关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
kqzhang
/
PAMTRI
Not watched
1
6
Fork 4
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
23 Commits
1 Branch
34 MiB
23 Download
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
kqzhang f6fbd49580 update veri.py | fix read picture error 1 year ago
MultiTaskNet fix READEME & dataset.py 2 years ago
PoseEstNet update veri.py | fix read picture error 1 year ago
image add PAMTRI model 2 years ago
README.md add PAMTRI model 2 years ago

README.md

目录

PAMTRI概述

PAMTRI使用多任务学习和嵌入的姿态表示来解决车辆重新识别的问题。模型框架由两个卷积神经网络（CNN）组成，如下图所示。上部：姿势估计网络(PoseEstNet)是高分辨率网络（HRNet）的延伸，用于预测关键点坐标（有置信度/可见度）和生成热图/分段。底部。多任务网络(MultiTaskNet)使用来自HRNet的嵌入式姿态信息，用于车辆的联合重新识别和属性分类。

论文 Tang Z , Naphade M , Birchfield S , et al. PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data[J]. IEEE, 2020.

模型架构

PAMTRI网络结构

具体代码实现如下：

  • PoseEstNet:用于车辆姿势估计的HRNet的修改版。

  • MultiTaskNet:使用嵌入式姿态表征的车辆联合重新识别和属性分类的多任务网络。

Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

Python Shell Markdown C++ Text

Contributors (1)
All

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit