Will moving tensor from GPU to CPU to GPU break back-propagation?

Hi,

I have to do torch.inverse() on tensor with a size of 4 x 240 x 320 x 3 x 3 every iteration during training. Since torch.inverse() supports batch inverse, I guess 3 x 3 is too small so torch.inverse() is pretty slow on GPU. So I moved the batch from GPU to CPU when doing torch.inverse() and move the output back to GPU for other operations. I’m wondering if GPU->CPU->GPU would break the back-propagation as I haven’t got any errors so far?

Hi,

No moving Tensors across devices is perfectly differentiable. It will all work fine!

1 Like