mirrors
/
person-re-ranking
mirror of https://github.com/zhunzhong07/person-re-ranking
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update README.md

pull/25/head
Zhun Zhong 2018-01-14 11:17:48 +11:00 committed by GitHub
parent 3d8dd9064d
commit ecf8577e6b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -31,6 +31,9 @@ The neighbor encoding method of our paper is inspired by the reference [2]. If y
1. re_ranking_feature.py: re-ranking with original feature, Euclidean distance is used. Thanks [Hao Luo](https://github.com/michuanhaohao) ! 1. re_ranking_feature.py: re-ranking with original feature, Euclidean distance is used. Thanks [Hao Luo](https://github.com/michuanhaohao) !
2. re_ranking_ranklist: re-ranking with given distance matrices, handle the difference of / division between python 2 and 3. Thanks [huang houjing](https://github.com/huanghoujing) ! 2. re_ranking_ranklist: re-ranking with given distance matrices, handle the difference of / division between python 2 and 3. Thanks [huang houjing](https://github.com/huanghoujing) !
### Pytorch re-implementations
-[Person_reID_baseline + Random Erasing + Re-ranking](https://github.com/layumi/Person_reID_baseline_pytorch)
================================================================ ================================================================
## The new training/testing protocol for CUHK03 ## The new training/testing protocol for CUHK03