"Epoch 4526/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5789 - accuracy: 0.7188 - val_loss: 3.2166 - val_accuracy: 0.2188\n",
"Epoch 4527/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5284 - accuracy: 0.5938 - val_loss: 3.2088 - val_accuracy: 0.2188\n",
"Epoch 4528/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5328 - accuracy: 0.7188 - val_loss: 3.2140 - val_accuracy: 0.2188\n",
"Epoch 4529/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5774 - accuracy: 0.5625 - val_loss: 3.2069 - val_accuracy: 0.2188\n",
"Epoch 4530/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5604 - accuracy: 0.7188 - val_loss: 3.2403 - val_accuracy: 0.2188\n",
"Epoch 4531/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4844 - accuracy: 0.7500 - val_loss: 3.2145 - val_accuracy: 0.2188\n",
"Epoch 4532/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5135 - accuracy: 0.5625 - val_loss: 3.2184 - val_accuracy: 0.2188\n",
"Epoch 4533/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5340 - accuracy: 0.7500 - val_loss: 3.2545 - val_accuracy: 0.1875\n",
"Epoch 4534/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5243 - accuracy: 0.7188 - val_loss: 3.1950 - val_accuracy: 0.1875\n",
"Epoch 4535/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.4887 - accuracy: 0.7188 - val_loss: 3.2629 - val_accuracy: 0.2188\n",
"Epoch 4536/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.4924 - accuracy: 0.6250 - val_loss: 3.2328 - val_accuracy: 0.2188\n",
"Epoch 4537/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5321 - accuracy: 0.6562 - val_loss: 3.2673 - val_accuracy: 0.2188\n",
"Epoch 4538/5000\n",
"1/1 [==============================] - 0s 215ms/step - loss: 0.4945 - accuracy: 0.7500 - val_loss: 3.2536 - val_accuracy: 0.2188\n",
"Epoch 4539/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 0.4215 - accuracy: 0.7812 - val_loss: 3.3516 - val_accuracy: 0.2188\n",
"Epoch 4540/5000\n",
"1/1 [==============================] - 0s 230ms/step - loss: 0.5111 - accuracy: 0.7188 - val_loss: 3.2642 - val_accuracy: 0.1875\n",
"Epoch 4541/5000\n",
"1/1 [==============================] - 0s 215ms/step - loss: 0.5116 - accuracy: 0.6562 - val_loss: 3.2448 - val_accuracy: 0.1875\n",
"Epoch 4542/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4393 - accuracy: 0.7188 - val_loss: 3.2577 - val_accuracy: 0.2188\n",
"Epoch 4543/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.3693 - accuracy: 0.7812 - val_loss: 3.2466 - val_accuracy: 0.2188\n",
"Epoch 4544/5000\n",
"1/1 [==============================] - 0s 230ms/step - loss: 0.4310 - accuracy: 0.6875 - val_loss: 3.2487 - val_accuracy: 0.1875\n",
"Epoch 4545/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5471 - accuracy: 0.6875 - val_loss: 3.3626 - val_accuracy: 0.2188\n",
"Epoch 4546/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5037 - accuracy: 0.6250 - val_loss: 3.2687 - val_accuracy: 0.2188\n",
"Epoch 4547/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5098 - accuracy: 0.6562 - val_loss: 3.2939 - val_accuracy: 0.2188\n",
"Epoch 4548/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.4860 - accuracy: 0.6875 - val_loss: 3.2768 - val_accuracy: 0.2188\n",
"Epoch 4549/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4962 - accuracy: 0.6875 - val_loss: 3.2718 - val_accuracy: 0.2188\n",
"Epoch 4550/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5559 - accuracy: 0.6250 - val_loss: 3.2931 - val_accuracy: 0.2188\n",
"Epoch 4551/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5352 - accuracy: 0.6562 - val_loss: 3.3087 - val_accuracy: 0.2188\n",
"Epoch 4552/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5884 - accuracy: 0.6875 - val_loss: 3.2500 - val_accuracy: 0.1875\n",
"Epoch 4553/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 0.4884 - accuracy: 0.7812 - val_loss: 3.2921 - val_accuracy: 0.2188\n",
"Epoch 4554/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4564 - accuracy: 0.7188 - val_loss: 3.2999 - val_accuracy: 0.2188\n",
"Epoch 4555/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5027 - accuracy: 0.7188 - val_loss: 3.2727 - val_accuracy: 0.1875\n",
"Epoch 4556/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5617 - accuracy: 0.7188 - val_loss: 3.4611 - val_accuracy: 0.1875\n",
"Epoch 4557/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4857 - accuracy: 0.6875 - val_loss: 3.3269 - val_accuracy: 0.2188\n",
"Epoch 4558/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 0.6182 - accuracy: 0.6875 - val_loss: 3.3637 - val_accuracy: 0.2188\n",
"Epoch 4559/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.4202 - accuracy: 0.8438 - val_loss: 3.3109 - val_accuracy: 0.2188\n",
"Epoch 4560/5000\n",
"1/1 [==============================] - 0s 211ms/step - loss: 0.4441 - accuracy: 0.6562 - val_loss: 3.3037 - val_accuracy: 0.2188\n",
"Epoch 4561/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.5437 - accuracy: 0.7188 - val_loss: 3.3707 - val_accuracy: 0.1875\n",
"Epoch 4562/5000\n",
"1/1 [==============================] - 0s 208ms/step - loss: 0.4842 - accuracy: 0.6562 - val_loss: 3.3148 - val_accuracy: 0.2188\n",
"Epoch 4563/5000\n",
"1/1 [==============================] - 0s 210ms/step - loss: 0.4651 - accuracy: 0.6875 - val_loss: 3.2979 - val_accuracy: 0.2188\n",
"Epoch 4564/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5636 - accuracy: 0.7188 - val_loss: 3.3788 - val_accuracy: 0.1875\n",
"Epoch 4565/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.4507 - accuracy: 0.7188 - val_loss: 3.3332 - val_accuracy: 0.2188\n",
"Epoch 4566/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5105 - accuracy: 0.6562 - val_loss: 3.3506 - val_accuracy: 0.1875\n",
"Epoch 4567/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.5115 - accuracy: 0.65 - 0s 177ms/step - loss: 0.5115 - accuracy: 0.6562 - val_loss: 3.4148 - val_accuracy: 0.2188\n",
"Epoch 4568/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 0.5588 - accuracy: 0.6875 - val_loss: 3.3921 - val_accuracy: 0.2188\n",
"Epoch 4569/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.4904 - accuracy: 0.7188 - val_loss: 3.3398 - val_accuracy: 0.1875\n",
"Epoch 4570/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5566 - accuracy: 0.6562 - val_loss: 3.4009 - val_accuracy: 0.1875\n",
"Epoch 4571/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5465 - accuracy: 0.6562 - val_loss: 3.3417 - val_accuracy: 0.1875\n",
"Epoch 4572/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4819 - accuracy: 0.7500 - val_loss: 3.4003 - val_accuracy: 0.1875\n",
"Epoch 4573/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.5073 - accuracy: 0.6250 - val_loss: 3.3416 - val_accuracy: 0.1875\n",
"Epoch 4574/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4331 - accuracy: 0.7812 - val_loss: 3.3181 - val_accuracy: 0.1875\n",
"Epoch 4575/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.5208 - accuracy: 0.7188 - val_loss: 3.3672 - val_accuracy: 0.2188\n",
"Epoch 4576/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5521 - accuracy: 0.6562 - val_loss: 3.3876 - val_accuracy: 0.1875\n",
"Epoch 4577/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5632 - accuracy: 0.5625 - val_loss: 3.3496 - val_accuracy: 0.2188\n",
"Epoch 4578/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4120 - accuracy: 0.8438 - val_loss: 3.3888 - val_accuracy: 0.1875\n",
"Epoch 4579/5000\n",
"1/1 [==============================] - 0s 208ms/step - loss: 0.5157 - accuracy: 0.6562 - val_loss: 3.2786 - val_accuracy: 0.1875\n",
"Epoch 4580/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5887 - accuracy: 0.6875 - val_loss: 3.5323 - val_accuracy: 0.2188\n",
"Epoch 4581/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5997 - accuracy: 0.6562 - val_loss: 3.3402 - val_accuracy: 0.1875\n",
"Epoch 4582/5000\n",
"1/1 [==============================] - 0s 206ms/step - loss: 0.4749 - accuracy: 0.7188 - val_loss: 3.4196 - val_accuracy: 0.2188\n",
"Epoch 4583/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.4710 - accuracy: 0.7812 - val_loss: 3.4363 - val_accuracy: 0.2188\n",
"Epoch 4584/5000\n",
"1/1 [==============================] - 0s 205ms/step - loss: 0.5528 - accuracy: 0.7500 - val_loss: 3.3663 - val_accuracy: 0.2188\n",
"Epoch 4585/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 0.4390 - accuracy: 0.6875 - val_loss: 3.3920 - val_accuracy: 0.2188\n",
"Epoch 4586/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.4636 - accuracy: 0.6875 - val_loss: 3.4147 - val_accuracy: 0.2188\n",
