action='store_true')
parser.add_argument('--save_path', '-p', default=None)
parser.add_argument('--input_size',
type=str,
default='1x3x512x1024',
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 = BiSeNet(config.num_classes,
is_training=False,
criterion=None,
ohem_criterion=None)
data_setting = {
'img_root': config.img_root_folder,
'gt_root': config.gt_root_folder,
'train_source': config.train_source,
'eval_source': config.eval_source
}
dataset = Cityscapes(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)
# config network and criterion
criterion = nn.CrossEntropyLoss(reduction='mean', ignore_index=255)
ohem_criterion = ProbOhemCrossEntropy2d(
ignore_label=255,
thresh=0.7,
min_kept=int(config.batch_size // len(engine.devices) *
config.image_height * config.image_width //
(16 * config.gt_down_sampling**2)),
use_weight=False)
if engine.distributed:
BatchNorm2d = SyncBatchNorm
model = BiSeNet(config.num_classes,
is_training=True,
criterion=criterion,
ohem_criterion=ohem_criterion,
pretrained_model=config.pretrained_model,
norm_layer=BatchNorm2d)
init_weight(model.business_layer,
nn.init.kaiming_normal_,
BatchNorm2d,
config.bn_eps,
config.bn_momentum,
mode='fan_in',
nonlinearity='relu')
# group weight and config optimizer
base_lr = config.lr
if engine.distributed:
base_lr = config.lr * engine.world_size
