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>>>
JDOpenISCT
/
fast-reid
mirror of https://github.com/JDAI-CV/fast-reid
Not watched
8
21
Fork 17
Code
Releases 4 Wiki Activity
Issues 0 Datasets Model 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.
531 Commits
1 Branch
14 MiB
103 Download
 
 
 
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
fast-reid/projects/FastAttr
Sherlock ced654431b fix bug in attribute evaluation 2 years ago
..
configs bugfix for attribute project (#450) 3 years ago
fastattr fix bug in attribute evaluation 2 years ago
README.md update fastreid V1.0 3 years ago
train_net.py update fastreid v1.2 3 years ago

README.md

FastAttr in FastReID

This project provides a strong baseline for pedestrian attribute recognition.

Datasets Preparation

We use PA100k to evaluate the model's performance.
You can do download dataset from HydraPlus-Net.

Usage

The training config file can be found in projects/FastAttr/config, which you can use to reproduce the results of the repo.

For example

python3 projects/FastAttr/train_net.py --config-file projects/FastAttr/configs/pa100.yml --num-gpus 4

Experiment Results

We refer to A Strong Baseline of Pedestrian Attribute Recognition as our baseline methods and conduct the experiment
with 4 GPUs.
More details can be found in the config file and code.

PA100k

Method Pretrained mA Accu Prec Recall F1
attribute baseline ImageNet 80.50 78.84 87.24 87.12 86.78
FastAttr ImageNet 77.57 78.03 88.39 84.98 86.65
Delete task

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

cancel
confirm

该算法把样本聚类和特征学习融合到一个端到端的网络框架中，提升模型的跨域能力。该模型在Market训练，DukeMTMC上测试能达到82.0%的准确率，在DukeMTMC上训练，Market上测试能达到92.2%的准确率。

Text Python C++ Protocol Buffer Markdown other

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