Keras implementation of some GAN models.

Sources:

• Improved Techniques for Training GANs
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANHacks

• tqdm==4.17.0
• opencv_python==3.3.0.10
• numpy==1.13.3
• matplotlib==2.0.2
• Keras==2.0.8
• Theano==0.9.0 or Tensorflow==1.3.0
• h5py==2.7.0
• parmap==1.5.1

Follow these instructions.

Follow these instructions

CelebA example results

MNIST example results

For each image:

• The first 2 rows are generated images
• The last 2 rows are real images