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

tfsim-nightly

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

metric-learn

Metric learning algorithms in Python

open-metric-learning

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

finetuner

Task-oriented finetuning for better embeddings on neural search.

tensorflow-similarity

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

pylmnn

Large Margin Nearest Neighbors implementation in python

quaterion

Blazing fast framework for fine-tuning similarity learning models

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

powerful-benchmarker

A library for ML benchmarking. It's powerful.

metric-learning-layers

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

tomotwin-cryoet

Picking procedure for cryo em tomography

ggml-ot

Supervised OT with Global Ground Metric Learning

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

kernelmethods

Kernel methods and classes for composable kernel learning workflows.

pytorchcml

Collaborative Metric Learning implemented by PyTorch

chesspos

Embedding based chess position search and embedding learning for chess positions

tf-metric-learning

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

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.

ssrlib

A modular Python framework for Self-Supervised Learning with automatic component discovery and intelligent caching