"Epoch 4587/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4811 - accuracy: 0.6875 - val_loss: 3.3998 - val_accuracy: 0.2188\n",
"Epoch 4588/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.4985 - accuracy: 0.6875 - val_loss: 3.5160 - val_accuracy: 0.1875\n",
"Epoch 4589/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4699 - accuracy: 0.6250 - val_loss: 3.3770 - val_accuracy: 0.1875\n",
"Epoch 4590/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.4897 - accuracy: 0.6562 - val_loss: 3.4902 - val_accuracy: 0.1875\n",
"Epoch 4591/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5427 - accuracy: 0.6875 - val_loss: 3.3530 - val_accuracy: 0.1562\n",
"Epoch 4592/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4521 - accuracy: 0.7500 - val_loss: 3.5336 - val_accuracy: 0.1875\n",
"Epoch 4593/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.4596 - accuracy: 0.7500 - val_loss: 3.4336 - val_accuracy: 0.2188\n",
"Epoch 4594/5000\n",
"1/1 [==============================] - 0s 227ms/step - loss: 0.5632 - accuracy: 0.6562 - val_loss: 3.4470 - val_accuracy: 0.2188\n",
"Epoch 4595/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5789 - accuracy: 0.6562 - val_loss: 3.4297 - val_accuracy: 0.2188\n",
"Epoch 4596/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5350 - accuracy: 0.6875 - val_loss: 3.5074 - val_accuracy: 0.2188\n",
"Epoch 4597/5000\n",
"1/1 [==============================] - 0s 231ms/step - loss: 0.4098 - accuracy: 0.7812 - val_loss: 3.5110 - val_accuracy: 0.2188\n",
"Epoch 4598/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.4969 - accuracy: 0.6875 - val_loss: 3.5262 - val_accuracy: 0.2188\n",
"Epoch 4599/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.4445 - accuracy: 0.7500 - val_loss: 3.4534 - val_accuracy: 0.1875\n",
"Epoch 4600/5000\n",
"1/1 [==============================] - 0s 236ms/step - loss: 0.5481 - accuracy: 0.7812 - val_loss: 3.4735 - val_accuracy: 0.1875\n",
"Epoch 4601/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4990 - accuracy: 0.7812 - val_loss: 3.4847 - val_accuracy: 0.2188\n",
"Epoch 4602/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.4660 - accuracy: 0.7188 - val_loss: 3.5266 - val_accuracy: 0.2188\n",
"Epoch 4603/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5395 - accuracy: 0.6875 - val_loss: 3.5216 - val_accuracy: 0.2188\n",
"Epoch 4604/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4160 - accuracy: 0.7188 - val_loss: 3.4743 - val_accuracy: 0.1875\n",
"Epoch 4605/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.4670 - accuracy: 0.7188 - val_loss: 3.4567 - val_accuracy: 0.2188\n",
"Epoch 4606/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4755 - accuracy: 0.7500 - val_loss: 3.4485 - val_accuracy: 0.2188\n",
"Epoch 4607/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4954 - accuracy: 0.6562 - val_loss: 3.4284 - val_accuracy: 0.2188\n",
"Epoch 4608/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5320 - accuracy: 0.7188 - val_loss: 3.6142 - val_accuracy: 0.1875\n",
"Epoch 4609/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.4026 - accuracy: 0.7500 - val_loss: 3.4640 - val_accuracy: 0.1875\n",
"Epoch 4610/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4697 - accuracy: 0.7812 - val_loss: 3.4407 - val_accuracy: 0.1875\n",
"Epoch 4611/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.5170 - accuracy: 0.6562 - val_loss: 3.5218 - val_accuracy: 0.2188\n",
"Epoch 4612/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5092 - accuracy: 0.7188 - val_loss: 3.4640 - val_accuracy: 0.2188\n",
"Epoch 4613/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5086 - accuracy: 0.6562 - val_loss: 3.4706 - val_accuracy: 0.2188\n",
"Epoch 4614/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4586 - accuracy: 0.7500 - val_loss: 3.4818 - val_accuracy: 0.2188\n",
"Epoch 4615/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.4699 - accuracy: 0.7188 - val_loss: 3.4935 - val_accuracy: 0.2188\n",
"Epoch 4616/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.5425 - accuracy: 0.6875 - val_loss: 3.5411 - val_accuracy: 0.1875\n",
"Epoch 4617/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5555 - accuracy: 0.5938 - val_loss: 3.4900 - val_accuracy: 0.2188\n",
"Epoch 4618/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4645 - accuracy: 0.6562 - val_loss: 3.5599 - val_accuracy: 0.1875\n",
"Epoch 4619/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4018 - accuracy: 0.7188 - val_loss: 3.5435 - val_accuracy: 0.2188\n",
"Epoch 4620/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4690 - accuracy: 0.7500 - val_loss: 3.5213 - val_accuracy: 0.1875\n",
"Epoch 4621/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.3897 - accuracy: 0.7500 - val_loss: 3.5856 - val_accuracy: 0.2188\n",
"Epoch 4622/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.4025 - accuracy: 0.7188 - val_loss: 3.4816 - val_accuracy: 0.1875\n",
"Epoch 4623/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5714 - accuracy: 0.7812 - val_loss: 3.6921 - val_accuracy: 0.1875\n",
"Epoch 4624/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5402 - accuracy: 0.6250 - val_loss: 3.5169 - val_accuracy: 0.2188\n",
"Epoch 4625/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6213 - accuracy: 0.6562 - val_loss: 3.5743 - val_accuracy: 0.1875\n",
"Epoch 4626/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.4351 - accuracy: 0.6875 - val_loss: 3.4713 - val_accuracy: 0.1875\n",
"Epoch 4627/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4480 - accuracy: 0.7188 - val_loss: 3.4884 - val_accuracy: 0.2188\n",
"Epoch 4628/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5496 - accuracy: 0.7188 - val_loss: 3.5395 - val_accuracy: 0.2188\n",
"Epoch 4629/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.4655 - accuracy: 0.7188 - val_loss: 3.5003 - val_accuracy: 0.2188\n",
"Epoch 4630/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5311 - accuracy: 0.6250 - val_loss: 3.6010 - val_accuracy: 0.2188\n",
"Epoch 4631/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 0.5204 - accuracy: 0.6250 - val_loss: 3.5201 - val_accuracy: 0.1875\n",
"Epoch 4632/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 0.6074 - accuracy: 0.62 - 0s 162ms/step - loss: 0.6074 - accuracy: 0.6250 - val_loss: 3.5202 - val_accuracy: 0.2188\n",
"Epoch 4633/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4818 - accuracy: 0.7188 - val_loss: 3.5324 - val_accuracy: 0.2188\n",
"Epoch 4634/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 0.5554 - accuracy: 0.6875 - val_loss: 3.5538 - val_accuracy: 0.2188\n",
"Epoch 4635/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4872 - accuracy: 0.7500 - val_loss: 3.5545 - val_accuracy: 0.2188\n",
"Epoch 4636/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5358 - accuracy: 0.6875 - val_loss: 3.5895 - val_accuracy: 0.2188\n",
"Epoch 4637/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4072 - accuracy: 0.7812 - val_loss: 3.5643 - val_accuracy: 0.2188\n",
"Epoch 4638/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4413 - accuracy: 0.7812 - val_loss: 3.5601 - val_accuracy: 0.2188\n",
"Epoch 4639/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4350 - accuracy: 0.7188 - val_loss: 3.5150 - val_accuracy: 0.1875\n",
"Epoch 4640/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4723 - accuracy: 0.7500 - val_loss: 3.5635 - val_accuracy: 0.2188\n",
"Epoch 4641/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5175 - accuracy: 0.6562 - val_loss: 3.6048 - val_accuracy: 0.2188\n",
"Epoch 4642/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.4325 - accuracy: 0.7500 - val_loss: 3.5556 - val_accuracy: 0.2188\n",
"Epoch 4643/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6281 - accuracy: 0.5938 - val_loss: 3.5703 - val_accuracy: 0.2188\n",
"Epoch 4644/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.4074 - accuracy: 0.7812 - val_loss: 3.5432 - val_accuracy: 0.1875\n",
"Epoch 4645/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.4425 - accuracy: 0.7500 - val_loss: 3.6364 - val_accuracy: 0.2188\n",
"Epoch 4646/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5049 - accuracy: 0.7188 - val_loss: 3.5760 - val_accuracy: 0.1875\n",
"Epoch 4647/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5989 - accuracy: 0.6562 - val_loss: 3.5664 - val_accuracy: 0.2188\n",
"Epoch 4648/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5550 - accuracy: 0.7500 - val_loss: 3.6196 - val_accuracy: 0.1875\n",
