EOFError: Ran out of input

[Barnonewdm]

python global_classifier.py --input_path ./examples/modified.jpg --model_path ./weights/global.pth --gpu_id 1

Traceback (most recent call last): File "global_classifier.py", line 64, in <module> model = load_classifier(args.model_path, args.gpu_id) File "global_classifier.py", line 19, in load_classifier state_dict = torch.load(model_path, map_location='cpu') File "/data/weidongming/Tools/miniconda3/envs/torch/lib/python3.6/site-packages/torch/serialization.py", line 387, in load return _load(f, map_location, pickle_module, **pickle_load_args) File "/data/weidongming/Tools/miniconda3/envs/torch/lib/python3.6/site-packages/torch/serialization.py", line 564, in _load magic_number = pickle_module.load(f, **pickle_load_args) EOFError: Ran out of input Could help me?

[PeterWang512]

It might be that your weights/global.pth is not downloaded properly. Can you try downloading the model weights again and see if it works?

[PeterWang512]

Also, you can try to download the weights manually. Here are the links: global.pth: https://www.dropbox.com/s/rb8zpvrbxbbutxc/global.pth?dl=0 local.pth: https://www.dropbox.com/s/pby9dhpr6cqziyl/local.pth?dl=0