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

info-nce-pytorch

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

coca-pytorch

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

tensorflow-similarity

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

contrastive-rl-pytorch

Contrastive Reinforcement Learning

libauc

LibAUC: A Deep Learning Library for X-Risk Optimization

uform

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

cebra

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

tfsim-nightly

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

sc-concept

Contrastive pre-training for technology-agnostic single-cell representations beyond reconstruction

labelbank

Retrieve + rerank over a closed label bank: LLM bi-encoders with self-mined hard negatives and a generative listwise reranker

ak-ssl

A Self-Supervised Learning Library

group-appeal-detector

Python package to automatically detect presence and location of a social group mention in political text as well as the author's stance toward the referenced group and the qualitative group category.

simple-clip

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

qx-quark

Vector embeddings for quantum circuits, so equivalent ones land close

mammut-pytorch

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

inf-cl

A highly memory-efficient contrastive loss.

contrastive-ft

CRAFT: Contrastive Representation Aware Fine-Tuning toolkit

ctdecon

Reference-based cell type deconvolution in spatial transcriptomics.

open-retrievals

Text Embeddings for Retrieval and RAG based on transformers

relic-pytorch

A simple PyTorch implementation of the Representation Learning via Invariant Causal Mechanisms self-supervised contrastive learning paper