open-reid

Open source person re-identification library in python

Github星跟蹤圖

Open-ReID

Open-ReID is a lightweight library of person re-identification for research
purpose. It aims to provide a uniform interface for different datasets, a full
set of models and evaluation metrics, as well as examples to reproduce (near)
state-of-the-art results.

Installation

Install PyTorch (version >= 0.2.0). Although we support
both python2 and python3, we recommend python3 for better performance.

git clone https://github.com/Cysu/open-reid.git
cd open-reid
python setup.py install

Examples

python examples/softmax_loss.py -d viper -b 64 -j 2 -a resnet50 --logs-dir logs/softmax-loss/viper-resnet50

This is just a quick example. VIPeR dataset may not be large enough to train a deep neural network.

Check about more examples
and benchmarks.

主要指標

概覽
名稱與所有者Cysu/open-reid
主編程語言Python
編程語言Python (語言數: 1)
平台
許可證MIT License
所有者活动
創建於2017-02-20 03:30:29
推送於2019-04-23 11:49:54
最后一次提交2017-12-08 07:09:58
發布數0
用户参与
星數1.4k
關注者數39
派生數350
提交數212
已啟用問題?
問題數91
打開的問題數36
拉請求數7
打開的拉請求數1
關閉的拉請求數2
项目设置
已啟用Wiki?
已存檔?
是復刻?
已鎖定?
是鏡像?
是私有?