torch
准确率高 Python 2.7
https://github.com/qiaoguan/Person-reid-GAN-pytorch
稀疏标记平滑正则化在半监督人身份识别中的应用，准确率比较高，有权重
Sparse Label Smoothing Regularization for semi-supervised Person Re-Identification
https://github.com/jpainam/SLS_ReID
Multi-query results for Market-1501 dataset
| Dataset | Rank 1 | Rank 5 | Rank 10 | mAP |
|---|---|---|---|---|
| ResNet baseline | 91.27% | 96.85% | 98.19% | 76.94% |
| DenseNet baseline | 92.90% | 97.89% | 98.69% | 81.22% |
| Resnet SLS_ReID | 92.25% | 97.51% | 98.34% | 81.92% |
| Dense SLS_ReID | 94.06% | 98.16% | 98.84% | 85.20% |
多粒度网络 python3 准确率高 0.98
https://github.com/seathiefwang/MGN-pytorch
| mAP | rank1 | rank3 | rank5 | rank10 | |
|---|---|---|---|---|---|
| 2018-7-22 | 0.9217 | 0.9460 | 0.9653 | 0.9706 | 0.9801 |
| 2018-7-24 | 0.9353 | 0.9534 | 0.9706 | 0.9768 | 0.9849 |
https://github.com/levyfan/reid-mgn
面向人身份识别的人类语义解析
Code for our CVPR 2018 paper - Human Semantic Parsing for Person Re-identification
https://github.com/emrahbasaran/SPReID
有预训练
| Market-1501 | CUHK03 | DukeMTMC-reID | ||||
|---|---|---|---|---|---|---|
| Model | mAP(%) | rank-1 | mAP(%) | rank-1 | mAP(%) | rank-1 |
| SPReIDw/fg | 77.62 | 90.88 | - | 87.69 | 65.66 | 81.73 |
| SPReIDw/fg-ft | 80.54 | 92.34 | - | 89.68 | 69.29 | 83.80 |
https://github.com/zhunzhong07/CamStyle
https://github.com/zhunzhong07/person-re-ranking
需要看：
https://github.com/huanghoujing/person-re-identification-check-eval-code
https://github.com/huanghoujing/person-reid-triplet-loss-baseline
https://github.com/huanghoujing/AlignedReID-Re-Production-Pytorch
17 cvpr
https://github.com/InnovArul/rgb_IR_personreid
效果未知：
https://github.com/ECer23/reid-tutorial
python 2
https://github.com/zyoohv/TSCNN
https://github.com/zydou/Deep-Person
实时的：
https://github.com/longcw/MOTDT
有训练
https://github.com/KaiyangZhou/deep-person-reid
https://github.com/VisualComputingInstitute/triplet-reid
70%准确率
https://github.com/layumi/Person_reID_baseline_pytorch
准确率不高：
https://github.com/mangye16/Visible-Thermal-Person-Re-Identification
matlab：
https://github.com/layumi/2016_person_re-ID
无训练
https://github.com/Cysu/open-reid
tf版：
https://github.com/pse-ecn/pose-sensitive-embedding
https://github.com/VisualComputingInstitute/triplet-reid
https://github.com/digitalbrain79/person-reid
c++：
https://github.com/Cysu/dgd_person_reid
https://github.com/qqxx6661/Trajectory-prediction