"Epoch 4649/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.4760 - accuracy: 0.6562 - val_loss: 3.5837 - val_accuracy: 0.1875\n",
"Epoch 4650/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.6134 - accuracy: 0.6562 - val_loss: 3.5384 - val_accuracy: 0.2188\n",
"Epoch 4651/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4321 - accuracy: 0.6875 - val_loss: 3.6632 - val_accuracy: 0.1875\n",
"Epoch 4652/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4247 - accuracy: 0.7188 - val_loss: 3.5912 - val_accuracy: 0.2188\n",
"Epoch 4653/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4997 - accuracy: 0.7812 - val_loss: 3.6365 - val_accuracy: 0.1875\n",
"Epoch 4654/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5495 - accuracy: 0.6875 - val_loss: 3.6083 - val_accuracy: 0.1875\n",
"Epoch 4655/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.4625 - accuracy: 0.7188 - val_loss: 3.5954 - val_accuracy: 0.1875\n",
"Epoch 4656/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4373 - accuracy: 0.6562 - val_loss: 3.4447 - val_accuracy: 0.1875\n",
"Epoch 4657/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4604 - accuracy: 0.6875 - val_loss: 3.5905 - val_accuracy: 0.1875\n",
"Epoch 4658/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5171 - accuracy: 0.6562 - val_loss: 3.4903 - val_accuracy: 0.1875\n",
"Epoch 4659/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.4897 - accuracy: 0.7188 - val_loss: 3.6408 - val_accuracy: 0.1875\n",
"Epoch 4660/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.4600 - accuracy: 0.7188 - val_loss: 3.5497 - val_accuracy: 0.1875\n",
"Epoch 4661/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5584 - accuracy: 0.6875 - val_loss: 3.5428 - val_accuracy: 0.2188\n",
"Epoch 4662/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5493 - accuracy: 0.5938 - val_loss: 3.5704 - val_accuracy: 0.2188\n",
"Epoch 4663/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5572 - accuracy: 0.7188 - val_loss: 3.6633 - val_accuracy: 0.1875\n",
"Epoch 4664/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4825 - accuracy: 0.7188 - val_loss: 3.5950 - val_accuracy: 0.2188\n",
"Epoch 4665/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4916 - accuracy: 0.8125 - val_loss: 3.6316 - val_accuracy: 0.2188\n",
"Epoch 4666/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.4515 - accuracy: 0.7188 - val_loss: 3.6211 - val_accuracy: 0.2188\n",
"Epoch 4667/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4565 - accuracy: 0.7188 - val_loss: 3.6590 - val_accuracy: 0.2188\n",
"Epoch 4668/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.4699 - accuracy: 0.7812 - val_loss: 3.6191 - val_accuracy: 0.2188\n",
"Epoch 4669/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4663 - accuracy: 0.7812 - val_loss: 3.6240 - val_accuracy: 0.2188\n",
"Epoch 4670/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.3645 - accuracy: 0.7812 - val_loss: 3.6078 - val_accuracy: 0.1875\n",
"Epoch 4671/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5108 - accuracy: 0.6562 - val_loss: 3.6990 - val_accuracy: 0.1875\n",
"Epoch 4672/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.5305 - accuracy: 0.7188 - val_loss: 3.5931 - val_accuracy: 0.2188\n",
"Epoch 4673/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4432 - accuracy: 0.6562 - val_loss: 3.5980 - val_accuracy: 0.2188\n",
"Epoch 4674/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.4606 - accuracy: 0.7188 - val_loss: 3.5934 - val_accuracy: 0.2188\n",
"Epoch 4675/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6174 - accuracy: 0.5938 - val_loss: 3.7460 - val_accuracy: 0.2188\n",
"Epoch 4676/5000\n",
"1/1 [==============================] - 0s 152ms/step - loss: 0.4583 - accuracy: 0.6250 - val_loss: 3.5519 - val_accuracy: 0.1875\n",
"Epoch 4677/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4693 - accuracy: 0.7188 - val_loss: 3.5814 - val_accuracy: 0.2188\n",
"Epoch 4678/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5313 - accuracy: 0.6875 - val_loss: 3.7215 - val_accuracy: 0.1875\n",
"Epoch 4679/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4153 - accuracy: 0.8125 - val_loss: 3.6171 - val_accuracy: 0.2188\n",
"Epoch 4680/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.3702 - accuracy: 0.7500 - val_loss: 3.5557 - val_accuracy: 0.1875\n",
"Epoch 4681/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6030 - accuracy: 0.6562 - val_loss: 3.6729 - val_accuracy: 0.1875\n",
"Epoch 4682/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.4378 - accuracy: 0.7188 - val_loss: 3.5588 - val_accuracy: 0.1875\n",
"Epoch 4683/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5467 - accuracy: 0.7188 - val_loss: 3.6686 - val_accuracy: 0.1875\n",
"Epoch 4684/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.4092 - accuracy: 0.7500 - val_loss: 3.5745 - val_accuracy: 0.2188\n",
"Epoch 4685/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5094 - accuracy: 0.7188 - val_loss: 3.6462 - val_accuracy: 0.1875\n",
"Epoch 4686/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.5118 - accuracy: 0.6562 - val_loss: 3.6036 - val_accuracy: 0.2188\n",
"Epoch 4687/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4349 - accuracy: 0.8125 - val_loss: 3.6324 - val_accuracy: 0.2188\n",
"Epoch 4688/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.4319 - accuracy: 0.8125 - val_loss: 3.6599 - val_accuracy: 0.2188\n",
"Epoch 4689/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4149 - accuracy: 0.7500 - val_loss: 3.6861 - val_accuracy: 0.1875\n",
"Epoch 4690/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.4867 - accuracy: 0.7188 - val_loss: 3.6543 - val_accuracy: 0.2188\n",
"Epoch 4691/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.6265 - accuracy: 0.5312 - val_loss: 3.6687 - val_accuracy: 0.2188\n",
"Epoch 4692/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5649 - accuracy: 0.6250 - val_loss: 3.6413 - val_accuracy: 0.1875\n",
"Epoch 4693/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5046 - accuracy: 0.6875 - val_loss: 3.5609 - val_accuracy: 0.1875\n",
"Epoch 4694/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.5848 - accuracy: 0.7500 - val_loss: 3.7981 - val_accuracy: 0.1562\n",
"Epoch 4695/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.4398 - accuracy: 0.6562 - val_loss: 3.4836 - val_accuracy: 0.1875\n",
"Epoch 4696/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5687 - accuracy: 0.6562 - val_loss: 3.8586 - val_accuracy: 0.1875\n",
"Epoch 4697/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5579 - accuracy: 0.6562 - val_loss: 3.5554 - val_accuracy: 0.1875\n",
"Epoch 4698/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5994 - accuracy: 0.6250 - val_loss: 3.9494 - val_accuracy: 0.2188\n",
"Epoch 4699/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5931 - accuracy: 0.5000 - val_loss: 3.5487 - val_accuracy: 0.1562\n",
"Epoch 4700/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5385 - accuracy: 0.7188 - val_loss: 3.8585 - val_accuracy: 0.2188\n",
"Epoch 4701/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4635 - accuracy: 0.6875 - val_loss: 3.6105 - val_accuracy: 0.2188\n",
"Epoch 4702/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5664 - accuracy: 0.6875 - val_loss: 3.7381 - val_accuracy: 0.1875\n",
"Epoch 4703/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5075 - accuracy: 0.7188 - val_loss: 3.6847 - val_accuracy: 0.2188\n",
"Epoch 4704/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5580 - accuracy: 0.5312 - val_loss: 3.7096 - val_accuracy: 0.2188\n",
"Epoch 4705/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5029 - accuracy: 0.7500 - val_loss: 3.6724 - val_accuracy: 0.2188\n",
"Epoch 4706/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5593 - accuracy: 0.5938 - val_loss: 3.6747 - val_accuracy: 0.1875\n",
"Epoch 4707/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.4509 - accuracy: 0.8125 - val_loss: 3.6516 - val_accuracy: 0.1875\n",
"Epoch 4708/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4866 - accuracy: 0.6250 - val_loss: 3.7396 - val_accuracy: 0.1875\n",
"Epoch 4709/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4201 - accuracy: 0.7812 - val_loss: 3.6057 - val_accuracy: 0.2188\n",
"Epoch 4710/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4047 - accuracy: 0.7188 - val_loss: 3.6724 - val_accuracy: 0.2188\n",
