Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
lib
 
 
 
 
 
 
 
 
 
 
 
 

Multi-purpose-Disentangling-Variational-Autoencoders-for-ECG-data

Work In Progress

PyTorch Implementations of 1-D CNN VAE architectures for learning frameworks presented in following papers:
1] Auto-Encoding Variational Bayes,
Diederik P. Kingma, Max Welling,
https://arxiv.org/pdf/1312.6114.pdf
2] beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Higgins et. al
https://openreview.net/pdf?id=Sy2fzU9gl
3] IBP-VAE:
Gyawali, et. al
https://arxiv.org/pdf/1909.01839.pdf
4] Group-based Learning of Disentangled Representations with Generalizability for Novel Contents
Haruo Hosoya
https://pdfs.semanticscholar.org/fcb0/031751b1aa0d17ebdcf48be3d8a4d076e5b0.pdf

All architectures are supported with:
1] Unsupervised Learning
2] Conditional Learning (VAE decoder conditioned on learnable class labels)
3] Deterministic classification network

Uses 1-dimensional convolutional neural network for VAEs.
All dependencies are in requirements.txt file

About

No description, website, or topics provided.

Resources

Releases

No releases published

Packages

No packages published

Languages