ResNeXT OOM Error #3
Comments
Then perhaps you need to use a smaller batch size. |
I am using a GTX 1080 Ti, and was told your CAAD 2018 submission used a batch size of 20. Given that, I am wondering why the batch size needs to be reduced that significantly. |
It's best to paste your command so we know what you did. |
I am performing white-box evaluation on a single GPU. Note that I do not have trouble with the default batch size of 32 when evaluating R152. For ResNeXT, manually reducing the batch size to 10 still yields OOM errors.
|
In the CAAD submission, only forward pass is needed so the memory requirement there is very minimal. On a GPU with 16G memory I can run your command with 32 batch size while seeing some OOM messages (which did not affect the evaluation). |
Understood, my evaluation is terminated due to ResourceExhaustedError. I will reduce the batch size further. Thanks. |
I grabbed a 1080Ti with 10.4G free memory and I was able to execute your command with batch size 15. It's probably just an environment issue. I'm on TF1.13.0rc1, cuda10, cudnn7.4.24, if that matters. |
Get OOM error evaluating ResNeXT model even with batch size = 10
The text was updated successfully, but these errors were encountered: