Metric Learning Python Packages

pytorch-metric-learning

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

catalyst

Accelerated deep learning R&D

metric-learn

Metric learning algorithms in Python

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.

open-metric-learning

Metric learning and retrieval pipelines, models and zoo.

finetuner

:dart: Task-oriented embedding tuning for BERT, CLIP, etc.

pylmnn

Large Margin Nearest Neighbors implementation in python

metric-learning-layers

A simple PyTorch package that includes the most common metric learning layers.

disent

Vae disentanglement framework built with pytorch lightning.

ggml-ot

Improve Optimal Transport applications by Global Ground Metric Learning (published at AISTATS2025). This package supports single-cell data in Anndata format and generic array-like data.

tomotwin-cryoet

Picking procedure for cryo em tomography

quaterion

Similarity Learning fine-tuning framework

powerful-benchmarker

A library for ML benchmarking. It's powerful.

pytorchcml

Collaborative Metric Learning implemented by PyTorch

tf-metric-learning

Minimalistic TensorFlow2+ deep metric/similarity learning library with loss functions, miners, and utils as embedding projector.

ssrlib

A modular Python framework for self-supervised representation analysis with automatic component discovery and training-time embedding monitoring

scmdml

scmdml

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

chesspos

A library for manipulating, learning and searching chess positions

kernelmethods

Foundational library for Kernel methods in pattern analysis and machine learning

wsingular

Python package for the ICML 2022 paper "Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors".

mtsc

mtSC

finetuner-client

Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks.