callbacks = [
EarlyStopping(monitor='loss', patience=3, mode='auto'),
ModelCheckpoint(filepath='best' + MODEL_NAME + '.h5',
monitor='val_loss',
save_best_only=True,
mode='auto')
]
history_object = model.fit_generator(
training_generator,
len(train_samples) // BATCH_SIZE,
epochs=EPOCH,
verbose=1,
callbacks=callbacks,
validation_data=validation_generator,
validation_steps=len(validation_samples) // BATCH_SIZE,
class_weight=None,
workers=1,
initial_epoch=0,
use_multiprocessing=False,
max_queue_size=10)
t2 = time.time()
print('Training model complete...')
print(' Time Taken:', (t2 - t1) / 60, 'minutes')
print('Loss: ')
print(history_object.history['loss'])
print('Validation Loss: ')
print(history_object.history['val_loss'])
batch_size=BATCH_SIZE,
type=type_)
print('Training model...')
model = CNNModel()
callbacks = [
EarlyStopping(monitor='val_loss', patience=3),
ModelCheckpoint(filepath='best' + MODEL_NAME + '.h5',
monitor='val_loss',
save_best_only=True)
]
history_object = model.fit_generator(training_generator, samples_per_epoch= \
len(train_samples)//BATCH_SIZE, validation_data=validation_generator, \
validation_steps=len(validation_samples)//BATCH_SIZE, callbacks=callbacks, epochs=EPOCH, verbose=1)
print('Training model complete...')
print(history_object.history.keys())
print('Loss')
print(history_object.history['loss'])
print('Validation Loss')
print(history_object.history['val_loss'])
plt.figure(figsize=[10, 8])
plt.plot(np.arange(1,
len(history_object.history['loss']) + 1),
history_object.history['loss'],
'r',
