Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

.pt file not found #28

Open
t1307109256 opened this issue Oct 16, 2023 · 4 comments
Open

.pt file not found #28

t1307109256 opened this issue Oct 16, 2023 · 4 comments

Comments

@t1307109256
Copy link

The pre-trained model you gave only has a .pkl file but not a .pt file. Where can I get this file?
2023-10-16 18-19-55 的屏幕截图

@makaylacmac2
Copy link

makaylacmac2 commented Oct 17, 2023

In the file backbones/efficientnet_pytorch/utils.py at the bottom of the file there is code commented out. I assume the first two lines are supposed to be uncommented and the if-else commented out, but it still doesn't work for me. If you figure out this issue, please let me know.
image

I was able to download the file manually from the links defined in the mapping variables, but I apparently did not put it in the right location.

@t1307109256
Copy link
Author

May be you can try downloading the .pt files from link https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b3-5fb5a3c3.pth and link https://github.com/lukemelas/EfficientNet-PyTorch/releases/download/1.0/efficientnet-b4-6ed6700e.pth and then put them in the corresponding path (/data/efficientnet) and see if it works.

@molokanov50
Copy link

molokanov50 commented Feb 15, 2024

@makaylacmac2 @t1307109256 Put a dot before /data since without a dot it is considered as absolute path which obviously doesn't exist in linux. It worked for me.

@Gnonymous
Copy link

@makaylacmac2 Sorry to bother you. I would like to ask you if you have successfully performed the training, how was the training dataset's set up, was only one frame extracted from each video, according to extract_frames_idm.py?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants