vita-epfl / hybrid-feature-fusion Goto Github PK

/root/anaconda3/envs/hff/lib/python3.7/site-packages/torchvision/models/_utils.py:193: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
f"The parameter '{pretrained_param}' is deprecated since 0.13 and may be removed in the future, "
/root/anaconda3/envs/hff/lib/python3.7/site-packages/torchvision/models/_utils.py:207: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=ResNet18_Weights.IMAGENET1K_V1. You can also use weights=ResNet18_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Traceback (most recent call last):
File "eval_hybrid.py", line 144, in
main()
File "eval_hybrid.py", line 124, in main
_ = load_from_checkpoint(decoder_path, decoder_lstm, optimizer=None, scheduler=None, verbose=True)
File "/media/ubuntu/新增磁碟區/hybrid-feature-fusion/src/utils.py", line 33, in load_from_checkpoint
checkpoint = torch.load(checkpoint_path,map_location='cpu')
File "/root/anaconda3/envs/hff/lib/python3.7/site-packages/torch/serialization.py", line 699, in load
with _open_file_like(f, 'rb') as opened_file:
File "/root/anaconda3/envs/hff/lib/python3.7/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/root/anaconda3/envs/hff/lib/python3.7/site-packages/torch/serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
IsADirectoryError: [Errno 21] Is a directory: '.'

Sorry, I am a beginner at this topic., there are two things that I want to ask.

1. Can you provide more tutorials to save the checkpoints?
2. Can you upload the checkpoints for the encoder & decoder files?

Thank you so much.

Hi,
First of all, thanks for sharing this code and for introducing this new benchmark . The paper is very interesting.
Is it possible to have the pretrained models that generate the results of the paper?
Thank you very much.

Hello, excellent work! I am interested in this paper. Finally, I can get the average precision for jaad and titan datasets. But I got in trouble here. Can you provide the command or how I can visualize the qualitative result of your paper from the draw.py file? Because when I run python3 draw.py, there has nothing happens. I appreciate any help you can provide.