Representation Learning Python Packages

s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit

uform

Pocket-Sized Multimodal AI for Content Understanding and Generation

grailts

"GRAIL: Efficient Time-Series Representation Learning"

autobotlib

An autoML for explainable text classification.

open-metric-learning

OML is a PyTorch-based framework to train and validate the models producing high-quality embeddings.

crosslearn

Reusable representation extractors for reinforcement learning across vectors, images, and Chronos-backed time-series windows.

foundation-cancer-image-biomarker

[Nature Machine Intelligence 2024] Code and evaluation repository for the paper

avex

A comprehensive Python-based system for training, evaluating, and analyzing audio representation learning models with support for both supervised and self-supervised learning paradigms

cellmapper

k-NN-based mapping of cells across representations to transfer labels, embeddings, and expression values.

ampligraph

A Python library for relational learning on knowledge graphs.

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

pykg2vec

Python library for knowledge graph embedding and representation learning.

rs-embed

Unified ROI->embedding interface for remote sensing foundation models.

reptimeline

Track how discrete representations evolve during neural network training — lifecycle events, phase transitions, ontology discovery, and causal verification

topoembedx

Representation Learning on Topological Domains

hyper-models

A model zoo for non-Euclidean embedding models (hyperbolic, spherical, product manifolds)

deberta

The implementation of DeBERTa

embedders

High-level API for creating sentence and token embeddings

torch-molecule

torch-molecule is a deep learning package for molecular discovery, designed with an sklearn-style interface for property prediction, inverse design and representation learning.

torchok

Production-oriented Computer Vision models training pipeline for common tasks: classification, segmentation, detection and representation🥤

doraemon-torch

A powerful baseline for image classification, face recognition and image retrieval with Pytorch

mklpy

A package for Multiple Kernel Learning in Python

simple-clip

A minimal, but effective implementation of CLIP (Contrastive Language-Image Pretraining) in PyTorch

relic-pytorch

Simple self-supervised contrastive based on based on the ReLIC method