"""
Sec 2.3: We keep the per-worker sample size n constant when we change the number of workers k.
In this work, we use n = 32 which has performed well for a wide range of datasets and networks.
"""
parser.add_argument('--batch', help='per-GPU batch size', default=32, type=int)
args = parser.parse_args()
model = Model(args.depth, args.norm, args.use_ws)
model.accum_grad = args.accum_grad
if args.weight_decay_norm:
model.weight_decay_pattern = ".*/W|.*/gamma|.*/beta"
if args.eval:
batch = 128 # something that can run on one gpu
ds = get_val_dataflow(args.data, batch, fbresnet_augmentor(False))
eval_classification(model, get_model_loader(args.load), ds)
sys.exit()
logger.info("Training on {}".format(socket.gethostname()))
# Print some information for sanity check.
os.system("nvidia-smi")
assert args.load is None
hvd.init()
if args.logdir is None:
args.logdir = os.path.join('train_log', 'Horovod-{}GPUs-{}Batch'.format(hvd.size(), args.batch))
if hvd.rank() == 0:
logger.set_logger_dir(args.logdir, 'd')
logger.info("Rank={}, Local Rank={}, Size={}".format(hvd.rank(), hvd.local_rank(), hvd.size()))
raise
logger.info("Name Transform: " + k + ' --> ' + newname)
resnet_param[newname] = v
return resnet_param
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--load', required=True,
help='.npz model file generated by tensorpack.utils.loadcaffe')
parser.add_argument('-d', '--depth', help='resnet depth', required=True, type=int, choices=[50, 101, 152])
parser.add_argument('--input', help='an input image')
parser.add_argument('--convert', help='npz output file to save the converted model')
parser.add_argument('--eval', help='ILSVRC dir to run validation on')
args = parser.parse_args()
DEPTH = args.depth
param = dict(np.load(args.load))
param = convert_param_name(param)
if args.convert:
assert args.convert.endswith('.npz')
np.savez_compressed(args.convert, **param)
if args.eval:
ds = get_imagenet_dataflow(args.eval, 'val', 128, get_inference_augmentor())
eval_classification(Model(), DictRestore(param), ds)
elif args.input:
run_test(param, args.input)
parser = argparse.ArgumentParser()
parser.add_argument('--gpu', help='the physical ids of GPUs to use')
parser.add_argument('--load', help='load a checkpoint, or a npz (given as the pretrained model)')
parser.add_argument('--data', help='ILSVRC dataset dir')
parser.add_argument('--run', help='run on a list of images with the pretrained model', nargs='*')
parser.add_argument('--eval', action='store_true')
args = parser.parse_args()
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
if args.run:
assert args.load.endswith('.npz')
run_image(Model(), SmartInit(args.load), args.run)
sys.exit()
if args.eval:
BATCH_SIZE = 128
ds = get_data('val')
eval_classification(Model(), SmartInit(args.load), ds)
sys.exit()
nr_tower = max(get_nr_gpu(), 1)
BATCH_SIZE = TOTAL_BATCH_SIZE // nr_tower
logger.set_logger_dir(os.path.join(
'train_log', 'alexnet-dorefa-{}'.format(args.dorefa)))
logger.info("Batch per tower: {}".format(BATCH_SIZE))
config = get_config()
config.session_init = SmartInit(args.load)
launch_train_with_config(config, SyncMultiGPUTrainerReplicated(nr_tower))
help='variants of resnet to use',
default='resnet')
args = parser.parse_args()
if args.gpu:
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
model = Model(args.depth, args.mode)
model.data_format = args.data_format
if args.weight_decay_norm:
model.weight_decay_pattern = ".*/W|.*/gamma|.*/beta"
if args.eval:
batch = 128 # something that can run on one gpu
ds = get_imagenet_dataflow(args.data, 'val', batch)
eval_classification(model, SmartInit(args.load), ds)
else:
if args.fake:
logger.set_logger_dir(os.path.join('train_log', 'tmp'), 'd')
else:
logger.set_logger_dir(
os.path.join(
'/data0/wangguangrun/tensorflow_log/train_log',
'imagenet-{}-d{}-batch{}'.format(args.mode, args.depth,
args.batch)))
config = get_config(model)
config.session_init = SmartInit(args.load)
trainer = SyncMultiGPUTrainerReplicated(max(get_num_gpu(), 1))
launch_train_with_config(config, trainer)
'--load',
help='load a checkpoint, or a npz (given as the pretrained model)')
parser.add_argument('--data', help='ILSVRC dataset dir')
parser.add_argument(
'--dorefa',
required=True,
help='number of bits for W,A,G, separated by comma. W="t" means TTQ')
parser.add_argument(
'--run',
help='run on a list of images with the pretrained model',
nargs='*')
parser.add_argument('--eval', action='store_true')
args = parser.parse_args()
if args.eval:
BATCH_SIZE = 128
data_test = dataset.SVHNDigit('test')
augmentors = [
imgaug.Resize((40, 40)),
imgaug.Brightness(30),
imgaug.Contrast((0.5, 1.5)),
]
data_test = AugmentImageComponent(data_test, augmentors)
data_test = BatchData(data_test, 128, remainder=True)
eval_classification(Model(), get_model_loader(args.load), data_test)
sys.exit()
BITW, BITA, BITG = map(int, args.dorefa.split(','))
config = get_config()
launch_train_with_config(config, SimpleTrainer())