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

Very inaccurate results from pretrained model #30

Open
uros1610 opened this issue Oct 22, 2024 · 4 comments
Open

Very inaccurate results from pretrained model #30

uros1610 opened this issue Oct 22, 2024 · 4 comments

Comments

@uros1610
Copy link

I managed to run the pretrained model, downloaded from https://drive.google.com/file/d/1mqdBdVzC9myTWImkevQIn-AuBrVEix18/view?usp=sharing, on afwl dataset, but I am getting almost the same very inaccurate result on every image, so I wondered if anybody has tested this pretrained model, and what are the impressions?

@WZUchen
Copy link

WZUchen commented Nov 6, 2024

You can directly predict without pre-training, and the results are quite good. I have tested it.

@uros1610
Copy link
Author

uros1610 commented Nov 6, 2024

I had to train the model.Only then I managed to get good results.

@SFyingchen
Copy link

how to directly predict without pre-training? i have a error positions = m.vertices[m.faces].reshape((3 * len(m.faces), 3))
IndexError: index 0 is out of bounds for axis 0 with size 0, Do you have ? @WZUchen

@SFyingchen
Copy link

Do you have try the method offered by WZUchen? Do you have a good result? @uros1610

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

3 participants