Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
| Date | Stars |
|---|---|
| 2026-07-24 | 4439 |
| 2026-07-25 | 4439 |
| 2026-07-28 | 4439 |
| 2026-07-30 | 4439 |
| 2026-08-06 | 4439 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center"> Pytorch ReID </h1>
<h2 align="center"> Strong, Small, Friendly </h2>
[](https://opensource.org/licenses/MIT)
[](https://scholar.google.com/scholar?cites=270746001988088124)
[](https://github.com/layumi/Person_reID_baseline_pytorch/stargazers)
A tiny, friendly, strong baseline code for Object-reID (based on [pytorch](https://pytorch.org)) since 2017.
- **Strong.** It is consistent with the new baseline result in several top-conference works, e.g., [Joint Discriminative and Generative Learning for Person Re-identification(CVPR19)](https://arxiv.org/abs/1904.07223), [Beyond Part Models: Person Retrieval with Refined Part Pooling(ECCV18)](https://arxiv.org/abs/1711.09349), [Camera Style Adaptation for Person Re-identification(CVPR18)](https://arxiv.org/abs/1711.10295). We arrived Rank@1=88.24%, mAP=70.68% only with softmax loss.
- **Small.** With bf16/fp16 (supported by native pytorch), our baseline could be trained with only 2GB GPU memory.
- **Friendly.** You may use the off-the-shelf options to apply many state-of-the-art tricks in one line.
Besides, if you are new to object re-ID, you may check out our **[Tutorial](https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial)** first (8 min read) :+1: .
Share to
<!-- Facebook -->
<a href="http://www.facebook.com/sharer.php?u=https://github.com/layumi/Person_reID_baseline_pytorch/" target="_blank">
<img src="https://github.com/layumi/Person_reID_baseline_pytorch/raw/master/docs/1_Facebook_colored_svg_copy-64.webp" alt="Facebook" width="60"/>
</a>
<!-- Twitter -->
<a href="https://twitter.com/share?url=https://github.com/layumi/Person_reID_baseline_pytorch/&text=Strong,%20Small,%20Friendly%20Pytorch%20re-ID&hashtags=pytorch re-ID" target="_blank">
<img src="https://github.com/layumi/Person_reID_baseline_pytorch/raw/master/docs/2018_social_media_popular_app_logo_twitter-64.webp" alt="Twitter" width="60"/>
</a>
<!-- Weibo -->
<a href="https://service.weibo.com/share/share.php?url=https://github.com/layumi/Person_reID_baseline_pytorch/&text=Strong,%20Small,%20Friendly%20Pytorch%20re-ID&hashtags=pytorch re-ID" target="_blank">
<img src="https://github.com/layumi/Person_reID_baseline_pytorch/raw/master/docs/Weibo-64.webp" alt="Weibo" width="60" />
</a>
<!-- LinkedIn -->
<a href="http://www.linkedin.com/shareArticle?mini=true&url=https://github.com/layumi/Person_reID_baseline_pytorch/" target="_blank">
<img src="https://github.com/layumi/Person_reID_baseline_pytorch/raw/master/docs/circle-linkedin-64.webp" alt="LinkedIn" width="60" />
</a>
<!-- Email -->
<a href="mailto:?Subject=Strong, Small, Friendly Pytorch Re-identification&Body=I%20saw%20this%20and%20thought%20of%20you!%20 https://github.com/layumi/Person_reID_baseline_pytorch/">
<img src="https://github.com/layumi/Person_reID_baseline_pytorch/raw/master/docs/Email-64.webp" alt="Email" width="60"/>
</a>
## Tutorial
* [8 min Tutorial](https://github.com/layumi/Person_reID_baseline_pytorch/blob/master/tutorial/README.md)，[8分钟教程](https://zhuanlan.zhihu.com/p/50387521)
* [中文视频简介](https://www.bilibili.com/video/BV11K4y1f7eQ)
* [Answer to Tutorial](https://github.com/layumi/Person_reID_baseline_pytorch/blob/master/tutorial/Answers_to_Quick_Questions.md)
## Table of contents
* [Features](#features)
* [Some News](#some-news)
* [Trained Model](#trained-model)
* [Prerequisites](#prerequisites)
* [Getting Started](#getting-started)
* [Installation](#installation)
* [Dataset PreparatExcerpt of 36,998 characters
Read on GitHub
Zhedong Zheng · University of Macau · China
165
Eddie He · South China Normal University (SCNU) · China
1
Yangxin Luo
1
Mikhail Scherbina · Glam Labs · Thailand
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:46aac8d9d95d185e, topic:tutorial, desc:tutorial, readme:tutorial
matched fp:46aac8d9d95d185e, topic:pytorch