if args.savepath is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.savepath = args.savepath
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.savepath = osp.join('./results',
osp.splitext(osp.basename(args.config))[0])
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids
else:
cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
mata = dict()
# make dirs
mkdir_or_exist(osp.abspath(cfg.savepath))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
cfg.log_file = osp.join(cfg.savepath, f'{timestamp}.log')
# create text log
# build model
model = build_network(cfg.model,
train_cfg=cfg.train_cfg,
test_cfg=cfg.test_cfg)
load(cfg.load_from, model, None)
# build dataset
datasets = build_dataset(cfg.data.test)
# put model on gpu
if torch.cuda.is_available():
# model = DataParallel(model.cuda(), device_ids=cfg.gpu_ids)
model = model.cuda()
if args.work_dir is not None:
# update configs according to CLI args if args.work_dir is not None
cfg.work_dir = args.work_dir
elif cfg.get('work_dir', None) is None:
# use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0])
if args.gpu_ids is not None:
cfg.gpu_ids = args.gpu_ids
else:
cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
mata = dict()
# make dirs
mkdir_or_exist(osp.abspath(cfg.work_dir))
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
cfg.log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
# create text log
logger = get_root_logger(log_file=cfg.log_file, log_level=cfg.log_level)
dash_line = '-' * 60 + '\n'
logger.info(dash_line)
logger.info(f'Config:\n{cfg.pretty_text}')
# build model
model = build_network(cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
logger.info('-' * 20 + 'finish build model' + '-' * 20)
logger.info('Total Parameters: %d, Trainable Parameters: %s',
model.net_parameters['Total'],
str(model.net_parameters['Trainable']))