Load the trained model and report an error when testing separately

[liuge1008]

When I use your following code to load the model：
source_state = torch.load(args.weight)
target_state = OrderedDict()
for k, v in source_state.items():
if k[:7] != 'module.':
k = 'module.' + k
target_state[k] = v
model.load_state_dict(target_state)

Report an error：