callbacks=[csv_logger, checkpointer, early_stopper])
else:
print('Using real-time data augmentation.')
# This will do preprocessing and realtime data augmentation:
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
# randomly rotate images in the range (degrees, 0 to 180)
rotation_range=0,
# randomly shift images horizontally (fraction of total width)
width_shift_range=0.1,
# randomly shift images vertically (fraction of total height)
height_shift_range=0.1,
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# Compute quantities required for feature-wise normalization
# (std, mean, and principal components if ZCA whitening is applied).
datagen.fit(x_train)
# Fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(x_train, y_train,
batch_size=batch_size),
steps_per_epoch=x_train.shape[0] // batch_size,
epochs=epochs,
validation_data=(x_test, y_test),
callbacks=[csv_logger, checkpointer, early_stopper])
train_gen = data_gen.flow_from_directory(path_train,
batch_size=batch_size,
target_size=shape,
class_mode='categorical',
color_mode='grayscale')
valid_gen = data_gen.flow_from_directory(path_valid,
batch_size=batch_size,
target_size=shape,
class_mode='categorical',
color_mode='grayscale')
history = []
try:
history = model.fit_generator(train_gen, steps_epoch, epochs,
valid_gen, valid_steps)
print("Saving weights")
model.save_weights(obj_weight)
print("Saving history")
pickle.dump(history.history, open(obj_history, 'wb'))
except KeyboardInterrupt:
print("\n\n --- Interruption ---\n ---Saving weights---")
model.save_weights(obj_weight)
print(" ---Saving history---")
pickle.dump(history.history, open(obj_history, 'wb'))
sys.exit(0)
