mirrors
/
deep-person-reid
mirror of https://github.com/KaiyangZhou/deep-person-reid.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

update readme

pull/17/head
KaiyangZhou 2018-04-30 12:41:10 +01:00
parent af9f1f234c
commit 6433ec9e98
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -10,7 +10,7 @@ We support
- download of trained models.
## Updates
- Apr 2018: Added [DukeMTMC-reID](https://github.com/layumi/DukeMTMC-reID_evaluation#dukemtmc-reid-description); Added [SqueezeNet](https://arxiv.org/abs/1602.07360) and [MobileNetV2 (CVPR'18)](https://arxiv.org/abs/1801.04381).
- Apr 2018: Added [DukeMTMC-reID](https://github.com/layumi/DukeMTMC-reID_evaluation#dukemtmc-reid-description); Added [SqueezeNet](https://arxiv.org/abs/1602.07360), [MobileNetV2 (CVPR'18)](https://arxiv.org/abs/1801.04381) and [ShuffleNet (CVPR'18)](https://arxiv.org/abs/1707.01083).
- Apr 2018: Added [Harmonious Attention CNN (CVPR'18)](https://arxiv.org/abs/1802.08122). We achieved Rank-1 42.4% (vs. 41.7% in the paper) on CUHK03 (Detected) by training from scratch. The result can be reproduced by `python train_img_model_xent.py -d cuhk03 -a hacnn --save-dir log/hacnn-xent-cuhk03 --height 160 --width 64 --max-epoch 500 --stepsize -1 --eval-step 50`.
- Apr 2018: Code upgraded to pytorch 0.4.0.
- Apr 2018: Added [CUHK03](http://www.ee.cuhk.edu.hk/~xgwang/CUHK_identification.html). Models are [available](https://github.com/KaiyangZhou/deep-person-reid#cuhk03-detected-new-protocol-767700).
@ -121,6 +121,7 @@ These two classes are used for [torch.utils.data.DataLoader](http://pytorch.org/
* `models/HACNN.py`: HACNN [15].
* `models/SqueezeNet.py`: SqueezeNet [18].
* `models/MobileNet.py`: MobileNetV2 [19].
* `models/ShuffleNet.py`: ShuffleNet [20].
See `models/__init__.py` for details regarding how to call these models in command line.
@ -261,3 +262,4 @@ Of course, you can pass `model.classifier.parameters()` to optimizer if you only
[17] [Zheng et al. Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro. ICCV 2017.](https://arxiv.org/abs/1701.07717) <br />
[18] [Iandola et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv:1602.07360.](https://arxiv.org/abs/1602.07360) <br />
[19] [Sandler et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. CVPR 2018.](https://arxiv.org/abs/1801.04381) <br />
[20] [Zhang et al. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. CVPR 2018.](https://arxiv.org/abs/1707.01083) <br />