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

should it be false in stpls3d dataset? #51

Open
Rurouni-z opened this issue Jan 11, 2024 · 1 comment
Open

should it be false in stpls3d dataset? #51

Rurouni-z opened this issue Jan 11, 2024 · 1 comment

Comments

@Rurouni-z
Copy link

Rurouni-z commented Jan 11, 2024

if i set true, and use pretrained model from isbnet_backbone_stpls3d.yaml then i got error:

AssertionError: No inf checks were recorded for this optimizer.

otherwise i can train the all network

@Rurouni-z
Copy link
Author

Rurouni-z commented Jan 11, 2024

and i dont know why i always got OOM in training

i use single A100 to train model, but in a multi-GPU environment

and my command set up a specific GPU:

CUDA_VISIBLE_DEVICES=2 python3 tools/train.py configs/stpls3d/isbnet_stpls3d.yaml --trainall --exp_name default

update:

I tried changing fp16=true in backbone.yaml and got the worst results, but if I don't set true I have to set fp16=false in stpls3d.yaml which causes recurring OOM

@Rurouni-z Rurouni-z changed the title should it be false in stpl3d dataset? should it be false in stpls3d dataset? Jan 11, 2024
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