big-discriminator-batch-spoofing-gan
big-discriminator-batch-spoofing-gan copied to clipboard
BMSG-GAN with more features
There exists an apparent error in the implementation of LSGAN below. https://github.com/akanimax/BBMSG-GAN/blob/da82aa2e8507d17801bd2134a4ae754335d716f5/sourcecode/MSG_GAN/Losses.py#L145 Right implementation: ```python class LSGAN(GANLoss): def __init__(self, dis): super().__init__(dis) def dis_loss(self, real_samps, fake_samps): real_scores = th.mean((self.dis(real_samps) - 1)...
I run a few hours on 8GPUs wihtout any progress. Each sample is pixelwise copy of each other in all layers. 4x4  64x64  setup ``` git clone [email protected]:akanimax/BBMSG-GAN.git...
Hi there, I've been trying to get BBMSG-GAN running but haven't been able to get training started. I have two 11 GB 1080 Ti cards on Ubuntu 18.10 with pytorch...