def get_model():
if mode == '':
# a 25 layers deep VGG-style network with batchnorm
k = 32
model = VGG(input_shape=x_train.shape[1:],
nbstages=4,
nblayers=[6] * 4,
nbfilters=[1 * k, 2 * k, 4 * k, 8 * k],
nbclasses=y_train.shape[1],
use_bias=False,
batchnorm_training=False,
kernel_initializer='he_uniform')
elif mode == 'fast':
k = 16
# a 13 layers deep VGG-style network with batchnorm
model = VGG(input_shape=x_train.shape[1:],
nbstages=4,
nblayers=[3] * 4,
nbfilters=[1 * k, 2 * k, 4 * k, 8 * k],
nbclasses=y_train.shape[1],
use_bias=False,
batchnorm_training=False,
kernel_initializer='he_uniform')
weights_location = 'model_initial_weights/cifar10_initial_weights' + mode + '.h5'
if 'cifar10_initial_weights' + mode + '.h5' not in os.listdir(
'model_initial_weights'):
model.save_weights(weights_location)
else:
model.load_weights(weights_location)
return model
def get_model():
k = 32
model = VGG(
input_shape=x_train.shape[1:],
nbstages=5,
nblayers=[2] * 5,
nbfilters=[1 * k, 2 * k, 4 * k, 8 * k, 16 * k],
nbclasses=y_train.shape[1],
use_bias=False,
batchnorm_training=False, #use_batchnorm = False,
kernel_initializer='he_uniform',
batchnorm_momentum=0.9
) ### because training sometimes stops after very few epochs (~15)
weights_location = 'model_initial_weights/tinyImagenet_initial_weights_batchnorm.h5'
if 'tinyImagenet_initial_weights_batchnorm.h5' not in os.listdir(
'model_initial_weights'):
model.save_weights(weights_location)
else:
model.load_weights(weights_location)
return model
acc_val = train_accuracy.result() * 100
print(template.format(epoch + 1, loss_val, acc_val), '\n')
epoch += 1
if loss_val < hparams.epsilon or epoch > hparams.max_epochs:
break
# if abs(loss_val - hparams.epsilon) < 0.01 or epoch > hparams.max_epochs:
# # if we've reached the cross-entropy criterion stopping point
# # or if we've exceeded the number of permissible epochs
# break
end = time.time()
total_time = end - start
print('Stopping criterion reached!\nSaving model...')
h5_path = os.path.join(os.getcwd(),
'weights_{}.h5'.format(hparams.model_num))
model.save_weights(h5_path)
info = {}
train_acc_val = train_accuracy.result() * 100
test_acc_val = test_accuracy.result() * 100
info['hparams'] = vars(hparams)
info['train_acc'] = float(train_acc_val.numpy())
info['test_acc'] = float(test_acc_val.numpy())
info['train_time'] = total_time
json_path = os.path.join(os.getcwd(),
'config_{}.json'.format(hparams.model_num))
with open(json_path, 'w') as file:
json.dump(info, file)
with summary_writer.as_default():
tf.summary.scalar('Train Time (sec)', total_time, step=0)
print('Training Time Elapsed: {} | Training Accuracy: {}'.format(
total_time, train_acc_val))
