Example-Research-COAT/README.md

35 lines
1.2 KiB
Markdown
Raw Permalink Blame History

This file contains invisible Unicode characters!

This file contains invisible Unicode characters that may be processed differently from what appears below. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to reveal hidden characters.

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

## Cascade Transformers for End-to-End Person Search
### 一、代码说明
这个仓库是论文`Cascade Transformers for End-to-End Person Search [CVPR 2022]`的源码仓库。在这项工作中我们开发了一种新颖的级联遮挡感知Transformer (COAT) 模型,用于端到端行人搜索。该模型在`PRW`基准数据集上大幅超越了**当前最先进**的方法,并在`CUHK-SYSU`数据集上达到了最先进的性能。
### 二、环境配置 & 运行
#### 2.1 开发环境的配置
本下项目可以采用`anaconda`或者`docker`进行环境配置。
`anaconda`的配置方式:
```shell
# 以下是安装anaconda环境安装的指令
conda create -n COAT python=3.8.1
conda activate COAT
```
#### 2.2 数据集的下载
##### 2.2.1 PRW 行人重识别视频数据集
- 发布机构: University of Technology Sydney
- 下载地址: https://hyper.ai/datasets/17890
- 原始发布地址: http://zheng-lab.cecs.anu.edu.au/Project/project_prw.html
##### 2.2.1 ...
### 三、框架说明
这篇论文采用基于`Transformer`的级联神经网络优化...,其核心框架如下说明:
![image-20241003004438891](./Docs/Image/COAT-Framework.png)