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

eval.py for the demo #2

Closed
duyguislakoglu opened this issue Apr 1, 2020 · 2 comments
Closed

eval.py for the demo #2

duyguislakoglu opened this issue Apr 1, 2020 · 2 comments

Comments

@duyguislakoglu
Copy link

Hello,
Great work!

I tried to run eval.py for the demo. Since in default.yaml, test:eval_mesh_iou is true, it does not initialize 'dataset' properly (Because data provided for demo does not contain points_seq). I solved this issue by adding test:eval_mesh_iou:false to demo.yaml.

Is there anything I am missing here?

Thank you,
Duygu

@m-niemeyer
Copy link
Collaborator

Hi @duyguislakoglu , Thanks a lot for you message and interest!

Yes, you are right. We added the demo data only for a short demonstration of the generation, not for evaluation.

For running the full evaluation, you would have to

  1. Download and prepare the dataset
  2. Generate predicted data, e.g. with one of the pre-trained models
  3. Call the evaluation function

I hope this helps. Good luck with your research!

Best,
Michael

@duyguislakoglu
Copy link
Author

You are right. Since I was not able to download the dataset (due to some OS related problems), I wanted to try it with demo. I will run the full evaluation when the dataset is ready.

Thank you for your reply,
Duygu

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