Skip to content

Instantly share code, notes, and snippets.

@giantneco

giantneco/keras-tuner-helloworld.ipynb Secret

Last active June 26, 2019 05:06
Show Gist options
  • Save giantneco/e12fdba557de538598e704bcf23dae46 to your computer and use it in GitHub Desktop.
Save giantneco/e12fdba557de538598e704bcf23dae46 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
keras-tuner-helloworld.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from tensorflow import keras\n",
"from tensorflow.keras import layers\n",
"\n",
"import numpy as np\n",
"\n",
"from kerastuner.tuners import RandomSearch\n",
"from kerastuner.engine.hypermodel import HyperModel\n",
"from kerastuner.engine.hyperparameters import HyperParameters\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
"11493376/11490434 [==============================] - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - ETA: - 1s 0us/step\n"
]
}
],
"source": [
"\n",
"(x, y), (val_x, val_y) = keras.datasets.mnist.load_data()\n",
"x = x.astype('float32') / 255.\n",
"val_x = val_x.astype('float32') / 255.\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"x = x[:10000]\n",
"y = y[:10000]\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def build_model(hp):\n",
" model = keras.Sequential()\n",
" model.add(layers.Flatten(input_shape=(28, 28)))\n",
" for i in range(hp.Range('num_layers', 2, 20)):\n",
" model.add(layers.Dense(units=hp.Range('units_' + str(i), 32, 512, 32),\n",
" activation='relu'))\n",
" model.add(layers.Dense(10, activation='softmax'))\n",
" model.compile(\n",
" optimizer=keras.optimizers.Adam(\n",
" hp.Choice('learning_rate', [1e-2, 1e-3, 1e-4])),\n",
" loss='sparse_categorical_crossentropy',\n",
" metrics=['accuracy'])\n",
" return model\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"tuner = RandomSearch(\n",
" build_model,\n",
" objective='val_accuracy',\n",
" max_trials=5,\n",
" executions_per_trial=3,\n",
" directory='test_dir')\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"tuner = RandomSearch(\n",
" build_model,\n",
" objective='val_accuracy',\n",
" max_trials=5,\n",
" executions_per_trial=3,\n",
" directory='test_dir')\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Search space summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-Default search space size: 4</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">num_layers (Range)</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-default: 2</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-max_value: 20</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-min_value: 2</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-step: 1</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">units_0 (Range)</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-default: 32</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-max_value: 512</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-min_value: 32</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-step: 32</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">units_1 (Range)</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-default: 32</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-max_value: 512</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-min_value: 32</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-step: 32</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">learning_rate (Choice)</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-default: 0.01</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-values: [0.01, 0.001, 0.0001]</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"tuner.search_space_summary()\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">New model</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hp values:</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-learning_rate: 0.001</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-num_layers: 4</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_0: 224</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_1: 352</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 1/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING: Logging before flag parsing goes to stderr.\n",
"W0625 14:42:41.780411 4672964032 deprecation.py:323] From /Users/shingo-s/.pyenv/versions/3.6.5/envs/keras-tuner/lib/python3.6/site-packages/tensorflow/python/ops/math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.where in 2.0, which has the same broadcast rule as np.where\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4a6139ddb66b4c9ab01850097647a615",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4c45c9052e224d59863db59c58cf25a6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "7c70ae5a8b3a4a928399057aebd0bf48",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 2/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "81d322a9244849d487eb4d3edf6df87d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "24b5b9f0908643fcb7f19fe660264233",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "16849fce947a4c1dacd4700a1713a63c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 3/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3b068db62acc45a39ef20b8cc50714f0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5f39f60662e642398fb62aac535702b1",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "275e14ab557847bcbe64e5e1df4d2aaa",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th>Name </th><th>Best model </th><th>Current model </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td>accuracy </td><td>0.9635 </td><td>0.9635 </td></tr>\n",
"<tr><td>loss </td><td>0.121 </td><td>0.121 </td></tr>\n",
"<tr><td>val_loss </td><td>0.2106 </td><td>0.2106 </td></tr>\n",
"<tr><td><span style=\"color:green\">val_accuracy</span></td><td><span style=\"color:green\">0.9386</span></td><td><span style=\"color:green\">0.9386</span></td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#64DD17\"><span style=\"font-size:14px\"><b>4/5 trials left</b></span></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">New model</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hp values:</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-learning_rate: 0.0001</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-num_layers: 7</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_0: 320</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_1: 160</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_2: 64</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_3: 352</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 1/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6be4f5d80f224b46a7dd07050367ddd1",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a3e7a05f88b64ff59b749520a8479a5c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3f3a68f5b2724d5eabd70464d4222d71",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 2/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "81d4e9ecbb8249da9d98372fee213ec9",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3030219afd4145c09af2431f6612436c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "35eb33f836d747ac9dba6805045ebf06",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 3/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "fc34cba418f247418cccd1e38d565ccc",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6f988bc594794040b435cad442849de8",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "675b51ef63f84fa294960db26d38a425",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th>Name </th><th>Best model </th><th>Current model </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td>accuracy </td><td>0.9635 </td><td>0.9098 </td></tr>\n",
"<tr><td>loss </td><td>0.121 </td><td>0.335 </td></tr>\n",
"<tr><td>val_loss </td><td>0.2106 </td><td>0.3451 </td></tr>\n",
