Open elliothe opened 7 years ago
Did you find a solution?
@keillernogueira , no I tried to migrate the backend function from pytorch to torch, but it looks like taking too much time. Then, I just move to pytorch. They are not maintaining torch anymore, so I suggest you just change the platform. You can check this: https://github.com/pytorch/pytorch/issues/1708
When I include the spatialdepthwiseconvolution in the network, the GPU memory usage keep growing during training, then running out of memory.