Giter Club home page Giter Club logo

mindspore_daps's Introduction

DAPS描述

DAPS论文地址参见是ECCV2022的中稿工作,论文全名为Domain Adaptive Person Search。该方法基于SeqNet,在CUHK-SYSU和PRW两个数据集之间测试了互相的迁移性能,并针对行人搜索这一任务提出了新的域自适应方法。

如下为MindSpore使用CUHK-SYSU数据集对DAPS进行训练的示例。该项目的Pytorch实现版本可以参考

性能

Source Target mAP Top-1
PRW CUHK-SYSU 78.5 80.7
CUHK-SYSU PRW 35.3 80.2

数据集

使用的数据集:CUHK-SYSUPRW

环境要求

  • 硬件
    • 准备Ascend处理器搭建硬件环境。
  • 框架
    • MindSpore,本模型编写时版本为r1.2,12.30更新由r1.5编写的版本。
  • 如需查看详情,请参见如下资源:

脚本及样例代码

.
└─project1_fasterrcnn
  ├─README.md                           
  ├─scripts
    └─run_eval_ascend.sh                
    └─run_eval_gpu.sh                   
    └─run_eval_cpu.sh                   
  ├─src
    ├─FasterRcnn
      ├─__init__.py                     
      ├─hm.py                           // reid所使用的混合memory定义
      ├─cluster.py                      // 聚类方法
      ├─jaccad.py                       // 计算jaccad距离
      ├─anchor_generator.py             // 生成anchor
      ├─faster_rcnn_r50.py              // 模型定义
      ├─fpn_neck.py                     // neck层
      ├─rcnn.py                         // head(检测和重识别头)
      ├─resnet50.py                     // ResNet-50
      ├─roi_align.py                    // ROI Align层
      └─rpn.py                          // Region Proposal Network
    ├─config.py               
    ├─dataset.py              
    ├─lr_schedule.py          
    ├─network_define.py       
    └─util.py                 
  ├─cocoapi                   
  ├─pretrained_faster_rcnn.ckpt         
  ├─eval.py                   // evaluation script
  └─train.py                  // training script

环境准备

pip install -r requirements.txt

# install COCO evaluation API
cd cocoapi/PythonAPI
python setup.py install

模型性能评测

执行如下命令

# evaluate (on Ascend/GPU/CPU. Choose one according to your device.)
sh ./scripts/run_eval_ascend.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH]
sh ./scripts/run_eval_gpu.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH]
sh ./scripts/run_eval_cpu.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH]

mindspore_daps's People

Contributors

caposerenity avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.