GeDML is an easy-to-use generalized deep metric learning library

Borui Zhang

Last update: Dec 5, 2022

Related tags

Deep Learning computer-vision metric-learning loss-functions deep-metric-learning self-supervised-learning contrastive-learning

Overview

News

[2021-9-6]: v0.0.0 has been released.

Introduction

GeDML is an easy-to-use generalized deep metric learning library, which contains:

State-of-the-art DML algorithms: We contrain 18+ losses functions and 6+ sampling strategies, and divide these algorithms into three categories (i.e., collectors, selectors, and losses).
Bridge bewteen DML and SSL: We attempt to bridge the gap between deep metric learning and self-supervised learning through specially designed modules, such as collectors.
Auxiliary modules to assist in building: We also encapsulates the upper interface for users to start programs quickly and separates the codes and configs for managing hyper-parameters conveniently.

Installation

Pip

pip install gedml

Framework

This project is modular in design. The pipeline diagram is as follows:

Code structure

_debug: Debug files.
demo: Demos of configuration files.
docs: Documentation.
src: Source code.
- core: Losses, selectors, collectors, etc.
- client: Tmux manager.
- config: Config files including link, convert, assert and params.
- launcher: Manager, Trainer, Tester, etc.
- recorder: Recorder.

Method

Collectors

method	description
BaseCollector	Base class
DefaultCollector	Do nothing
ProxyCollector	Maintain a set of proxies
MoCoCollector	paper: Momentum Contrast for Unsupervised Visual Representation Learning
SimSiamCollector	paper: Exploring Simple Siamese Representation Learning
HDMLCollector	paper: Hardness-Aware Deep Metric Learning
DAMLCollector	paper: Deep Adversarial Metric Learning
DVMLCollector	paper: Deep Variational Metric Learning

Losses

classifier-based

method	description
CrossEntropyLoss	Cross entropy loss for unsupervised methods
LargeMarginSoftmaxLoss	paper: Large-Margin Softmax Loss for Convolutional Neural Networks
ArcFaceLoss	paper: ArcFace: Additive Angular Margin Loss for Deep Face Recognition
CosFaceLoss	paper: CosFace: Large Margin Cosine Loss for Deep Face Recognition

pair-based

method	description
ContrastiveLoss	paper: Learning a Similarity Metric Discriminatively, with Application to Face Verification
MarginLoss	paper: Sampling Matters in Deep Embedding Learning
TripletLoss	paper: Learning local feature descriptors with triplets and shallow convolutional neural networks
AngularLoss	paper: Deep Metric Learning with Angular Loss
CircleLoss	paper: Circle Loss: A Unified Perspective of Pair Similarity Optimization
FastAPLoss	paper: Deep Metric Learning to Rank
LiftedStructureLoss	paper: Deep Metric Learning via Lifted Structured Feature Embedding
MultiSimilarityLoss	paper: Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning
NPairLoss	paper: Improved Deep Metric Learning with Multi-class N-pair Loss Objective
SignalToNoiseRatioLoss	paper: Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning
PosPairLoss	paper: Exploring Simple Siamese Representation Learning

proxy-based

method	description
ProxyLoss	paper: No Fuss Distance Metric Learning Using Proxies
ProxyAnchorLoss	paper: Proxy Anchor Loss for Deep Metric Learning
SoftTripleLoss	paper: SoftTriple Loss: Deep Metric Learning Without Triplet Sampling

Selectors

method	description
BaseSelector	Base class
DefaultSelector	Do nothing
DenseTripletSelector	Select all triples
DensePairSelector	Select all pairs

Quickstart

Please set the environment variable WORKSPACE first to indicate where to manage your project.

Initialization

Use ConfigHandler to create all objects.

config_handler = ConfigHandler()
config_handler.get_params_dict()
objects_dict = config_handler.create_all()

Start

Use manager to automatically call trainer and tester.

manager = utils.get_default(objects_dict, "managers")
manager.run()

Directly use trainer and tester.

trainer = utils.get_default(objects_dict, "trainers")
tester = utils.get_default(objects_dict, "testers")
recorder = utils.get_default(objects_dict, "recorders")

# start to train
utils.func_params_mediator(
    [objects_dict],
    trainer.__call__
)

# start to test
metrics = utils.func_params_mediator(
    [
        {"recorders": recorder},
        objects_dict,
    ],
    tester.__call__
)

Document

For more information, please refer to:

📖 👉 Docs

Some specific guidances:

Configs

We will continually update the optimal parameters of different configs in TsinghuaCloud

Code Reference

TODO:

assert parameters
distributed methods and Non-distributed methods!!!
write github action to automate unit-test, package publish and docs building.
add cross-validation splits protocol.

You might also like...

Fast image augmentation library and easy to use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about library: https://www.mdpi.com/2078-2489/11/2/125

Albumentations Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to inc

11.4k Jan 9, 2023

Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation

Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation The code repository for "Audio-Visual Generalized Few-Shot Learning with

3 Jun 27, 2022

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

The official code for the NeurIPS 2021 paper Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

13 Dec 22, 2022

Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks

OnsagerNet Learning hidden low dimensional dyanmics using a Generalized Onsager Principle and neural networks This is the original pyTorch implemenati

3 Aug 24, 2022

An Easy-to-use, Modular and Prolongable package of deep-learning based Named Entity Recognition Models.

DeepNER An Easy-to-use, Modular and Prolongable package of deep-learning based Named Entity Recognition Models. This repository contains complex Deep

9 May 30, 2022

An efficient and easy-to-use deep learning model compression framework

TinyNeuralNetwork 简体中文 TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework, which contains features like neura

441 Dec 25, 2022

this is a lite easy to use virtual keyboard project for anyone to use

virtual_Keyboard this is a lite easy to use virtual keyboard project for anyone to use motivation I made this for this year's recruitment for RobEn AA

3 Oct 23, 2021

Metric learning algorithms in Python

metric-learn: Metric Learning in Python metric-learn contains efficient Python implementations of several popular supervised and weakly-supervised met

1.3k Dec 28, 2022

Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning"

VANET Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning" Introduction This is the implementation of article VAN

23 Dec 26, 2022

Comments

About the parameter information storage.

It will be more friendly to save the key parameter information in the experiments (like in a txt file) in order not to forget the parameter and it is easier to check the parameter for comparison.

opened by wangck20 1