TF-GAN is a lightweight library for training and evaluating Generative Adversarial Networks (GANs).
pip install tensorflow-gan, and used with
import tensorflow_gan as tfgan
TF-GAN is composed of several parts, which are designed to exist independently:
Frechet Distance, or
Kernel Distancewith a pretrained Inception network to evaluate your unconditional generative model. You can also use your own pretrained classifier for more specific performance numbers, or use other methods for evaluating conditional generative models.
Numerous projects inside Google. The following are some published papers that use TF-GAN:
Training in TF-GAN typically consists of the following steps:
At each stage, you can either use TF-GAN's convenience functions, or you can perform the step manually for fine-grained control.
There are various types of GAN setup. For instance, you can train a generator to sample unconditionally from a learned distribution, or you can condition on extra information such as a class label. TF-GAN is compatible with many setups, and we demonstrate in the well-tested examples directory