val-iisc/deligan Issues
Latent Space
Updated 5Some questions about the project
Closed 1Mode Collapse for toy dataset?
Closed 2Results in dg_mnist.py
Closed 1fixed batch size
Closed 3generating same sample
Closed 1
This project is an implementation of the Generative Adversarial Network proposed in our CVPR 2017 paper - DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data. DeLiGAN is a simple but effective modification of the GAN framework and aims to improve performance on datasets which are diverse yet small in size.