Generator in gan_cifar10 should use BatchNorm1D in preprocess

[gurgehjm]

wgan-gp/gan_cifar10.py

Line 42 in ae47a18

nn.BatchNorm2d(4 * 4 * 4 * DIM),

As the title says, based on how the code is written, i.e. the size of the noise variable is (BATCH_SIZE, 128), then we should use BatchNorm1d instead of BatchNorm2d.

Is this right?

[wchzh]

I have found this problem, and it give me some trouble to find this error. We should use the BatchNorm1d instead of BatchNorm2d.