I am trying to implement conditional GAN using GAN-CLS loss as described in paper: https://arxiv.org/abs/1605.05396
So, while training discriminator, I should I have three batches of data:
- [Real_Image, Embeddings]
- [Generated_Image, Embeddings]
And, while training generator, I should have one batch of data i.e [Generated_Image, Embeddings].
Is this correct way to train the model?