iamiqbal/generative-adversarial-networks

Implementations of Generative Adversarial Networks and AutoEncoders in Pytorch

Generative Adversarial Networks

This repository contains the architectures of different GANs/AEs that I have learned and implemented when I took GANs Specialization offered by DeepLearning.ai. I have experimented with various datasets as well and the results are attached inside the notebooks.

Apart from this, the repository also contains notes that I took during the specialization. I will keep the repository updated as I experiment with/implement new generative models' architectures other than the specialization.

Table of Contents

S.No	GAN	Paper
1	Basic GANs	Generative Adversarial Networks
2	Deep Convolutional GANs	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
3	WGAN - with Gradient Penalty	Improved Training of Wasserstein GANs
4	Spectrally Normalized GANs	Spectral Normalization for Generative Adversarial Networks
5	Conditional GANs	Conditional Generative Adversarial Nets
6	Controllable GANs	Controllable Generative Adversarial Network
7	Info GAN	InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
8	Variational Autoencoder	Auto-Encoding Variational Bayes
9	Data Augmentation using GANs	Data Augmentation Generative Adversarial Networks