The emd_loss has problem for backpropagation
Holmes-Alan opened this issue · comments
Holmes-Alan commented
I tried to use "get_emd_loss.py" but I met this problem
RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)
Could you resolve it?