Bug reversing the direction of the gradient

[phdmatamoros]

When I tried to train wassertein autoencoder , i have this error
d_z_loss.backward(-one)

RuntimeError: Mismatch in shape: grad_output[0] has a shape of torch.Size([1]) and output[0] has a shape of torch.Size([]).

[gabrielctn]

I have the exact same error, did you find a solution ?

[gabrielctn]

It seems like replacing

one = torch.tensor([1], dtype=torch.float)

by

one = torch.tensor(1, dtype=torch.float)

works