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
- I downloaded and placed the pre-trained weights in the
RegressionNetwork/checkpoints folder.
- I tried pointing
dataroot to a folder containing my own images, but the .pkl files seem essential for the script to run.
- I read the README, which mentions
distribution_representation.py, but I couldn’t figure out how to use it to generate these files.
Questions
- What should the
.pkl files in /nips/pkl/ contain?
- Is there a specific script or example to generate them?
- 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. 😊
Issue with Missing
.pklFiles for EMLightHi,
I’m encountering an issue with the EMLight project when trying to run the
test.pyscript in theGenProjectorfolder. The following error is raised:FileNotFoundError: [Errno 2] No such file or directory: '/home/fangneng.zfn/datasets/LavalIndoor/nips/pkl/'
I understand that the
pkldirectory should contain.pklfiles necessary for the model to work, but it’s unclear how to obtain or generate these files.What I’ve Done So Far
RegressionNetwork/checkpointsfolder.datarootto a folder containing my own images, but the.pklfiles seem essential for the script to run.distribution_representation.py, but I couldn’t figure out how to use it to generate these files.Questions
.pklfiles in/nips/pkl/contain?.pklfiles are not necessary to test the pre-trained model, how can I bypass this requirement?Context
/Users/adam/Desktop/test.pngThank You!
Thank you very much for your help!
I’m happy to provide more details if needed. 😊