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

Issue with Missing .pkl Files for EMLight #32

Open
BasAdam opened this issue Nov 17, 2024 · 1 comment
Open

Issue with Missing .pkl Files for EMLight #32

BasAdam opened this issue Nov 17, 2024 · 1 comment

Comments

@BasAdam
Copy link

BasAdam commented Nov 17, 2024

Issue with Missing .pkl Files for EMLight

Hi,

I’m encountering an issue with the EMLight project when trying to run the test.py script in the GenProjector folder. The following error is raised:

FileNotFoundError: [Errno 2] No such file or directory: '/home/fangneng.zfn/datasets/LavalIndoor/nips/pkl/'

I understand that the pkl directory should contain .pkl files necessary for the model to work, but it’s unclear how to obtain or generate these files.


What I’ve Done So Far

  1. I downloaded and placed the pre-trained weights in the RegressionNetwork/checkpoints folder.
  2. I tried pointing dataroot to a folder containing my own images, but the .pkl files seem essential for the script to run.
  3. I read the README, which mentions distribution_representation.py, but I couldn’t figure out how to use it to generate these files.

Questions

  1. What should the .pkl files in /nips/pkl/ contain?
  2. Is there a specific script or example to generate them?
  3. If the .pkl files are not necessary to test the pre-trained model, how can I bypass this requirement?

Context

  • Operating System: macOS
  • Python Version: 3.12
  • Hardware: CPU (no GPU available)
  • Image Path: /Users/adam/Desktop/test.png

Thank You!

Thank you very much for your help!
I’m happy to provide more details if needed. 😊

@GBWen2024
Copy link

Hi,I trained the regression network from small samples to large samples according to the suggestions in the readme, but when I trained 10,000 samples, the loss value increased instead of decreasing. Could you please tell me the specific steps of training the regression network, thank you very much!

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

2 participants