Vinay Raghavan

@erilyth See [this line](https://github.com/osh/KerasGAN/blob/master/mnist_gan.py#L192). Here, before training the GAN as a whole, we assign the output labels as all 1s in the 1 column, which is a label of all...

One this I noticed, but am not totally sure of, is that by adding [this line](https://github.com/osh/KerasGAN/blob/master/mnist_gan.py#L107), it makes the the discriminator part of the GAN untrainable before the GAN is...