D_real.backward(mone) RuntimeError: invalid gradient at index 0 - expected shape [] but got [1]

[ramesh720]

while training wgan-gp i got this error. can you help to sove this . thanks in ADVANCE

[DanielLongo]

had the same issue. You need to make one a scalar not array. Try one = torch.ones([])

[horsepurve]

use

D_real = D_real.mean().unsqueeze(0)

[Harryjun]

I have the same issue. could you tell me how to do

[Harryjun]

@ramesh720 Hi, I have the same issue. could you tell me how to do

[demarche]

use

one = torch.tensor(1, dtype=torch.float)
mone = one * -1