PyRetri

Introduction

PyRetri is a novel deep learning-based image retrieval toolbox based on PyTorch, which is designed for researchers and engineers.

Pyretri is a versatile deep learning-based image retrieval toolbox designed with simplicity, flexibility in mind.

Modular Design: We decompose the deep learning-based image retrieval into several stages and one can easily construct a image retrieval pipeline by combining different modules.
Flexible Loading: The toolbox is able to adapt to load several types of model parameters, including parameters with the same keys and shape, parameters with different keys, and parameters with the same keys but different shapes.
Support of Multiple Methods: The toolbox directly supports several popluar methods designed for deep learning-based image retrieval, which are also suitable for person re-identification.
Combinations Search Tool: We provide the pipeline combinations search scripts to help users to find possible combinations of approaches with various hyper-parameters.

The toolbox supports several popluar methods and one can design and add their own modules.

Pre-processing
- DirectReszie, PadResize, ShorterResize
- CenterCrop, TenCrop
- TwoFlip
- ToTensor, ToCaffeTensor
- Normalize
Feature Representation
- GAP, GMP
- R-MAC, SPoC, CroW, GeM, SCDA, PWA
- PCB
Post-processing
- SVD, PCA
- DBA
- QE, K-reciprocal

This project is released under the Apache 2.0 license.

Please refer to INSTALL.md for installation and dataset preparation.

Please see GETTING_STARTED.md for the basic usage of PyRetri.

Results and models are available in MODEL_ZOO.md.

If you use this toolbox in your research, please cite this project.

If you have any questions about our work, please do not hesitate to contact us by emails.