search

gauravmm / cifar-gan

Our start with GANs.
1 stars 0 forks source link

BatchNorm #14

Open gauravmm opened 7 years ago

gauravmm commented 7 years ago

Construct different mini-batches for real and fake, i.e. each mini-batch needs to contain only all real images or all generated images. when batchnorm is not an option use instance normalization (for each sample, subtract mean and divide by standard deviation).

gauravmm commented 7 years ago

See #35

There is a bug in Keras. See this issue: fchollet/keras#5644