"<tr><td><span style=\"color:red\">val_accuracy</span></td><td><span style=\"color:red\">0.9386</span></td><td><span style=\"color:red\">0.9023</span></td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#64DD17\"><span style=\"font-size:14px\"><b>3/5 trials left</b></span></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">New model</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hp values:</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-learning_rate: 0.01</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-num_layers: 4</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_0: 64</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_1: 160</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_2: 384</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_3: 224</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_4: 160</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_5: 352</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_6: 256</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 1/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "bed4bbce379d426e9ea0eddcacd4ab0f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e073184356fe4ee0a96e2ec7286e2004",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2221baca026944a48a0108e791a6c98a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 2/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "4120a1c1dd454fe596ebbfad492b3445",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3076a6065172447c9ba0d2c2c7cee1d7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "aa9d9249311644ad890d03eba1dbcbeb",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 3/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e084ce8370244bc1943a244cd803b64f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "89b39e9302f34990875d9bccbc29e4f6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "994f2c4b73ce4c9f846e8667459e23ab",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th>Name </th><th>Best model </th><th>Current model </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td>accuracy </td><td>0.9635 </td><td>0.9109 </td></tr>\n",
"<tr><td>loss </td><td>0.121 </td><td>0.3654 </td></tr>\n",
"<tr><td>val_loss </td><td>0.2106 </td><td>0.3988 </td></tr>\n",
"<tr><td><span style=\"color:red\">val_accuracy</span></td><td><span style=\"color:red\">0.9386</span></td><td><span style=\"color:red\">0.897</span></td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#64DD17\"><span style=\"font-size:14px\"><b>2/5 trials left</b></span></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">New model</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hp values:</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-learning_rate: 0.001</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-num_layers: 11</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_0: 448</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_1: 384</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_2: 224</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_3: 384</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_4: 192</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_5: 224</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_6: 96</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 1/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "32037125e39d4aaa8a99ea72ab606743",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "86f03623a7644129b58508ce028e2ab6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "229f17c348c9481ca46fd61ec19db546",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 2/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "d915c31db98a4bf2946d36c11e8510cf",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "65820dc57f754fd4b3c4c932f4062e58",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "84607df9a375424fa4cb56162b0617ac",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 3/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a7a6c7ece87640cc9bce6ea09e5e4f84",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c6b876b5917b4a7abaad8717594beb6c",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "61ffa5443ba14508af580b88e82fc00d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th>Name </th><th>Best model </th><th>Current model </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td>accuracy </td><td>0.9635 </td><td>0.948 </td></tr>\n",
"<tr><td>loss </td><td>0.121 </td><td>0.2034 </td></tr>\n",
"<tr><td>val_loss </td><td>0.2106 </td><td>0.2788 </td></tr>\n",
"<tr><td><span style=\"color:red\">val_accuracy</span></td><td><span style=\"color:red\">0.9386</span></td><td><span style=\"color:red\">0.9358</span></td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#64DD17\"><span style=\"font-size:14px\"><b>1/5 trials left</b></span></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">New model</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hp values:</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-learning_rate: 0.001</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-num_layers: 11</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_0: 480</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_1: 192</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_10: 192</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_2: 288</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_3: 320</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_4: 224</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_5: 256</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_6: 352</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_7: 192</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:blue\"> |-units_8: 320</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-units_9: 64</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 1/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2578152158df471bafea99fee63d33a6",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e2da49cc13724cb5840e474dd3c73fb5",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ea6e14c435f545fca0d94a0945211cd0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 2/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9060648e2d0643b1a1be2ff7c3de527d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a4f6a8756219437a921f99d3ab833cac",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "dfe548b5cd71450b967ac030e1b4956a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Execution 3/3</h2></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ef4c9e3919b34ac6b1d8aa9557a71151",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "5cd54eb077ff4134b4ada6162c3349a7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3b5fcfcf8d7e41c691d12872ff2dce1f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=313), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th>Name </th><th>Best model </th><th>Current model </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td>accuracy </td><td>0.9635 </td><td>0.9425 </td></tr>\n",
"<tr><td>loss </td><td>0.121 </td><td>0.2308 </td></tr>\n",
"<tr><td>val_loss </td><td>0.2106 </td><td>0.3055 </td></tr>\n",
"<tr><td><span style=\"color:red\">val_accuracy</span></td><td><span style=\"color:red\">0.9386</span></td><td><span style=\"color:red\">0.9248</span></td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:#64DD17\"><span style=\"font-size:14px\"><b>Hypertuning complete - results in test_dir/untitled_project</b></span></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"tuner.search(x=x,\n",
" y=y,\n",
" epochs=3,\n",
" validation_data=(val_x, val_y))\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Results summary</h1></span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-Results in test_dir/untitled_project</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-Ran 5 trials</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-Ran 15 executions (3 per trial)</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<span style=\"color:cyan\"> |-Best val_accuracy: 0.9386</span>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"tuner.results_summary()\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"models = tuner.get_best_models(num_models=2)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment