How to use the torchfcn.models.FCN16s function in torchfcn

def get_parameters(model, bias=False):
    import torch.nn as nn
    modules_skipped = (
        nn.ReLU,
        nn.MaxPool2d,
        nn.Dropout2d,
        nn.Sequential,
        torchfcn.models.FCN32s,
        torchfcn.models.FCN16s,
        torchfcn.models.FCN8s,
    )
    for m in model.modules():
        if isinstance(m, nn.Conv2d):
            if bias:
                yield m.bias
            else:
                yield m.weight
        elif isinstance(m, nn.ConvTranspose2d):
            # weight is frozen because it is just a bilinear upsampling
            if bias:
                assert m.bias is None
        elif isinstance(m, modules_skipped):
            continue
        else:
            raise ValueError('Unexpected module: %s' % str(m))

os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpu)
    model_file = args.model_file

    root = osp.expanduser('~/data/datasets')
    val_loader = torch.utils.data.DataLoader(
        torchfcn.datasets.VOC2011ClassSeg(
            root, split='seg11valid', transform=True),
        batch_size=1, shuffle=False,
        num_workers=4, pin_memory=True)

    n_class = len(val_loader.dataset.class_names)

    if osp.basename(model_file).startswith('fcn32s'):
        model = torchfcn.models.FCN32s(n_class=21)
    elif osp.basename(model_file).startswith('fcn16s'):
        model = torchfcn.models.FCN16s(n_class=21)
    elif osp.basename(model_file).startswith('fcn8s'):
        if osp.basename(model_file).startswith('fcn8s-atonce'):
            model = torchfcn.models.FCN8sAtOnce(n_class=21)
        else:
            model = torchfcn.models.FCN8s(n_class=21)
    else:
        raise ValueError
    if torch.cuda.is_available():
        model = model.cuda()
    print('==> Loading %s model file: %s' %
          (model.__class__.__name__, model_file))
    model_data = torch.load(model_file)
    try:
        model.load_state_dict(model_data)
    except Exception:
        model.load_state_dict(model_data['model_state_dict'])

# 1. dataset

    root = osp.expanduser('~/data/datasets')
    kwargs = {'num_workers': 4, 'pin_memory': True} if cuda else {}
    train_loader = torch.utils.data.DataLoader(
        torchfcn.datasets.SBDClassSeg(root, split='train', transform=True),
        batch_size=1, shuffle=True, **kwargs)
    val_loader = torch.utils.data.DataLoader(
        torchfcn.datasets.VOC2011ClassSeg(
            root, split='seg11valid', transform=True),
        batch_size=1, shuffle=False, **kwargs)

    # 2. model

    model = torchfcn.models.FCN16s(n_class=21)
    start_epoch = 0
    start_iteration = 0
    if args.resume:
        checkpoint = torch.load(args.resume)
        model.load_state_dict(checkpoint['model_state_dict'])
        start_epoch = checkpoint['epoch']
        start_iteration = checkpoint['iteration']
    else:
        fcn32s = torchfcn.models.FCN32s()
        state_dict = torch.load(args.pretrained_model)
        try:
            fcn32s.load_state_dict(state_dict)
        except RuntimeError:
            fcn32s.load_state_dict(state_dict['model_state_dict'])
        model.copy_params_from_fcn32s(fcn32s)
    if cuda:

torchfcn.datasets.VOC2011ClassSeg(
            root, split='seg11valid', transform=True),
        batch_size=1, shuffle=False, **kwargs)

    # 2. model

    model = torchfcn.models.FCN8s(n_class=21)
    start_epoch = 0
    start_iteration = 0
    if args.resume:
        checkpoint = torch.load(args.resume)
        model.load_state_dict(checkpoint['model_state_dict'])
        start_epoch = checkpoint['epoch']
        start_iteration = checkpoint['iteration']
    else:
        fcn16s = torchfcn.models.FCN16s()
        state_dict = torch.load(args.pretrained_model)
        try:
            fcn16s.load_state_dict(state_dict)
        except RuntimeError:
            fcn16s.load_state_dict(state_dict['model_state_dict'])
        model.copy_params_from_fcn16s(fcn16s)
    if cuda:
        model = model.cuda()

    # 3. optimizer

    optim = torch.optim.SGD(
        [
            {'params': get_parameters(model, bias=False)},
            {'params': get_parameters(model, bias=True),
             'lr': args.lr * 2, 'weight_decay': 0},