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 on rendering Shapenet Dataset #6

Closed
AmanKishore opened this issue Oct 1, 2022 · 7 comments
Closed

Issue on rendering Shapenet Dataset #6

AmanKishore opened this issue Oct 1, 2022 · 7 comments

Comments

@AmanKishore
Copy link

When running:
python render_all.py --save_folder dataset/ --dataset_folder ShapeNetCore.v1/ --blender_root <path-to-blender>

Getting the following error:

ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
@SteveJunGao
Copy link
Collaborator

Hi @AmanKishore,

the script would still work with this error (render the images and save cameras). I also have seen the same output before

@AmanKishore
Copy link
Author

Cool, I was about to comment that it doesn't seem like an issue and can be ignored!
Thank you for the quick response!

@AmanKishore
Copy link
Author

@SteveJunGao Quick follow up, how long is the render_all script supposed to take? And is it dependant on GPU memory?

@SteveJunGao
Copy link
Collaborator

It depends on the type of GPU card you're using. Typically, it can run 2-3 days

@AmanKishore
Copy link
Author

Whoa that's extensive, any ideas on how to parallelize that across 8 GPUs?

@SteveJunGao
Copy link
Collaborator

You can split the whole shapenet objects into 8 different subsets, then use each GPU to render each subset. E.g GPU0 render 0-1000, GPU1 render 1000-2000, etc.

@AmanKishore
Copy link
Author

Good suggestion!

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