/MDGAN-Tensorflow

Simple Tensorflow implementation of "MDGAN: Mixture Density Generative Adversarial Networks" (CVPR 2019)

Primary LanguagePythonMIT LicenseMIT

MDGAN — Simple TensorFlow Implementation [Paper]

: Mixture Density Generative Adversarial Networks

Usage

fake_img = generator(noise)

real_logit = discriminator(real_img)
fake_logit = discriminator(fake_img)

g_loss = generator_loss(fake_logit)
d_loss = discriminator_loss(real_logit, fake_logit)

Reference

Author

Junho Kim