nmichlo / disent
🧶 Modular VAE disentanglement framework for python built with PyTorch Lightning ▸ Including metrics and datasets ▸ With strongly supervised, weakly supervised and unsupervised methods ▸ Easily configured and run with Hydra config ▸ Inspired by disentanglement_lib
☆124Updated last year
Related projects ⓘ
Alternatives and complementary repositories for disent
- Ladder Variational Autoencoders (LVAE) in PyTorch☆89Updated 4 years ago
- Multimodal Mixture-of-Experts VAE☆194Updated last year
- ☆17Updated 10 months ago
- Disentanglement library for PyTorch☆274Updated 2 years ago
- Code for the paper: "Independent mechanism analysis, a new concept?"☆25Updated last year
- Repository for theory and methods for Out-of-Distribution (OoD) generalization☆63Updated 2 years ago
- A minimalist implementation of score-based diffusion model☆122Updated 3 years ago
- A curated list of techniques to avoid posterior collapse☆85Updated last year
- ☆121Updated last year
- Official PyTorch BIVA implementation (BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling)☆82Updated last year
- This repository contains code for applying Riemannian geometry in machine learning.☆78Updated 3 years ago
- code for "Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders".☆123Updated last year
- A σ-VAE implementation in PyTorch☆94Updated 3 years ago
- VAEs and nonlinear ICA: a unifying framework☆30Updated 4 years ago
- Official source code repository for the ICML 2021 paper "Hierarchical VAEs Know What They Don't Know"☆29Updated 2 years ago
- Code for "Bayesian Structure Learning with Generative Flow Networks"☆80Updated 2 years ago
- ☆146Updated 2 years ago
- Code for paper "SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows"☆284Updated 3 years ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆417Updated 2 years ago
- Code for the paper "Contrastive Learning Inverts the Data Generating Process".☆88Updated 3 months ago
- Code for ICE-BeeM paper - NeurIPS 2020☆87Updated 3 years ago
- Official Release of "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling"☆49Updated 4 years ago
- Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style☆48Updated 2 years ago
- Package for working with hypernetworks in PyTorch.☆118Updated last year
- Implementation and tutorials of normalizing flows with the novel distributions module☆160Updated 4 years ago
- Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J☆66Updated 7 months ago
- Algorithms for computations on random manifolds made easier☆86Updated 11 months ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆39Updated last year
- Transformers with doubly stochastic attention☆40Updated 2 years ago
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆37Updated 3 years ago