help='Input size. '
'channels x height x width (default: 1x3x224x224)')
parser.add_argument('-speed', '--speed_test', action='store_true')
parser.add_argument('--iteration', type=int, default=5000)
parser.add_argument('-summary', '--summary', action='store_true')
args = parser.parse_args()
all_dev = parse_devices(args.devices)
network = Network_Res50(config.num_classes, is_training=False)
data_setting = {'img_root': config.img_root_folder,
'gt_root': config.gt_root_folder,
'train_source': config.train_source,
'eval_source': config.eval_source,
'test_source': config.test_source}
dataset = Cil(data_setting, 'test', None)
if args.speed_test:
device = all_dev[0]
logger.info("=========DEVICE:%s SIZE:%s=========" % (
torch.cuda.get_device_name(device), args.input_size))
input_size = tuple(int(x) for x in args.input_size.split('x'))
compute_speed(network, input_size, device, args.iteration)
elif args.summary:
input_size = tuple(int(x) for x in args.input_size.split('x'))
stat(network, input_size)
else:
with torch.no_grad():
segmentor = SegEvaluator(dataset, config.num_classes, config.image_mean,
config.image_std, network,
config.eval_scale_array, config.eval_flip,
parser.add_argument('-speed', '--speed_test', action='store_true')
parser.add_argument('--iteration', type=int, default=5000)
parser.add_argument('-summary', '--summary', action='store_true')
args = parser.parse_args()
all_dev = parse_devices(args.devices)
network = PSPNet(config.num_classes)
data_setting = {
'img_root': config.img_root_folder,
'gt_root': config.gt_root_folder,
'train_source': config.train_source,
'eval_source': config.eval_source,
'test_source': config.test_source
}
dataset = Cil(data_setting, 'val', None)
if args.speed_test:
device = all_dev[0]
logger.info("=========DEVICE:%s SIZE:%s=========" %
(torch.cuda.get_device_name(device), args.input_size))
input_size = tuple(int(x) for x in args.input_size.split('x'))
compute_speed(network, input_size, device, args.iteration)
elif args.summary:
input_size = tuple(int(x) for x in args.input_size.split('x'))
stat(network, input_size)
else:
with torch.no_grad():
segmentor = SegEvaluator(dataset, config.num_classes,
config.image_mean, config.image_std,
network, config.eval_scale_array,
help='Input size. '
'channels x height x width (default: 1x3x224x224)')
parser.add_argument('-speed', '--speed_test', action='store_true')
parser.add_argument('--iteration', type=int, default=5000)
parser.add_argument('-summary', '--summary', action='store_true')
args = parser.parse_args()
# all_dev = parse_devices(args.devices) #gpu
all_dev = [0] #cpu
#`n_iter=10`: During the test time, iteration count was increased to 10.
network = CrfRnnNet(config.num_classes, n_iter=10)
data_setting = {
'img_root': config.img_root_folder,
'gt_root': config.gt_root_folder,
'train_source': config.train_source,
'eval_source': config.eval_source,
'test_source': config.test_source
}
# dataset = Cil(data_setting, 'test', None)
dataset = Cil(data_setting, 'train', None)
with torch.no_grad():
segmentor = SegEvaluator(dataset, config.num_classes,
config.image_mean, config.image_std, network,
config.eval_scale_array, config.eval_flip,
all_dev, args.verbose, args.save_path)
segmentor.run(config.snapshot_dir, args.epochs, config.val_log_file,
config.link_val_log_file)