CycleGAN

A CycleGAN is fundamentally similar to a DiscoGAN with one small modification. In a CycleGAN, we have the flexibility to determine how much weight to assign to the reconstruction loss with respect to the GAN loss or the loss attributed to the discriminator. This parameter helps in balancing the losses in correct proportions based on the problem at hand to help the network converge faster while training. The rest of the implementation of a CycleGAN is the same as that of the DiscoGAN.