The discriminator is simpler in comparison to the generator. Deep convolutional networks are commonplace in classification research. The key thing to remember with GANs, however, is that the training should be adversarial—simply grabbing state-of-the-art classification techniques may not give the generator the ability to learn. In essence, there is a balancing act to structuring your discriminator.
As always, keep track of your directory and make sure that you are placing newly developed structures in the right place, as follows:
DCGAN ├── data ├── docker ├── README.md ├── run.sh ├── scripts └── src ├── discriminator.py ├── gan.py ├── generator.py ├── save_to_npy.py
It's simple to modify the following structure from Goodfellow, to a DCGAN type; all you need to do is add two core changes to the Chapter...