"Epoch 4711/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4488 - accuracy: 0.7188 - val_loss: 3.6073 - val_accuracy: 0.2188\n",
"Epoch 4712/5000\n",
"1/1 [==============================] - 0s 184ms/step - loss: 0.4728 - accuracy: 0.7812 - val_loss: 3.6984 - val_accuracy: 0.2188\n",
"Epoch 4713/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4979 - accuracy: 0.6562 - val_loss: 3.6706 - val_accuracy: 0.2188\n",
"Epoch 4714/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.4810 - accuracy: 0.7188 - val_loss: 3.6523 - val_accuracy: 0.2188\n",
"Epoch 4715/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5825 - accuracy: 0.6562 - val_loss: 3.6711 - val_accuracy: 0.1875\n",
"Epoch 4716/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 0.5453 - accuracy: 0.7812 - val_loss: 3.6570 - val_accuracy: 0.2188\n",
"Epoch 4717/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.4960 - accuracy: 0.7812 - val_loss: 3.7173 - val_accuracy: 0.1875\n",
"Epoch 4718/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 0.3802 - accuracy: 0.7500 - val_loss: 3.6236 - val_accuracy: 0.2188\n",
"Epoch 4719/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5668 - accuracy: 0.6562 - val_loss: 3.7283 - val_accuracy: 0.1875\n",
"Epoch 4720/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5278 - accuracy: 0.6250 - val_loss: 3.6037 - val_accuracy: 0.1875\n",
"Epoch 4721/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.4867 - accuracy: 0.7500 - val_loss: 3.7831 - val_accuracy: 0.2188\n",
"Epoch 4722/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5936 - accuracy: 0.6250 - val_loss: 3.5343 - val_accuracy: 0.1875\n",
"Epoch 4723/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.3532 - accuracy: 0.7500 - val_loss: 3.6402 - val_accuracy: 0.2188\n",
"Epoch 4724/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.4183 - accuracy: 0.7500 - val_loss: 3.6627 - val_accuracy: 0.2188\n",
"Epoch 4725/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4033 - accuracy: 0.7812 - val_loss: 3.6724 - val_accuracy: 0.2188\n",
"Epoch 4726/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.3505 - accuracy: 0.7500 - val_loss: 3.7144 - val_accuracy: 0.2188\n",
"Epoch 4727/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.4951 - accuracy: 0.7188 - val_loss: 3.6564 - val_accuracy: 0.2188\n",
"Epoch 4728/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.3998 - accuracy: 0.6875 - val_loss: 3.7523 - val_accuracy: 0.1875\n",
"Epoch 4729/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.5008 - accuracy: 0.6562 - val_loss: 3.6598 - val_accuracy: 0.1562\n",
"Epoch 4730/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5052 - accuracy: 0.6562 - val_loss: 3.7727 - val_accuracy: 0.2188\n",
"Epoch 4731/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.4275 - accuracy: 0.7500 - val_loss: 3.6965 - val_accuracy: 0.1875\n",
"Epoch 4732/5000\n",
"1/1 [==============================] - 0s 192ms/step - loss: 0.5129 - accuracy: 0.7500 - val_loss: 3.7718 - val_accuracy: 0.1875\n",
"Epoch 4733/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.3943 - accuracy: 0.7500 - val_loss: 3.5911 - val_accuracy: 0.1875\n",
"Epoch 4734/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 0.5419 - accuracy: 0.7500 - val_loss: 3.8582 - val_accuracy: 0.1875\n",
"Epoch 4735/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.5316 - accuracy: 0.6562 - val_loss: 3.6818 - val_accuracy: 0.2188\n",
"Epoch 4736/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4236 - accuracy: 0.6562 - val_loss: 3.8279 - val_accuracy: 0.1875\n",
"Epoch 4737/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5540 - accuracy: 0.6250 - val_loss: 3.6694 - val_accuracy: 0.2188\n",
"Epoch 4738/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.4529 - accuracy: 0.6562 - val_loss: 3.7421 - val_accuracy: 0.2188\n",
"Epoch 4739/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.6426 - accuracy: 0.7500 - val_loss: 3.9750 - val_accuracy: 0.2188\n",
"Epoch 4740/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5495 - accuracy: 0.7188 - val_loss: 3.6477 - val_accuracy: 0.1875\n",
"Epoch 4741/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.5916 - accuracy: 0.6250 - val_loss: 3.8901 - val_accuracy: 0.2188\n",
"Epoch 4742/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.6042 - accuracy: 0.5625 - val_loss: 3.5667 - val_accuracy: 0.1562\n",
"Epoch 4743/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5209 - accuracy: 0.7188 - val_loss: 3.9381 - val_accuracy: 0.1875\n",
"Epoch 4744/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7100 - accuracy: 0.5938 - val_loss: 3.5633 - val_accuracy: 0.1562\n",
"Epoch 4745/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.7274 - accuracy: 0.5312 - val_loss: 4.0571 - val_accuracy: 0.1562\n",
"Epoch 4746/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.7485 - accuracy: 0.5000 - val_loss: 3.5461 - val_accuracy: 0.1875\n",
"Epoch 4747/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.3831 - accuracy: 0.7812 - val_loss: 3.6857 - val_accuracy: 0.2188\n",
"Epoch 4748/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4058 - accuracy: 0.7500 - val_loss: 3.6944 - val_accuracy: 0.1875\n",
"Epoch 4749/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.3705 - accuracy: 0.7500 - val_loss: 3.6744 - val_accuracy: 0.1875\n",
"Epoch 4750/5000\n",
"1/1 [==============================] - 0s 187ms/step - loss: 0.5373 - accuracy: 0.6562 - val_loss: 3.7168 - val_accuracy: 0.2188\n",
"Epoch 4751/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.4164 - accuracy: 0.7500 - val_loss: 3.7745 - val_accuracy: 0.2188\n",
"Epoch 4752/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.4499 - accuracy: 0.5938 - val_loss: 3.7443 - val_accuracy: 0.1875\n",
"Epoch 4753/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5478 - accuracy: 0.6875 - val_loss: 3.7458 - val_accuracy: 0.2188\n",
"Epoch 4754/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 0.5445 - accuracy: 0.6875 - val_loss: 3.7461 - val_accuracy: 0.2188\n",
"Epoch 4755/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 0.4407 - accuracy: 0.6562 - val_loss: 3.7871 - val_accuracy: 0.2188\n",
"Epoch 4756/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.4806 - accuracy: 0.6875 - val_loss: 3.7127 - val_accuracy: 0.1875\n",
"Epoch 4757/5000\n",
"1/1 [==============================] - 0s 185ms/step - loss: 0.4129 - accuracy: 0.6562 - val_loss: 3.7473 - val_accuracy: 0.2188\n",
"Epoch 4758/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.4375 - accuracy: 0.7188 - val_loss: 3.7433 - val_accuracy: 0.2188\n",
"Epoch 4759/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.4578 - accuracy: 0.7188 - val_loss: 3.7282 - val_accuracy: 0.1875\n",
"Epoch 4760/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.5214 - accuracy: 0.7188 - val_loss: 3.7258 - val_accuracy: 0.2188\n",
"Epoch 4761/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.5068 - accuracy: 0.6875 - val_loss: 3.7294 - val_accuracy: 0.2188\n",
"Epoch 4762/5000\n",
"1/1 [==============================] - 0s 211ms/step - loss: 0.4702 - accuracy: 0.6250 - val_loss: 3.7485 - val_accuracy: 0.1875\n",
"Epoch 4763/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5059 - accuracy: 0.6250 - val_loss: 3.6037 - val_accuracy: 0.1875\n",
"Epoch 4764/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.4444 - accuracy: 0.6250 - val_loss: 3.6901 - val_accuracy: 0.2188\n",
"Epoch 4765/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5756 - accuracy: 0.6875 - val_loss: 3.6988 - val_accuracy: 0.1875\n",
"Epoch 4766/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.4415 - accuracy: 0.7188 - val_loss: 3.7608 - val_accuracy: 0.1875\n",
"Epoch 4767/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.4968 - accuracy: 0.6875 - val_loss: 3.6677 - val_accuracy: 0.1562\n",
"Epoch 4768/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6858 - accuracy: 0.5938 - val_loss: 4.9387 - val_accuracy: 0.1562\n",
"Epoch 4769/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.8761 - accuracy: 0.2500 - val_loss: 5.5899 - val_accuracy: 0.3438\n",
"Epoch 4770/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 20.1536 - accuracy: 0.218 - 0s 195ms/step - loss: 20.1536 - accuracy: 0.2188 - val_loss: 2.7581 - val_accuracy: 0.0000e+00\n",
"Epoch 4771/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 6.4053 - accuracy: 0.2188 - val_loss: 4.2140 - val_accuracy: 0.0312\n",
