RuntimeError: Expected object of backend CUDA but got backend CPU for ...

[starhiking]

The original code doesn't consider the gpu situation for loss, and will lead to the problem: RuntimeError: Expected object of backend CUDA but got backend CPU for ...

original code: https://github.com/yhenon/pytorch-retinanet/blob/ef2c16f4ad66b652b836be36465ee63c978f3194/retinanet/losses.py#L64

change:

regression_losses.append(torch.tensor(0).float().cuda())

[LIYHUI]

It really works, but why?

[starhiking]

It really works, but why?

CUDA is avaliable for that situation

[LIYHUI]

It really works, but why?

CUDA is avaliable for that situation

thank you, I am not familiar with that, but I understand it now.

[wvalcke]

Was a PR created for this ? This really fixes an error in the code.