In recent years, generative adversarial networks have proven to be very effective for training generative models and hundreds of different variants have been introduced. This proposal aims to implement novel techniques for training GANs efficiently such as mini-batch discrimination, virtual batch normalisation and additionally, adding support for Conditional GAN (CGAN). Future work for Stacked GAN (SGAN) is also proposed.

Organization

Student

Saksham Bansal

Mentors

  • Shikhar Jaiswal
close

2019