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 comments in the model zoo

pull/430/head
kaiyangzhou 2021-04-04 10:09:15 +08:00
parent 1da9383b43
commit fac15fe098
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docs/MODEL_ZOO.md
View File

@ -4,6 +4,7 @@
- When computing model size and FLOPs, only layers that are used at test time are considered (see `torchreid.utils.compute_model_complexity`). - When computing model size and FLOPs, only layers that are used at test time are considered (see `torchreid.utils.compute_model_complexity`).
- Asterisk (\*) means the model is trained from scratch. - Asterisk (\*) means the model is trained from scratch.
- `combineall=True` means all images in the dataset are used for model training. - `combineall=True` means all images in the dataset are used for model training.
- Why not use heavy data augmentation like [random erasing](https://arxiv.org/abs/1708.04896) for model training? It's because heavy data augmentation might harm the cross-dataset generalization performance (see [this paper](https://arxiv.org/abs/1708.04896)).
## ImageNet pretrained models ## ImageNet pretrained models