"Epoch 4772/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 3.7533 - accuracy: 0.0625 - val_loss: 3.2418 - val_accuracy: 0.0312\n",
"Epoch 4773/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 3.5443 - accuracy: 0.0625 - val_loss: 2.3627 - val_accuracy: 0.1250\n",
"Epoch 4774/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 3.2054 - accuracy: 0.1250 - val_loss: 2.5167 - val_accuracy: 0.0312\n",
"Epoch 4775/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 2.4864 - accuracy: 0.1875 - val_loss: 2.4158 - val_accuracy: 0.0312\n",
"Epoch 4776/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 2.3568 - accuracy: 0.2188 - val_loss: 2.6429 - val_accuracy: 0.0312\n",
"Epoch 4777/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.8266 - accuracy: 0.1250 - val_loss: 2.5480 - val_accuracy: 0.0000e+00\n",
"Epoch 4778/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.9044 - accuracy: 0.1875 - val_loss: 2.4071 - val_accuracy: 0.0625\n",
"Epoch 4779/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.0159 - accuracy: 0.2812 - val_loss: 2.5849 - val_accuracy: 0.0312\n",
"Epoch 4780/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 2.0960 - accuracy: 0.15 - 0s 160ms/step - loss: 2.0960 - accuracy: 0.1562 - val_loss: 2.4039 - val_accuracy: 0.0000e+00\n",
"Epoch 4781/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 2.1229 - accuracy: 0.2500 - val_loss: 2.6555 - val_accuracy: 0.0000e+00\n",
"Epoch 4782/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.2619 - accuracy: 0.1562 - val_loss: 2.4794 - val_accuracy: 0.0000e+00\n",
"Epoch 4783/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 2.5418 - accuracy: 0.2500 - val_loss: 3.1083 - val_accuracy: 0.0312\n",
"Epoch 4784/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 2.4624 - accuracy: 0.0938 - val_loss: 2.6688 - val_accuracy: 0.0000e+00\n",
"Epoch 4785/5000\n",
"1/1 [==============================] - 0s 220ms/step - loss: 1.8463 - accuracy: 0.1875 - val_loss: 2.5202 - val_accuracy: 0.0000e+00\n",
"Epoch 4786/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 2.0986 - accuracy: 0.1562 - val_loss: 2.5695 - val_accuracy: 0.0000e+00\n",
"Epoch 4787/5000\n",
"1/1 [==============================] - 0s 193ms/step - loss: 2.0263 - accuracy: 0.3125 - val_loss: 2.8446 - val_accuracy: 0.0000e+00\n",
"Epoch 4788/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 2.5374 - accuracy: 0.0938 - val_loss: 2.6122 - val_accuracy: 0.0000e+00\n",
"Epoch 4789/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 2.1259 - accuracy: 0.2188 - val_loss: 2.5140 - val_accuracy: 0.0000e+00\n",
"Epoch 4790/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.9437 - accuracy: 0.2812 - val_loss: 2.8735 - val_accuracy: 0.0000e+00\n",
"Epoch 4791/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 2.3897 - accuracy: 0.1250 - val_loss: 2.7295 - val_accuracy: 0.0000e+00\n",
"Epoch 4792/5000\n",
"1/1 [==============================] - 0s 191ms/step - loss: 2.3615 - accuracy: 0.1562 - val_loss: 2.5766 - val_accuracy: 0.0000e+00\n",
"Epoch 4793/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 2.5360 - accuracy: 0.1562 - val_loss: 2.9241 - val_accuracy: 0.0000e+00\n",
"Epoch 4794/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 2.3887 - accuracy: 0.1875 - val_loss: 2.5599 - val_accuracy: 0.0000e+00\n",
"Epoch 4795/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 2.8499 - accuracy: 0.1562 - val_loss: 2.6966 - val_accuracy: 0.0000e+00\n",
"Epoch 4796/5000\n",
"1/1 [==============================] - 0s 190ms/step - loss: 2.1261 - accuracy: 0.2188 - val_loss: 2.6380 - val_accuracy: 0.0000e+00\n",
"Epoch 4797/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.8787 - accuracy: 0.2188 - val_loss: 2.6400 - val_accuracy: 0.0312\n",
"Epoch 4798/5000\n",
"1/1 [==============================] - 0s 204ms/step - loss: 2.3249 - accuracy: 0.1875 - val_loss: 2.7909 - val_accuracy: 0.0000e+00\n",
"Epoch 4799/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.8982 - accuracy: 0.1875 - val_loss: 2.4535 - val_accuracy: 0.1875\n",
"Epoch 4800/5000\n",
"1/1 [==============================] - 0s 199ms/step - loss: 2.1786 - accuracy: 0.3438 - val_loss: 3.3946 - val_accuracy: 0.0312\n",
"Epoch 4801/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 2.6445 - accuracy: 0.0938 - val_loss: 2.3410 - val_accuracy: 0.1562\n",
"Epoch 4802/5000\n",
"1/1 [==============================] - 0s 200ms/step - loss: 3.3415 - accuracy: 0.0938 - val_loss: 4.4618 - val_accuracy: 0.0312\n",
"Epoch 4803/5000\n",
"1/1 [==============================] - 0s 194ms/step - loss: 3.0812 - accuracy: 0.0625 - val_loss: 3.4451 - val_accuracy: 0.0000e+00\n",
"Epoch 4804/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 3.2340 - accuracy: 0.1250 - val_loss: 3.0991 - val_accuracy: 0.0312\n",
"Epoch 4805/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 2.6572 - accuracy: 0.0625 - val_loss: 2.3384 - val_accuracy: 0.0625\n",
"Epoch 4806/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.1059 - accuracy: 0.3750 - val_loss: 3.0196 - val_accuracy: 0.0000e+00\n",
"Epoch 4807/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 2.1077 - accuracy: 0.0938 - val_loss: 2.5266 - val_accuracy: 0.0312\n",
"Epoch 4808/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 1.8081 - accuracy: 0.2812 - val_loss: 2.5717 - val_accuracy: 0.0312\n",
"Epoch 4809/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.1234 - accuracy: 0.1250 - val_loss: 2.6445 - val_accuracy: 0.0000e+00\n",
"Epoch 4810/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 2.2699 - accuracy: 0.1562 - val_loss: 2.7088 - val_accuracy: 0.0000e+00\n",
"Epoch 4811/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.3669 - accuracy: 0.0938 - val_loss: 2.6380 - val_accuracy: 0.0000e+00\n",
"Epoch 4812/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.9722 - accuracy: 0.1562 - val_loss: 2.9139 - val_accuracy: 0.0000e+00\n",
"Epoch 4813/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 2.2323 - accuracy: 0.0938 - val_loss: 2.5594 - val_accuracy: 0.0312\n",
"Epoch 4814/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.8248 - accuracy: 0.2500 - val_loss: 2.8723 - val_accuracy: 0.0000e+00\n",
"Epoch 4815/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 2.2211 - accuracy: 0.1562 - val_loss: 2.6294 - val_accuracy: 0.0312\n",
"Epoch 4816/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 2.0327 - accuracy: 0.1250 - val_loss: 2.9138 - val_accuracy: 0.0000e+00\n",
"Epoch 4817/5000\n",
"1/1 [==============================] - 0s 214ms/step - loss: 2.0089 - accuracy: 0.1562 - val_loss: 2.7479 - val_accuracy: 0.0000e+00\n",
"Epoch 4818/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.9649 - accuracy: 0.0938 - val_loss: 2.7009 - val_accuracy: 0.0000e+00\n",
"Epoch 4819/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.6693 - accuracy: 0.1562 - val_loss: 2.9704 - val_accuracy: 0.0000e+00\n",
"Epoch 4820/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.8224 - accuracy: 0.2500 - val_loss: 2.7554 - val_accuracy: 0.0000e+00\n",
"Epoch 4821/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.8370 - accuracy: 0.2500 - val_loss: 2.6747 - val_accuracy: 0.0625\n",
"Epoch 4822/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.7742 - accuracy: 0.2188 - val_loss: 3.0460 - val_accuracy: 0.0000e+00\n",
"Epoch 4823/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.7185 - accuracy: 0.1875 - val_loss: 2.7311 - val_accuracy: 0.0312\n",
"Epoch 4824/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.7735 - accuracy: 0.1562 - val_loss: 3.0232 - val_accuracy: 0.0000e+00\n",
"Epoch 4825/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.9637 - accuracy: 0.0625 - val_loss: 2.6773 - val_accuracy: 0.0312\n",
"Epoch 4826/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.7955 - accuracy: 0.2500 - val_loss: 3.2079 - val_accuracy: 0.0000e+00\n",
"Epoch 4827/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 2.1713 - accuracy: 0.0938 - val_loss: 2.9579 - val_accuracy: 0.0000e+00\n",
"Epoch 4828/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 1.8919 - accuracy: 0.2500 - val_loss: 2.7375 - val_accuracy: 0.0312\n",
"Epoch 4829/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.2062 - accuracy: 0.2500 - val_loss: 3.4522 - val_accuracy: 0.0000e+00\n",
"Epoch 4830/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.1011 - accuracy: 0.1250 - val_loss: 2.7941 - val_accuracy: 0.0312\n",
"Epoch 4831/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.5497 - accuracy: 0.2812 - val_loss: 3.0980 - val_accuracy: 0.0000e+00\n",
