issue of running inference
Naturallyyeyeye opened this issue · comments
Hi, I would like to ask for a help,I meet the problem as follows:
Traceback (most recent call last):
File "/home/yjj/Downloads/FlowNetPytorch-master/run_inference.py", line 121, in
main()
File "/home/yjj/.conda/envs/FlowNetPytorch/lib/python3.6/site-packages/torch/autograd/grad_mode.py", line 49, in decorate_no_grad
return func(*args, **kwargs)
File "/home/yjj/Downloads/FlowNetPytorch-master/run_inference.py", line 83, in main
network_data = torch.load(args.pretrained)
File "/home/yjj/.conda/envs/FlowNetPytorch/lib/python3.6/site-packages/torch/serialization.py", line 426, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File "/home/yjj/.conda/envs/FlowNetPytorch/lib/python3.6/site-packages/torch/serialization.py", line 603, in _load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: could not find MARK
What pytorch version are you using, and what file are you using to load the network?