def main(args):
cfg = setup_cfg(args)
if cfg.SEED >= 0:
print('Setting fixed seed: {}'.format(cfg.SEED))
set_random_seed(cfg.SEED)
setup_logger(cfg.OUTPUT_DIR)
if torch.cuda.is_available() and cfg.USE_CUDA:
torch.backends.cudnn.benchmark = True
print_args(args, cfg)
print('Collecting env info ...')
print('** System info **\n{}\n'.format(collect_env_info()))
trainer = build_trainer(cfg)
# Uncomment the following lines to do extract embedding features
#print('Running vis()')
#trainer.vis()
#return
if args.eval_only:
trainer.load_model(args.model_dir, epoch=args.load_epoch)
trainer.test()
return
if not args.no_train:
trainer.train()
def main(args):
cfg = setup_cfg(args)
set_random_seed(cfg.SEED)
setup_logger(cfg.OUTPUT_DIR)
if torch.cuda.is_available() and cfg.USE_CUDA:
torch.backends.cudnn.benchmark = True
print_args(args, cfg)
print('Collecting env info ...')
print('** System info **\n{}\n'.format(collect_env_info()))
trainer = build_trainer(cfg)
model = trainer.model
model_dict = model.state_dict()
for k, v in model_dict.items():
print(k)
def main(args):
cfg = setup_cfg(args)
set_random_seed(cfg.SEED)
setup_logger(cfg.OUTPUT_DIR)
if torch.cuda.is_available() and cfg.USE_CUDA:
torch.backends.cudnn.benchmark = True
print_args(args, cfg)
print('Collecting env info ...')
print('** System info **\n{}\n'.format(collect_env_info()))
trainer = build_trainer(cfg)
if args.eval_only:
trainer.load_model(args.model_dir, epoch=args.load_epoch)
trainer.test()
return
if not args.no_train:
trainer.train()