Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/astorfi/infogan-pytorch-1

Implementation of InfoGAN using PyTorch lightning

https://github.com/astorfi/infogan-pytorch-1

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Implementation of InfoGAN using PyTorch lightning

Basic Info
  • Host: GitHub
  • Owner: astorfi
  • License: mit
  • Default Branch: master
  • Homepage:
  • Size: 380 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of mohith-sakthivel/infogan-pytorch
Created over 4 years ago · Last pushed over 4 years ago

https://github.com/astorfi/infogan-pytorch-1/blob/master/ 

# Infogan

This project is an implementation of the paper infoGAN using Pytorch Lightning.

## Setup
```
git clone https://github.com/mohith-sakthivel/infogan-pytorch.git infogan_pl
cd infogan_pl

conda env create -f environment.yml
conda activate infogan_pl
```

## Run
To train the model on MNIST dataset , use
```
python -m infogan.infogan_module --datadir  --max_epochs 
```
### Arguments:
    datadir     - Directory to log data
    max_epochs  - Maximum number of training epochs

## Learnt Latent factors
InfoGAN can learn meaningul disentangled features in an unsupervised fashion. The following figures illustrate the high level image features captured by the latent factors when trained on the MNIST dataset. The latent code used has a variable sampled from a uniform categorical distribution with 10 classes and 2 independent gaussian variables. 

### Categorical Latents
- The follwing figure show the variation in the generated images with each class of the categorical distribution.
- The categorical latents captures the 10 digit classes



    



### Gaussian Latents
- The follwing figures show the variation in the generated images when the a single gaussian variable is gradually changed from -5 to +5.
- The first gaussian latent code learns to capture the thickness of the text



    



- The second gaussian latent code captures the orientation (or) slant of the digit



    



## To Do
    - Add other datasets
    - Implement Wasserstein loss with spectral normalization

## References
1. X Chen, Y Duan, R Houthooft, J Schulman, I Sutskever, P Abbeel - InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets, NeurIPS 2016. ([paper](https://arxiv.org/abs/1606.03657))

Owner

  • Name: Sina Torfi
  • Login: astorfi
  • Kind: user
  • Location: San Jose
  • Company: Meta

PhD & Developer working on Deep Learning, Computer Vision & NLP

GitHub Events

Total
Last Year