Discriminator

Discover how to implement the Discriminator in GANs using convolutional layers.

We'll cover the following

DCGAN discriminator implementation
Batchnormalization and LeakyReLU
Finalizing the discriminator model

The discriminator architecture is a map from a multidimensional space where images live to a much smaller dimensional space: the number line. This number line will be used to compute the probability that the input image is fake or real. Following the trend in computer vision, the discriminator architecture uses convolution layers to learn this projection. Our first discriminator implementation is based on a fully convolutional architecture called DCGAN. We provide DCGAN’s discriminator diagramDiscriminator DCGAN architectures. Source: Gluom's mxnet repo (https://gluon.mxnet.io/chapter14_generativeadversarial-networks/dcgan.html) below.

Get hands-on with 1400+ tech skills courses.

Getting Started

Deep Learning Basics and Environment Test

Introduction to Generative Models

Implementing Our First GAN

Evaluating Our First GAN

Improving Our First GAN

Synthesizing and Manipulating Images with GANs

Progressive Growing of GANs

Generation of Discrete Sequences Using GANs

Text-to-Image Synthesis with GANs

Speech Enhancement with GANs

TequilaGAN—Identifying GAN Samples

What’s Next in GANs

Conclusion

Appendix

Discriminator