kevakba

import tensorflow as tf
import numpy as np
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
import matplotlib.pyplot as plt
from tensorflow.keras import layers
import matplotlib.image as mpimg

kevakba

import pathlib
dataset_path = "C:/Users/ADMIN/Desktop/Project/1"
data_dir = pathlib.Path(dataset_path)
train_dir = os.path.join(data_dir, 'train')
val_dir = os.path.join(data_dir, 'val')

kevakba

batch_size=30
img_height=200
img_width=200

kevakba

image_gen_train = ImageDataGenerator(
                    rescale=1./255,
                    rotation_range=45,
                    width_shift_range=.15,
                    height_shift_range=.15,
                    horizontal_flip=True,
                    zoom_range=0.5
                    )

kevakba

image_gen_val = ImageDataGenerator(rescale=1./255)

val_data_gen = image_gen_val.flow_from_directory(batch_size=batch_size,
                                                 directory=val_dir,
                                                 target_size=(img_width,img_height),  color_mode='grayscale',
                                                 class_mode='sparse')

kevakba

model = tf.keras.Sequential()

model.add(Conv2D(16, 3, padding='same', activation='relu', input_shape=(img_width,img_height, 1)))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, 3, padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, 3, padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

kevakba

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

kevakba

epochs = 20

history = model.fit_generator(
    train_data_gen,
    steps_per_epoch=int(np.ceil(train_data_gen.n / float(batch_size))),
    epochs=epochs,
    validation_data=val_data_gen,
    validation_steps=int(np.ceil(val_data_gen.n / float(batch_size)))
) 

kevakba

Epoch 1/20
48/48 [==============================] - 15s 320ms/step - loss: 1.9151 - accuracy: 0.2396 - val_loss: 1.6345 - val_accuracy: 0.3139
Epoch 2/20
48/48 [==============================] - 15s 314ms/step - loss: 1.4954 - accuracy: 0.3917 - val_loss: 1.3522 - val_accuracy: 0.4722
Epoch 3/20
48/48 [==============================] - 16s 330ms/step - loss: 1.1761 - accuracy: 0.5528 - val_loss: 1.1349 - val_accuracy: 0.5389
Epoch 4/20
48/48 [==============================] - 16s 339ms/step - loss: 0.8542 - accuracy: 0.6958 - val_loss: 0.6563 - val_accuracy: 0.7194
Epoch 5/20
48/48 [==============================] - 16s 340ms/step - loss: 0.6892 - accuracy: 0.7417 - val_loss: 0.7053 - val_accuracy: 0.7472

kevakba

acc = history.history['accuracy']
val_acc = history.history['val_accuracy']

loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(epochs)

plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')