"Epoch 4832/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 2.0170 - accuracy: 0.3125 - val_loss: 2.9946 - val_accuracy: 0.0000e+00\n",
"Epoch 4833/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.2938 - accuracy: 0.1562 - val_loss: 3.2153 - val_accuracy: 0.0000e+00\n",
"Epoch 4834/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.8797 - accuracy: 0.2188 - val_loss: 2.8390 - val_accuracy: 0.0000e+00\n",
"Epoch 4835/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.7444 - accuracy: 0.2812 - val_loss: 3.0004 - val_accuracy: 0.0000e+00\n",
"Epoch 4836/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.6330 - accuracy: 0.1875 - val_loss: 2.8685 - val_accuracy: 0.0000e+00\n",
"Epoch 4837/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.8157 - accuracy: 0.2500 - val_loss: 3.2722 - val_accuracy: 0.0000e+00\n",
"Epoch 4838/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.9375 - accuracy: 0.2500 - val_loss: 2.8336 - val_accuracy: 0.0312\n",
"Epoch 4839/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 2.1987 - accuracy: 0.1250 - val_loss: 3.1413 - val_accuracy: 0.0000e+00\n",
"Epoch 4840/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 2.2289 - accuracy: 0.1250 - val_loss: 2.8094 - val_accuracy: 0.0312\n",
"Epoch 4841/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.9027 - accuracy: 0.2812 - val_loss: 3.4193 - val_accuracy: 0.0000e+00\n",
"Epoch 4842/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.9515 - accuracy: 0.1250 - val_loss: 2.8984 - val_accuracy: 0.0312\n",
"Epoch 4843/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.9655 - accuracy: 0.1875 - val_loss: 3.6764 - val_accuracy: 0.0000e+00\n",
"Epoch 4844/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 2.0169 - accuracy: 0.2812 - val_loss: 2.8325 - val_accuracy: 0.0312\n",
"Epoch 4845/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.7400 - accuracy: 0.2188 - val_loss: 3.1743 - val_accuracy: 0.0000e+00\n",
"Epoch 4846/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 2.1922 - accuracy: 0.2188 - val_loss: 2.8090 - val_accuracy: 0.0312\n",
"Epoch 4847/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 1.5664 - accuracy: 0.1875 - val_loss: 3.0726 - val_accuracy: 0.0000e+00\n",
"Epoch 4848/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.9438 - accuracy: 0.2812 - val_loss: 3.0254 - val_accuracy: 0.0000e+00\n",
"Epoch 4849/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 1.6276 - accuracy: 0.3125 - val_loss: 3.3579 - val_accuracy: 0.0000e+00\n",
"Epoch 4850/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.6375 - accuracy: 0.0938 - val_loss: 3.1339 - val_accuracy: 0.0000e+00\n",
"Epoch 4851/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.6977 - accuracy: 0.1875 - val_loss: 3.2165 - val_accuracy: 0.0000e+00\n",
"Epoch 4852/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.5048 - accuracy: 0.1875 - val_loss: 3.0300 - val_accuracy: 0.0000e+00\n",
"Epoch 4853/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.5741 - accuracy: 0.2812 - val_loss: 3.1710 - val_accuracy: 0.0000e+00\n",
"Epoch 4854/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.7661 - accuracy: 0.2500 - val_loss: 3.2232 - val_accuracy: 0.0000e+00\n",
"Epoch 4855/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.5667 - accuracy: 0.1875 - val_loss: 3.0434 - val_accuracy: 0.0000e+00\n",
"Epoch 4856/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.6700 - accuracy: 0.3750 - val_loss: 3.4290 - val_accuracy: 0.0000e+00\n",
"Epoch 4857/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.5663 - accuracy: 0.1562 - val_loss: 3.0322 - val_accuracy: 0.0000e+00\n",
"Epoch 4858/5000\n",
"1/1 [==============================] - 0s 177ms/step - loss: 1.5531 - accuracy: 0.2500 - val_loss: 3.3345 - val_accuracy: 0.0000e+00\n",
"Epoch 4859/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.9326 - accuracy: 0.2812 - val_loss: 2.8496 - val_accuracy: 0.0938\n",
"Epoch 4860/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.8027 - accuracy: 0.1562 - val_loss: 3.1124 - val_accuracy: 0.0312\n",
"Epoch 4861/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.4373 - accuracy: 0.3438 - val_loss: 3.2362 - val_accuracy: 0.0000e+00\n",
"Epoch 4862/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 2.2818 - accuracy: 0.1250 - val_loss: 3.0343 - val_accuracy: 0.0312\n",
"Epoch 4863/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 1.5926 - accuracy: 0.1875 - val_loss: 3.3253 - val_accuracy: 0.0000e+00\n",
"Epoch 4864/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.5640 - accuracy: 0.1562 - val_loss: 3.1418 - val_accuracy: 0.0000e+00\n",
"Epoch 4865/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 2.0004 - accuracy: 0.2188 - val_loss: 3.3732 - val_accuracy: 0.0000e+00\n",
"Epoch 4866/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.4839 - accuracy: 0.1875 - val_loss: 3.0657 - val_accuracy: 0.0000e+00\n",
"Epoch 4867/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.7085 - accuracy: 0.2812 - val_loss: 3.0858 - val_accuracy: 0.0000e+00\n",
"Epoch 4868/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.6349 - accuracy: 0.1875 - val_loss: 3.3194 - val_accuracy: 0.0000e+00\n",
"Epoch 4869/5000\n",
"1/1 [==============================] - 0s 154ms/step - loss: 1.8759 - accuracy: 0.2500 - val_loss: 3.0224 - val_accuracy: 0.0312\n",
"Epoch 4870/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.8047 - accuracy: 0.2500 - val_loss: 3.6248 - val_accuracy: 0.0000e+00\n",
"Epoch 4871/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.7656 - accuracy: 0.1562 - val_loss: 3.0236 - val_accuracy: 0.0312\n",
"Epoch 4872/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.5642 - accuracy: 0.2500 - val_loss: 3.2717 - val_accuracy: 0.0000e+00\n",
"Epoch 4873/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.3660 - accuracy: 0.2500 - val_loss: 3.2383 - val_accuracy: 0.0000e+00\n",
"Epoch 4874/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.6368 - accuracy: 0.2500 - val_loss: 3.3855 - val_accuracy: 0.0000e+00\n",
"Epoch 4875/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 1.8100 - accuracy: 0.2188 - val_loss: 3.1793 - val_accuracy: 0.0000e+00\n",
"Epoch 4876/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.7819 - accuracy: 0.2188 - val_loss: 3.6876 - val_accuracy: 0.0000e+00\n",
"Epoch 4877/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 1.8690 - accuracy: 0.1562 - val_loss: 3.0831 - val_accuracy: 0.0312\n",
"Epoch 4878/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.2467 - accuracy: 0.3125 - val_loss: 3.0657 - val_accuracy: 0.0312\n",
"Epoch 4879/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.5143 - accuracy: 0.2188 - val_loss: 3.1379 - val_accuracy: 0.0000e+00\n",
"Epoch 4880/5000\n",
"1/1 [==============================] - 0s 186ms/step - loss: 1.5844 - accuracy: 0.3438 - val_loss: 3.3449 - val_accuracy: 0.0000e+00\n",
"Epoch 4881/5000\n",
"1/1 [==============================] - 0s 201ms/step - loss: 1.5583 - accuracy: 0.2812 - val_loss: 3.0012 - val_accuracy: 0.0312\n",
"Epoch 4882/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.0713 - accuracy: 0.4062 - val_loss: 3.3965 - val_accuracy: 0.0000e+00\n",
"Epoch 4883/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.5212 - accuracy: 0.2188 - val_loss: 3.0972 - val_accuracy: 0.0000e+00\n",
"Epoch 4884/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.6434 - accuracy: 0.3750 - val_loss: 3.2743 - val_accuracy: 0.0000e+00\n",
"Epoch 4885/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.5908 - accuracy: 0.3125 - val_loss: 3.4167 - val_accuracy: 0.0000e+00\n",
"Epoch 4886/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.4224 - accuracy: 0.2188 - val_loss: 3.3062 - val_accuracy: 0.0000e+00\n",
"Epoch 4887/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.6115 - accuracy: 0.3125 - val_loss: 3.3012 - val_accuracy: 0.0000e+00\n",
"Epoch 4888/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.2857 - accuracy: 0.3125 - val_loss: 3.3123 - val_accuracy: 0.0000e+00\n",
"Epoch 4889/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.8469 - accuracy: 0.1250 - val_loss: 3.6785 - val_accuracy: 0.0000e+00\n",
"Epoch 4890/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.7315 - accuracy: 0.2500 - val_loss: 3.0176 - val_accuracy: 0.0312\n",
"Epoch 4891/5000\n",
"1/1 [==============================] - 0s 179ms/step - loss: 1.7660 - accuracy: 0.2812 - val_loss: 3.8454 - val_accuracy: 0.0312\n",
