update readme in projects/

This commit is contained in:
KaiyangZhou 2020-04-16 15:36:07 +01:00
parent 2bbaa47ab3
commit d0b735889d
2 changed files with 5 additions and 2 deletions

View File

@ -1,6 +1,6 @@
# Deep mutual learning # Deep mutual learning
This repo implements [Deep Mutual Learning](https://arxiv.org/abs/1706.00384) (DML) for person re-id. This repo implements [Deep Mutual Learning (CVPR'18)](https://zpascal.net/cvpr2018/Zhang_Deep_Mutual_Learning_CVPR_2018_paper.pdf) (DML) for person re-id.
We used this code in our [OSNet](https://arxiv.org/pdf/1905.00953.pdf) paper (see Supp. B). The training command to reproduce the result of "triplet + DML" (Table 12f in the paper) is We used this code in our [OSNet](https://arxiv.org/pdf/1905.00953.pdf) paper (see Supp. B). The training command to reproduce the result of "triplet + DML" (Table 12f in the paper) is
```bash ```bash
@ -9,6 +9,8 @@ python main.py \
--root $DATA --root $DATA
``` ```
`$DATA` corresponds to the path to your dataset folder.
Change `model.deploy` to `both` if you wanna enable model ensembling. Change `model.deploy` to `both` if you wanna enable model ensembling.
If you have any questions, please raise an issue in the Issues area. If you have any questions, please raise an issue in the Issues area.

View File

@ -1,3 +1,4 @@
Here are some research projects built on [Torchreid](https://arxiv.org/abs/1910.10093). Here are some research projects built on [Torchreid](https://arxiv.org/abs/1910.10093).
+ [Learning Generalisable Omni-Scale Representations for Person Re-Identification](OSNet_AIN) + [Learning Generalisable Omni-Scale Representations for Person Re-Identification](OSNet_AIN)
+ [Deep Mutual Learning (CVPR'18)](DML)