Batchnorm layer missing in the discriminator?

lucidrains / lightweight-gan

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

MIT License

1.62k stars 220 forks source link

Batchnorm layer missing in the discriminator? #118

Closed Entuserr closed 2 years ago

Entuserr commented 2 years ago

Well I may be wrong, but it looks like there is a batchnorm layer missing in the discriminator, if compared with the original paper (the figure 4 states 'batchnorm + leaky relu').

I expected it to be present here.