"Epoch 4892/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.7780 - accuracy: 0.1875 - val_loss: 3.5471 - val_accuracy: 0.0312\n",
"Epoch 4893/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.5319 - accuracy: 0.1875 - val_loss: 3.4551 - val_accuracy: 0.0000e+00\n",
"Epoch 4894/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 1.5026 - accuracy: 0.1875 - val_loss: 3.3663 - val_accuracy: 0.0000e+00\n",
"Epoch 4895/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 1.9499 - accuracy: 0.2188 - val_loss: 3.5310 - val_accuracy: 0.0000e+00\n",
"Epoch 4896/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3504 - accuracy: 0.3125 - val_loss: 3.1093 - val_accuracy: 0.0312\n",
"Epoch 4897/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 2.0922 - accuracy: 0.2500 - val_loss: 4.0977 - val_accuracy: 0.0312\n",
"Epoch 4898/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 2.1367 - accuracy: 0.1562 - val_loss: 3.4540 - val_accuracy: 0.0000e+00\n",
"Epoch 4899/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.4700 - accuracy: 0.2500 - val_loss: 3.3751 - val_accuracy: 0.0000e+00\n",
"Epoch 4900/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.6555 - accuracy: 0.2500 - val_loss: 3.3535 - val_accuracy: 0.0000e+00\n",
"Epoch 4901/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.4224 - accuracy: 0.2500 - val_loss: 3.2295 - val_accuracy: 0.0000e+00\n",
"Epoch 4902/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.4863 - accuracy: 0.2812 - val_loss: 3.2149 - val_accuracy: 0.0000e+00\n",
"Epoch 4903/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.3496 - accuracy: 0.2812 - val_loss: 3.2751 - val_accuracy: 0.0000e+00\n",
"Epoch 4904/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 1.3880 - accuracy: 0.3438 - val_loss: 3.4450 - val_accuracy: 0.0000e+00\n",
"Epoch 4905/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.4150 - accuracy: 0.2500 - val_loss: 3.2923 - val_accuracy: 0.0000e+00\n",
"Epoch 4906/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 1.3461 - accuracy: 0.2812 - val_loss: 3.3674 - val_accuracy: 0.0000e+00\n",
"Epoch 4907/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.6140 - accuracy: 0.2812 - val_loss: 3.3721 - val_accuracy: 0.0000e+00\n",
"Epoch 4908/5000\n",
"1/1 [==============================] - 0s 195ms/step - loss: 1.4044 - accuracy: 0.3750 - val_loss: 3.4605 - val_accuracy: 0.0000e+00\n",
"Epoch 4909/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 1.4286 - accuracy: 0.2188 - val_loss: 3.2887 - val_accuracy: 0.0312\n",
"Epoch 4910/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.5540 - accuracy: 0.2500 - val_loss: 3.6966 - val_accuracy: 0.0312\n",
"Epoch 4911/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 1.4287 - accuracy: 0.2500 - val_loss: 3.2252 - val_accuracy: 0.0312\n",
"Epoch 4912/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 1.4225 - accuracy: 0.2188 - val_loss: 3.4732 - val_accuracy: 0.0000e+00\n",
"Epoch 4913/5000\n",
"1/1 [==============================] - 0s 197ms/step - loss: 1.2483 - accuracy: 0.4062 - val_loss: 3.3204 - val_accuracy: 0.0000e+00\n",
"Epoch 4914/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.3412 - accuracy: 0.3438 - val_loss: 3.6528 - val_accuracy: 0.0312\n",
"Epoch 4915/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 1.2936 - accuracy: 0.3438 - val_loss: 3.2166 - val_accuracy: 0.0312\n",
"Epoch 4916/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 1.5578 - accuracy: 0.4688 - val_loss: 3.5027 - val_accuracy: 0.0000e+00\n",
"Epoch 4917/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.6757 - accuracy: 0.4375 - val_loss: 3.6129 - val_accuracy: 0.0625\n",
"Epoch 4918/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 1.4786 - accuracy: 0.3438 - val_loss: 3.4395 - val_accuracy: 0.0000e+00\n",
"Epoch 4919/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.4677 - accuracy: 0.2500 - val_loss: 3.5925 - val_accuracy: 0.0000e+00\n",
"Epoch 4920/5000\n",
"1/1 [==============================] - 0s 169ms/step - loss: 0.9872 - accuracy: 0.3750 - val_loss: 3.3406 - val_accuracy: 0.1250\n",
"Epoch 4921/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.1265 - accuracy: 0.4062 - val_loss: 3.5269 - val_accuracy: 0.0625\n",
"Epoch 4922/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 1.1348 - accuracy: 0.4062 - val_loss: 3.4391 - val_accuracy: 0.0625\n",
"Epoch 4923/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 1.2870 - accuracy: 0.5625 - val_loss: 3.5614 - val_accuracy: 0.0312\n",
"Epoch 4924/5000\n",
"1/1 [==============================] - 0s 171ms/step - loss: 1.1714 - accuracy: 0.3750 - val_loss: 3.6624 - val_accuracy: 0.0938\n",
"Epoch 4925/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 1.7112 - accuracy: 0.3125 - val_loss: 3.2284 - val_accuracy: 0.0625\n",
"Epoch 4926/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 1.9820 - accuracy: 0.3438 - val_loss: 4.1085 - val_accuracy: 0.0625\n",
"Epoch 4927/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 1.5861 - accuracy: 0.3125 - val_loss: 4.2438 - val_accuracy: 0.0938\n",
"Epoch 4928/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 1.4495 - accuracy: 0.2812 - val_loss: 3.3293 - val_accuracy: 0.0625\n",
"Epoch 4929/5000\n",
"1/1 [==============================] - ETA: 0s - loss: 1.0861 - accuracy: 0.50 - 0s 158ms/step - loss: 1.0861 - accuracy: 0.5000 - val_loss: 3.4866 - val_accuracy: 0.1250\n",
"Epoch 4930/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 1.0046 - accuracy: 0.3438 - val_loss: 3.4863 - val_accuracy: 0.0938\n",
"Epoch 4931/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.9160 - accuracy: 0.5312 - val_loss: 3.4293 - val_accuracy: 0.1875\n",
"Epoch 4932/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.9101 - accuracy: 0.4062 - val_loss: 3.5894 - val_accuracy: 0.0938\n",
"Epoch 4933/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.7543 - accuracy: 0.5938 - val_loss: 3.4129 - val_accuracy: 0.2188\n",
"Epoch 4934/5000\n",
"1/1 [==============================] - 0s 176ms/step - loss: 0.8269 - accuracy: 0.5000 - val_loss: 3.4717 - val_accuracy: 0.1875\n",
"Epoch 4935/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.7523 - accuracy: 0.6562 - val_loss: 3.4041 - val_accuracy: 0.2188\n",
"Epoch 4936/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.7665 - accuracy: 0.5000 - val_loss: 3.6403 - val_accuracy: 0.0938\n",
"Epoch 4937/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.8592 - accuracy: 0.6250 - val_loss: 3.6819 - val_accuracy: 0.1562\n",
"Epoch 4938/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 1.4456 - accuracy: 0.3750 - val_loss: 4.4975 - val_accuracy: 0.1562\n",
"Epoch 4939/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 1.1682 - accuracy: 0.4375 - val_loss: 3.2253 - val_accuracy: 0.1875\n",
"Epoch 4940/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.9767 - accuracy: 0.3438 - val_loss: 4.0085 - val_accuracy: 0.1562\n",
"Epoch 4941/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.8595 - accuracy: 0.5312 - val_loss: 3.4485 - val_accuracy: 0.2188\n",
"Epoch 4942/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.6630 - accuracy: 0.5000 - val_loss: 3.5392 - val_accuracy: 0.2188\n",
"Epoch 4943/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5791 - accuracy: 0.6875 - val_loss: 3.5171 - val_accuracy: 0.2188\n",
"Epoch 4944/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.7088 - accuracy: 0.5938 - val_loss: 3.5845 - val_accuracy: 0.2188\n",
"Epoch 4945/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.5977 - accuracy: 0.7188 - val_loss: 3.6161 - val_accuracy: 0.1875\n",
"Epoch 4946/5000\n",
"1/1 [==============================] - 0s 181ms/step - loss: 0.6358 - accuracy: 0.6875 - val_loss: 3.6691 - val_accuracy: 0.1875\n",
"Epoch 4947/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6175 - accuracy: 0.6250 - val_loss: 3.4791 - val_accuracy: 0.2188\n",
"Epoch 4948/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 1.2341 - accuracy: 0.6250 - val_loss: 3.8314 - val_accuracy: 0.1562\n",
"Epoch 4949/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.6478 - accuracy: 0.5000 - val_loss: 3.7345 - val_accuracy: 0.1875\n",
"Epoch 4950/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.8346 - accuracy: 0.5000 - val_loss: 3.9556 - val_accuracy: 0.1250\n",
"Epoch 4951/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6626 - accuracy: 0.6562 - val_loss: 3.6372 - val_accuracy: 0.2188\n",
