I am unable to load the pretrained model. I guess the pretrained model was done on a Windows PC and my system is on Ubuntu.
Is there anyway to convert it to a linux file?
Model Summary: 116 layers, 21935940 parameters, 21935940 gradients
Traceback (most recent call last):
File "eval.py", line 246, in
eval()
File "eval.py", line 71, in eval
checkpoint = torch.load('/home/cairs/code/crowd/multitask/crowd_counting/runs/weights/ShanghaiA_multi/model_best.pth.tar')
File "/home/cairs/miniconda3/envs/multitask/lib/python3.8/site-packages/torch/serialization.py", line 712, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/home/cairs/miniconda3/envs/multitask/lib/python3.8/site-packages/torch/serialization.py", line 1049, in _load
result = unpickler.load()
File "/home/cairs/miniconda3/envs/multitask/lib/python3.8/pathlib.py", line 1043, in new
raise NotImplementedError("cannot instantiate %r on your system"
NotImplementedError: cannot instantiate 'WindowsPath' on your system
I am unable to load the pretrained model. I guess the pretrained model was done on a Windows PC and my system is on Ubuntu.
Is there anyway to convert it to a linux file?