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

Problems encountered during the training of the model #32

Open
ChloeTT-LAO opened this issue Sep 25, 2023 · 0 comments
Open

Problems encountered during the training of the model #32

ChloeTT-LAO opened this issue Sep 25, 2023 · 0 comments

Comments

@ChloeTT-LAO
Copy link

Dear PoseNDF team,
Recently I encountered some problems when I run trainer.py on AMASS dataset. I found that no matter how I adjust the parameters, the loss function kept the same value unchanged after thousands of epochs having been iterated. I have no idea in which step I made mistakes, because I ran the code and generated the training dataset exactly the way you did.
What's more, I 'm a little confused about these two data files in load_data.py: data_path and amass_dir. What is the difference between them? According to my understanding, data_path refer to training dataset generated by prepare_traindata.py and amass_dir refer to sampled AMASS dataset, is that right? And what do these two variableds, data_files and amass_files refer to?
Look forward to your reply!
Thanks in advance!

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

1 participant