Skip to content

Modular Autoencoder training and inference pipeline using Pytorch Lighning.

Notifications You must be signed in to change notification settings

NJ-2020-thesis/AutoEncoders

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

61 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AutoEncoders

This project aims to create a modular Autoencoder training and inference pipeline. Different architectures of Autoencoders can easily be added for image representation generation along with image reconstruction.

The pipeline is designed to read a config file to dynamically generate the relavant input, output layer dimensions along with bottleneck layer size. Other training related hyperparameters are also read from the config file.

-----------------------------------------------------

📜 Dataset

The dataset used for testing consists of images captured from the wrist camera of a Kinova3 robot arm inside a coppeliaSim environment.

Ani

-----------------------------------------------------

📜 Contributors

🎓 This codebase is part of the authors Master Thesis titled Visuomotor Policy Learning for Predictive Manipulation

:octocat: Anirudh NJ
      Email: [email protected]
      GitHub: @njanirudh

-----------------------------------------------------

📜 References

  1. https://discuss.pytorch.org/t/model-eval-vs-with-torch-no-grad/19615/10
  2. https://github.com/ma-shamshiri/Human-Activity-Recognition/blob/main/README.md

About

Modular Autoencoder training and inference pipeline using Pytorch Lighning.

Topics

Resources

Stars

Watchers

Forks

Languages