A Tiny Person ReID Baseline
Paper: "Bag of Tricks and A Strong Baseline for Deep Person Re-identification"[pdf]
This project refers the official code link and can reproduce the results as good as it on Market1501 when the input size is set to 256x128. If you find this project useful, please cite the offical paper.
@inproceedings{luo2019bag,
title={Bag of Tricks and A Strong Baseline for Deep Person Re-identification},
author={Luo, Hao and Gu, Youzhi and Liao, Xingyu and Lai, Shenqi and Jiang, Wei},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
year={2019}
}
Difference from Official Code
- Developed based on the pytorch template link
- No need to install ignite and yacs
- Support computing DistMap using cosine similarity
- Set hyperparameters using a configuration class
- Only support ResNet50 as the backbone
Pipeline
Results on Market1501 (rank1/rank5/rank10/mAP)
Model | Market1501 |
---|---|
ResNet50 (128x64) | 88.2/95.7/97.5/70.5 |
The pretrained model can be downloaded now. Extraction code is u3q5.
Get Started
-
cd
to folder where you want to download this repo -
Run
git clone https://github.com/lulujianjie/person-reid-tiny-baseline.git
-
Install dependencies:
- pytorch>=0.4
- torchvision
Train
python train.py
Test
python test.py