"Epoch 4952/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5613 - accuracy: 0.7188 - val_loss: 3.8041 - val_accuracy: 0.1562\n",
"Epoch 4953/5000\n",
"1/1 [==============================] - 0s 172ms/step - loss: 0.6642 - accuracy: 0.5938 - val_loss: 3.6725 - val_accuracy: 0.2188\n",
"Epoch 4954/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5603 - accuracy: 0.6250 - val_loss: 3.6177 - val_accuracy: 0.2188\n",
"Epoch 4955/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5400 - accuracy: 0.7188 - val_loss: 3.7896 - val_accuracy: 0.1562\n",
"Epoch 4956/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6366 - accuracy: 0.5625 - val_loss: 3.6283 - val_accuracy: 0.2188\n",
"Epoch 4957/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.5391 - accuracy: 0.7188 - val_loss: 3.7740 - val_accuracy: 0.1875\n",
"Epoch 4958/5000\n",
"1/1 [==============================] - 0s 157ms/step - loss: 0.7114 - accuracy: 0.5625 - val_loss: 3.6537 - val_accuracy: 0.1875\n",
"Epoch 4959/5000\n",
"1/1 [==============================] - 0s 175ms/step - loss: 0.6110 - accuracy: 0.7188 - val_loss: 3.6168 - val_accuracy: 0.1562\n",
"Epoch 4960/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6224 - accuracy: 0.6875 - val_loss: 3.6366 - val_accuracy: 0.1875\n",
"Epoch 4961/5000\n",
"1/1 [==============================] - 0s 158ms/step - loss: 0.6919 - accuracy: 0.6250 - val_loss: 3.7697 - val_accuracy: 0.1875\n",
"Epoch 4962/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.4705 - accuracy: 0.6250 - val_loss: 3.6151 - val_accuracy: 0.1875\n",
"Epoch 4963/5000\n",
"1/1 [==============================] - 0s 153ms/step - loss: 0.6498 - accuracy: 0.6250 - val_loss: 4.0354 - val_accuracy: 0.1562\n",
"Epoch 4964/5000\n",
"1/1 [==============================] - 0s 170ms/step - loss: 0.6412 - accuracy: 0.6562 - val_loss: 3.5179 - val_accuracy: 0.1875\n",
"Epoch 4965/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.6751 - accuracy: 0.6875 - val_loss: 3.9919 - val_accuracy: 0.1562\n",
"Epoch 4966/5000\n",
"1/1 [==============================] - 0s 159ms/step - loss: 0.9357 - accuracy: 0.6562 - val_loss: 5.5717 - val_accuracy: 0.0938\n",
"Epoch 4967/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 2.5031 - accuracy: 0.2188 - val_loss: 6.3584 - val_accuracy: 0.1250\n",
"Epoch 4968/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 5.5443 - accuracy: 0.2188 - val_loss: 2.9001 - val_accuracy: 0.1562\n",
"Epoch 4969/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 4.4061 - accuracy: 0.3438 - val_loss: 5.2734 - val_accuracy: 0.0625\n",
"Epoch 4970/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 1.9318 - accuracy: 0.1562 - val_loss: 3.7811 - val_accuracy: 0.2188\n",
"Epoch 4971/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.8935 - accuracy: 0.3750 - val_loss: 3.2294 - val_accuracy: 0.1875\n",
"Epoch 4972/5000\n",
"1/1 [==============================] - 0s 156ms/step - loss: 0.7632 - accuracy: 0.5312 - val_loss: 3.3121 - val_accuracy: 0.1875\n",
"Epoch 4973/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.7612 - accuracy: 0.5000 - val_loss: 3.2784 - val_accuracy: 0.1875\n",
"Epoch 4974/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6592 - accuracy: 0.6562 - val_loss: 3.2805 - val_accuracy: 0.2188\n",
"Epoch 4975/5000\n",
"1/1 [==============================] - 0s 182ms/step - loss: 0.6494 - accuracy: 0.5625 - val_loss: 3.3279 - val_accuracy: 0.1875\n",
"Epoch 4976/5000\n",
"1/1 [==============================] - 0s 188ms/step - loss: 0.6073 - accuracy: 0.6875 - val_loss: 3.3348 - val_accuracy: 0.2188\n",
"Epoch 4977/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6585 - accuracy: 0.6875 - val_loss: 3.2741 - val_accuracy: 0.1875\n",
"Epoch 4978/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.6565 - accuracy: 0.7500 - val_loss: 3.3004 - val_accuracy: 0.1875\n",
"Epoch 4979/5000\n",
"1/1 [==============================] - 0s 162ms/step - loss: 0.5906 - accuracy: 0.5938 - val_loss: 3.3028 - val_accuracy: 0.2188\n",
"Epoch 4980/5000\n",
"1/1 [==============================] - 0s 183ms/step - loss: 0.6211 - accuracy: 0.6562 - val_loss: 3.2530 - val_accuracy: 0.2188\n",
"Epoch 4981/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5611 - accuracy: 0.6250 - val_loss: 3.3463 - val_accuracy: 0.1875\n",
"Epoch 4982/5000\n",
"1/1 [==============================] - 0s 168ms/step - loss: 0.6220 - accuracy: 0.7188 - val_loss: 3.3074 - val_accuracy: 0.2188\n",
"Epoch 4983/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.5635 - accuracy: 0.8125 - val_loss: 3.3718 - val_accuracy: 0.1875\n",
"Epoch 4984/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.6154 - accuracy: 0.6875 - val_loss: 3.3792 - val_accuracy: 0.1875\n",
"Epoch 4985/5000\n",
"1/1 [==============================] - 0s 161ms/step - loss: 0.6098 - accuracy: 0.7500 - val_loss: 3.3888 - val_accuracy: 0.1875\n",
"Epoch 4986/5000\n",
"1/1 [==============================] - 0s 174ms/step - loss: 0.5620 - accuracy: 0.6875 - val_loss: 3.3769 - val_accuracy: 0.1875\n",
"Epoch 4987/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.6183 - accuracy: 0.7500 - val_loss: 3.4331 - val_accuracy: 0.1875\n",
"Epoch 4988/5000\n",
"1/1 [==============================] - 0s 164ms/step - loss: 0.5877 - accuracy: 0.6562 - val_loss: 3.3808 - val_accuracy: 0.2188\n",
"Epoch 4989/5000\n",
"1/1 [==============================] - 0s 163ms/step - loss: 0.5611 - accuracy: 0.6562 - val_loss: 3.3869 - val_accuracy: 0.1875\n",
"Epoch 4990/5000\n",
"1/1 [==============================] - 0s 167ms/step - loss: 0.4999 - accuracy: 0.7188 - val_loss: 3.4411 - val_accuracy: 0.1875\n",
"Epoch 4991/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5534 - accuracy: 0.6562 - val_loss: 3.4401 - val_accuracy: 0.2188\n",
"Epoch 4992/5000\n",
"1/1 [==============================] - 0s 180ms/step - loss: 0.5554 - accuracy: 0.6875 - val_loss: 3.4315 - val_accuracy: 0.1875\n",
"Epoch 4993/5000\n",
"1/1 [==============================] - 0s 155ms/step - loss: 0.5882 - accuracy: 0.6562 - val_loss: 3.4041 - val_accuracy: 0.2188\n",
"Epoch 4994/5000\n",
"1/1 [==============================] - 0s 165ms/step - loss: 0.5838 - accuracy: 0.6562 - val_loss: 3.4491 - val_accuracy: 0.2188\n",
"Epoch 4995/5000\n",
"1/1 [==============================] - 0s 166ms/step - loss: 0.5180 - accuracy: 0.6562 - val_loss: 3.4738 - val_accuracy: 0.2188\n",
"Epoch 4996/5000\n",
"1/1 [==============================] - 0s 189ms/step - loss: 0.6248 - accuracy: 0.6875 - val_loss: 3.4912 - val_accuracy: 0.2188\n",
"Epoch 4997/5000\n",
"1/1 [==============================] - 0s 202ms/step - loss: 0.5717 - accuracy: 0.7188 - val_loss: 3.4440 - val_accuracy: 0.2188\n",
"Epoch 4998/5000\n",
"1/1 [==============================] - 0s 178ms/step - loss: 0.4857 - accuracy: 0.6875 - val_loss: 3.5350 - val_accuracy: 0.1875\n",
"Epoch 4999/5000\n",
"1/1 [==============================] - 0s 173ms/step - loss: 0.5533 - accuracy: 0.6875 - val_loss: 3.5605 - val_accuracy: 0.1875\n",
"Epoch 5000/5000\n",
"1/1 [==============================] - 0s 160ms/step - loss: 0.5312 - accuracy: 0.7188 - val_loss: 3.4788 - val_accuracy: 0.2188\n"
]
}
],
"source": [
"his = model.fit(\n",
"X_train,Y_train,\n",
" validation_data = (X_val,Y_val), \n",
" epochs=5000,\n",
" class_weight= class_weights, callbacks=[tensorboard_callback],\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"ys = model.predict(test_ds)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
"ys = tf.nn.softmax(ys)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[0., 0., 0., ..., 0., 0., 0.],\n",
" [0., 0., 0., ..., 0., 0., 1.],\n",
" [1., 0., 0., ..., 0., 0., 0.],\n",
" ...,\n",
" [0., 0., 0., ..., 0., 0., 1.],\n",
" [0., 0., 0., ..., 0., 0., 1.],\n",
" [0., 0., 0., ..., 0., 0., 1.]], dtype=float32)"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ys"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [],
"source": [
"# class_names = np.array(['NF', 'anger', 'contempt', 'disgust', 'fear', 'happiness', 'neutral', 'sadness', 'surprise', 'unknown'])\n",
"\n",
"class_names = np.array(['anger', 'contempt', 'disgust', 'fear', 'happiness', 'neutral', 'sadness', 'surprise'])\n",
"\n",
"def show_batch(image_batch, label_batch):\n",
" plt.figure(figsize=(10,10))\n",
" for n in range(25):\n",
" ax = plt.subplot(5,5,n+1)\n",
" plt.imshow(image_batch[n])\n",
" plt.title(class_names[label_batch[n]==1][0].title())\n",
" plt.axis('off')\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment