def training():
train_generator, validation_generator = prepare_data()
# train_generator, validation_generator, test_generator = prepare_data()
resnet50_network = ResNet50(include_top=False,
weights='imagenet',
input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))
for layer in resnet50_network.layers[:-3]:
layer.trainable = False
model = Sequential()
model.add(resnet50_network)
model.add(AveragePooling2D((7, 7), name='avg_pool'))
model.add(Flatten())
model.add(
Dense(train_generator.class_indices.items().__len__(),
activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=0.001),
metrics=['accuracy'])
early_stopping = EarlyStopping(patience=10)
checkpointer = ModelCheckpoint(filepath='car_resNet50_best.h5',
verbose=0,
save_best_only=True)
csv_logger = CSVLogger('ResNet50_training_log.csv',
append=True,
separator=';')
history = model.fit_generator(
train_generator,
steps_per_epoch=train_generator.samples / train_generator.batch_size,
epochs=EPOCHS,
callbacks=[early_stopping, checkpointer, csv_logger],
validation_data=validation_generator,
validation_steps=validation_generator.samples /
validation_generator.batch_size)
# evaluate_scores = model.evaluate_generator(generator=test_generator)
model.save('car_resNet50_final.h5')
model.sample_weights('resNet50_weights')
show_history(history)
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax')) # output layer
# Compile the model
model.compile(
optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy']
)
# Print a summery of the model
# model.summary()
# Training the model
model.fit(
x=x_train,
y=y_train,
batch_size=32,
epochs=30,
validation_data=(x_test, y_test),
shuffle=True
)
# Save neural network structure
model_structure = model.to_json()
file = Path('model_structure.json')
file.write_text(model_structure)
# Save neural network's trained weight
model.sample_weights('model_weights.h5')
