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.

contrastive-rl-pytorch

Contrastive Reinforcement Learning

tfsim-nightly

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

tensorflow-similarity

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

coca-pytorch

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

libauc

LibAUC: A Deep Learning Library for X-Risk Optimization

cebra

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

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 🖼️ & 🖋️

ak-ssl

A python library for self-supervised learning

clonetrast

CloneTrast reveals pan-cancer clonal niches of T-cells from single-cell RNA sequencing using contrastive learning

quaterion

Blazing fast framework for fine-tuning similarity learning models

kayak

Classify, route, and rank text in Python with self-hosted models. Typed decisions and evaluation.

simclr

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.

inf-cl

[CVPR 2025 Highlight] The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training scheme.

finest

Fine-grained Spatial Transcriptomics by integrating paired histology image

contrastive-ft

CRAFT: Contrastive Representation Aware Fine-Tuning toolkit

sceptr

Highly informative TCR representation model

cell-decipher

DECIPHER for learning high-fidelity disentangled embeddings from spatial omics data

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.

mammut-pytorch

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