RuntimeError: CUDA error: out of memory about facial-expression-recognition.pytorch HOT 7 CLOSED

May be you can decrease your batch size

from facial-expression-recognition.pytorch.

Thanks, decreasing the batch size can fix the problem.
And can you tell me the resources of your computer for the training?

from facial-expression-recognition.pytorch.

parser.add_argument('--model', type=str, default='VGG19', help='CNN architecture')
parser.add_argument('--dataset', type=str, default='FER2013', help='CNN architecture')
parser.add_argument('--bs', default=128, type=int, help='batch size')
parser.add_argument('--lr', default=0.01, type=float, help='learning rate')

from facial-expression-recognition.pytorch.

I mean the GPU resource for supporting the 128 batch size training.

from facial-expression-recognition.pytorch.

nvidia 1080 Ti

from facial-expression-recognition.pytorch.

It's kind of weird, I can use batch_size 64 for training, but can't use use 64 for testing.
I'm pretty sure my GPU memory is quiet enough.

from facial-expression-recognition.pytorch.

y

i met this problem too.did u figure it out?

from facial-expression-recognition.pytorch.