def calc_flops(model):
# manually build the graph with batch=1
input_desc = [
InputDesc(tf.float32, [1, 224, 224, 3], 'input'),
InputDesc(tf.int32, [1], 'label')
]
input = PlaceholderInput()
input.setup(input_desc)
with TowerContext('', is_training=False):
model.build_graph(*input.get_input_tensors())
model_utils.describe_trainable_vars()
tf.profiler.profile(
tf.get_default_graph(),
cmd='op',
options=tf.profiler.ProfileOptionBuilder.float_operation())
logger.info(
"Note that TensorFlow counts flops in a different way from the paper.")
logger.info(
"TensorFlow counts multiply+add as two flops, however the paper counts them "
"as 1 flop because it can be executed in one instruction.")
if args.eval:
batch = 128 # something that can run on one gpu
ds = get_data('val', batch)
eval_on_ILSVRC12(model, get_model_loader(args.load), ds)
elif args.flops:
# manually build the graph with batch=1
input_desc = [
InputDesc(tf.float32, [1, 224, 224, 3], 'input'),
InputDesc(tf.int32, [1], 'label')
]
input = PlaceholderInput()
input.setup(input_desc)
with TowerContext('', is_training=False):
model.build_graph(*input.get_input_tensors())
model_utils.describe_trainable_vars()
tf.profiler.profile(
tf.get_default_graph(),
cmd='op',
options=tf.profiler.ProfileOptionBuilder.float_operation())
logger.info("Note that TensorFlow counts flops in a different way from the paper.")
logger.info("TensorFlow counts multiply+add as two flops, however the paper counts them "
"as 1 flop because it can be executed in one instruction.")
else:
if args.v2:
name = "ShuffleNetV2-{}x".format(args.ratio)
else:
name = "ShuffleNetV1-{}x-g{}".format(args.ratio, args.group)
logger.set_logger_dir(os.path.join('train_log', name))
TOTAL_BATCH_SIZE = args.batch
model = Model()
if args.eval:
batch = 128 # something that can run on one gpu
ds = get_data('val', batch)
eval_classification(model, SmartInit(args.load), ds)
elif args.flops:
# manually build the graph with batch=1
with TowerContext('', is_training=False):
model.build_graph(
tf.placeholder(tf.float32, [1, 224, 224, 3], 'input'),
tf.placeholder(tf.int32, [1], 'label')
)
model_utils.describe_trainable_vars()
tf.profiler.profile(
tf.get_default_graph(),
cmd='op',
options=tf.profiler.ProfileOptionBuilder.float_operation())
logger.info("Note that TensorFlow counts flops in a different way from the paper.")
logger.info("TensorFlow counts multiply+add as two flops, however the paper counts them "
"as 1 flop because it can be executed in one instruction.")
else:
if args.v2:
name = "ShuffleNetV2-{}x".format(args.ratio)
else:
name = "ShuffleNetV1-{}x-g{}".format(args.ratio, args.group)
logger.set_logger_dir(os.path.join('train_log', name))
def after_create_session(self, session, cord):
describe_trainable_vars()