Cadene / vqa.pytorch

Visual Question Answering in Pytorch
713 stars 177 forks source link

Feature extraction: CUDA out of memory #46

Open AgarwalVedika opened 5 years ago

AgarwalVedika commented 5 years ago

Hi,

I am trying to extract features for coco dir - however it always gives me RuntimeError: CUDA out of memory. I have tried using single GPU by setting CUDA_VISIBLE_DEVICES=0- still ti gives me the same Runtime error even when the GPU is free.

What should I do?

Regards, Vedika

Cadene commented 5 years ago

You should use a smaller batch size. Best luck!


Remi Cadene PhD Student at LIP6 Sorbonne University http://remicadene.com 0033635504788

Le mer. 22 mai 2019 à 20:32, AgarwalVedika notifications@github.com a écrit :

Hi,

I am trying to extract features for coco dir - however it always gives me RuntimeError: CUDA out of memory. I have tried using single GPU by setting CUDA_VISIBLE_DEVICES=0- still ti gives me the same Runtime error even when the GPU is free.

What should I do?

Regards, Vedika

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/Cadene/vqa.pytorch/issues/46?email_source=notifications&email_token=ABDW6LQWVJQVC6XZFNQLCH3PWWGTVA5CNFSM4HOW4ZC2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4GVI723A, or mute the thread https://github.com/notifications/unsubscribe-auth/ABDW6LQFGS7GQYLN4WQBXILPWWGTVANCNFSM4HOW4ZCQ .