Contrastive Learning Python Packages

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

lightly

A python library for self-supervised learning on images.

lightly-utils

A python library for self-supervised learning on images.

x-clip

A concise but complete implementation of CLIP with various experimental improvements from recent papers

cebra

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

info-nce-pytorch

PyTorch implementation of the InfoNCE loss for self-supervised learning.

tfsim-nightly

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

uform

Pocket-Sized Multimodal AI for Content Understanding and Generation

coca-pytorch

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

libauc

LibAUC: A Deep Learning Library for X-Risk Optimization

group-appeal-detector

Automated detection of social group appeals in text

contrastive-rl-pytorch

Contrastive Reinforcement Learning

tensorflow-similarity

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.

quaterion

Blazing fast framework for fine-tuning similarity learning models

ak-ssl

A python library for self-supervised learning

mammut-pytorch

Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch

pygcl

PyGCL: A PyTorch Library for Graph Contrastive Learning

simple-clip

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

graphids

Graph-based cloud intrusion detection using GCN, Transformer autoencoder, and contrastive learning — Scientific Reports 2025

relic-pytorch

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

gedml

GeDML is an easy-to-use generalized deep metric learning library, which contains state-of-the-art deep metric learning algorithms and auxiliary modules to build end-to-end compute vision systems

langml

A Keras-based and TensorFlow-backend language model toolkit.

contrastive-ft

CRAFT: Contrastive Representation Aware Fine-Tuning toolkit

open-retrievals

All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers