mirrors
/
mmselfsup
mirror of https://github.com/open-mmlab/mmselfsup.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Fix] Fix lint of maskfeat (#520)

pull/526/head
Yixiao Fang 2022-10-18 15:32:04 +08:00
parent 8a15c412e8
commit bf5a82b502
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
configs/selfsup/maskfeat/README.md
View File

@ -17,9 +17,9 @@ We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training
Here, we report the results of the model, which is pre-trained on ImageNet-1k
for 400 epochs, the details are below:
| Backbone | Pre-train epoch | Fine-tuning Top-1 | Pre-train Config | Fine-tuning Config | Download |
| :------: | :-------------: | :---------------: | :------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| ViT-B/16 | 300 | 83.5 | [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-coslr-300e_in1k.py) | [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/classification/imagenet/maskfeat_vit-base-p16_ft-8xb512-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/mae/mae_vit-base-p16_8xb512-coslr-400e_in1k-224_20220223-85be947b.pth) \| [log](https://download.openmmlab.com/mmselfsup/mae/mae_vit-base-p16_8xb512-coslr-300e_in1k-224_20220210_140925.log.json) |
| Backbone | Pre-train epoch | Fine-tuning Top-1 | Pre-train Config | Fine-tuning Config | Download |
| :------: | :-------------: | :---------------: | :------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
| ViT-B/16 | 300 | 83.5 | [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-coslr-300e_in1k.py) | [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/classification/imagenet/maskfeat_vit-base-p16_ft-8xb512-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/maskfeat/maskfeat_vit-base-p16_8xb256-coslr-300e_in1k_20220913-591d4c4b.pth) \| [log](https://download.openmmlab.com/mmselfsup/maskfeat/maskfeat_vit-base-p16_8xb256-coslr-300e_in1k_20220829_225552.log.json) |
## Citation