def main():
"""CapsNet run as module.
Run full cycle when CapsNet is run as a module.
"""
people = fetch_lfw_people(
color=True,
min_faces_per_person=25,
# resize=1.,
# slice_=(slice(48, 202), slice(48, 202))
)
data = preprocess(people)
(x_train, y_train), (x_test, y_test) = data # noqa
model = CapsNet(x_train.shape[1:], len(np.unique(y_train, axis=0)))
model.summary()
# Start TensorBoard
tensorboard = callbacks.TensorBoard('model/tensorboard_logs',
batch_size=10,
histogram_freq=1,
write_graph=True,
write_grads=True,
write_images=True)
model.train(data, batch_size=10, extra_callbacks=[tensorboard])
model.save('/tmp')
metrics = model.test(x_test, y_test)
pprint(metrics)
def main(not_parsed_args):
# we use a margin loss
model = CapsNet()
last_epoch = load_weights(model)
model.compile(loss=margin_loss, optimizer=optimizers.Adam(FLAGS.lr), metrics=['accuracy'])
model.summary()
dataset = Dataset(FLAGS.dataset, FLAGS.batch_size)
tensorboard = TensorBoard(log_dir='./tf_logs', batch_size=FLAGS.batch_size, write_graph=False, write_grads=True, write_images=True, update_freq='batch')
tensorboard.set_model(model)
for epoch in range(last_epoch, FLAGS.epochs):
logging.info('Epoch %d' % epoch)
model.fit_generator(generator=dataset,
epochs=1,
steps_per_epoch=len(dataset),
verbose=1,
validation_data=dataset.eval_dataset,
validation_steps=len(dataset.eval_dataset))
logging.info('Saving model')
filename = 'model_%d.h5' % (epoch)
path = os.path.join(FLAGS.model_dir, filename)
path_info = os.path.join(FLAGS.model_dir, 'info')
model.save_weights(path)
f = open(path_info, 'w')
f.write(filename)
f.close()