Coder Social home page Coder Social logo

warren-ding / text-to-image-reidentification Goto Github PK

View Code? Open in Web Editor NEW

This project forked from cuiaiyu/text-to-image-reidentification

0.0 0.0 0.0 1.34 MB

A pytorch re-implementation of text-to-image Re-ID model Multi-granularity Image-text Alignments.

License: GNU General Public License v3.0

Jupyter Notebook 71.19% Python 28.67% Shell 0.14%

text-to-image-reidentification's Introduction

Language-to-vision Re-Identification: A Re-Implementation of Multi-granularity Image-text Alignments

(Still under testing)

@article{niu2020improving,
  title={Improving description-based person re-identification by multi-granularity image-text alignments},
  author={Niu, Kai and Huang, Yan and Ouyang, Wanli and Wang, Liang},
  journal={IEEE Transactions on Image Processing},
  volume={29},
  pages={5542--5556},
  year={2020},
  publisher={IEEE}
}
  • This is a beta version implementation. Bug could exist.
  • If you find this is useful in your research work, please cite the original paper (and probably star this repo ;-))

Dataset

Please download the train and val1 setfrom WIDER Person Search by Language dataset and save it in proper folder.

Performance

With bi-GRU as caption encoder and ResNet-50 as image encoder, we got the following results:

Model R@1 R@5 R@10
MIA (global-global) 47.56 71.34 79.34
MIA (global-global + global-part) 50.78 73.03 82.11
MIA (global-global + global-part + part-part) (reported) 53.10 75.00 82.90

for computational reason, we haven't implemented the global-global + global-part + part-part versiono of MIA, which might be released in next updates.

Train

run sh src/run.sh

Inference

run sh src/run.sh with --mode val and --load_ckpt_fn set as the path to the saved checkpoints.

Visualization

  1. Check notebook src/inference.ipynb for interactive retrieval with config set properly

  2. run python src/visualizations/heep_generator.py for generate a html page visualize retrieval result. Please set parameter accordingly to enable different visualization. e.g. False only for only display retrieval failures.

text-to-image-reidentification's People

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.