resnet_size=params['resnet_size'],
weight_decay=weight_decay,
learning_rate_fn=learning_rate_fn,
momentum=0.9,
data_format=params['data_format'],
version=params['version'],
loss_filter_fn=loss_filter_fn,
multi_gpu=params['multi_gpu'])
def main(unused_argv):
input_function = FLAGS.use_synthetic_data and get_synth_input_fn(
) or input_fn
resnet.resnet_main(FLAGS, cifar10_model_fn, input_function)
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
parser = resnet.ResnetArgParser()
# Set defaults that are reasonable for this model.
parser.set_defaults(data_dir='/tmp/cifar10_data',
model_dir='/tmp/cifar10_model',
resnet_size=32,
train_epochs=250,
epochs_per_eval=10,
batch_size=128)
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(argv=[sys.argv[0]] + unparsed)
boundary_epochs=[30, 60, 80, 90],
decay_rates=[1, 0.1, 0.01, 0.001, 1e-4])
return resnet.resnet_model_fn(features,
labels,
mode,
ImagenetModel,
resnet_size=params['resnet_size'],
weight_decay=1e-4,
learning_rate_fn=learning_rate_fn,
momentum=0.9,
data_format=params['data_format'],
version=params['version'],
loss_filter_fn=None,
multi_gpu=params['multi_gpu'])
def main(unused_argv):
input_function = FLAGS.use_synthetic_data and get_synth_input_fn(
) or input_fn
resnet.resnet_main(FLAGS, imagenet_model_fn, input_function)
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
parser = resnet.ResnetArgParser(
resnet_size_choices=[18, 34, 50, 101, 152, 200])
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(argv=[sys.argv[0]] + unparsed)