mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/swin/README.md

46 lines
6.5 KiB
Markdown
Raw Normal View History

[WIP] Add Swin Transformer (#511) * add Swin Transformer * add Swin Transformer * fixed import * Add some swin training settings. * Fix some filename error. * Fix attribute name: pretrain -> pretrained * Upload mmcls implementation of swin transformer. * Refactor Swin Transformer to follow mmcls style. * Refactor init_weigths of swin_transformer.py * Fix lint * Match inference precision * Add some comments * Add swin_convert to load official style ckpt * Remove arg: auto_pad * 1. Complete comments for each block; 2. Correct weight convert function; 3. Fix the pad of Patch Merging; * Clean function args. * Fix vit unit test. * 1. Add swin transformer unit tests; 2. Fix some pad bug; 3. Modify config to adapt new swin implementation; * Modify config arg * Update readme.md of swin * Fix config arg error and Add some swin benchmark msg. * Add MeM and ms test content for readme.md of swin transformer. * Fix doc string of swin module * 1. Register swin transformer to model list; 2. Modify pth url which keep meta attribute; * Update swin.py * Merge config settings. * Modify config style. * Update README.md Add ViT link * Modify main readme.md Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com> Co-authored-by: sennnnn <201730271412@mail.scut.edu.cn> Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-07-01 23:41:55 +08:00
# Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
## Introduction
fix swin readme (#764)
2021-08-09 05:10:00 +08:00
<!-- [ALGORITHM] -->
[WIP] Add Swin Transformer (#511) * add Swin Transformer * add Swin Transformer * fixed import * Add some swin training settings. * Fix some filename error. * Fix attribute name: pretrain -> pretrained * Upload mmcls implementation of swin transformer. * Refactor Swin Transformer to follow mmcls style. * Refactor init_weigths of swin_transformer.py * Fix lint * Match inference precision * Add some comments * Add swin_convert to load official style ckpt * Remove arg: auto_pad * 1. Complete comments for each block; 2. Correct weight convert function; 3. Fix the pad of Patch Merging; * Clean function args. * Fix vit unit test. * 1. Add swin transformer unit tests; 2. Fix some pad bug; 3. Modify config to adapt new swin implementation; * Modify config arg * Update readme.md of swin * Fix config arg error and Add some swin benchmark msg. * Add MeM and ms test content for readme.md of swin transformer. * Fix doc string of swin module * 1. Register swin transformer to model list; 2. Modify pth url which keep meta attribute; * Update swin.py * Merge config settings. * Modify config style. * Update README.md Add ViT link * Modify main readme.md Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com> Co-authored-by: sennnnn <201730271412@mail.scut.edu.cn> Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-07-01 23:41:55 +08:00
```latex
@article{liu2021Swin,
title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
journal={arXiv preprint arXiv:2103.14030},
year={2021}
}
```
[Enhancement] Delete convert function and add instruction to ViT/Swin README.md (#791) * delete convert function and add instruction to README.md * unified model convert and README * remove url * fix import error * fix unittest * rename pretrain * rename vit and deit pretrain * Update upernet_deit-b16_512x512_160k_ade20k.py * Update upernet_deit-b16_512x512_80k_ade20k.py * Update upernet_deit-b16_ln_mln_512x512_160k_ade20k.py * Update upernet_deit-b16_mln_512x512_160k_ade20k.py * Update upernet_deit-s16_512x512_160k_ade20k.py * Update upernet_deit-s16_512x512_80k_ade20k.py * Update upernet_deit-s16_ln_mln_512x512_160k_ade20k.py * Update upernet_deit-s16_mln_512x512_160k_ade20k.py Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com> Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-08-26 06:00:41 +08:00
## Usage
To use other repositories' pre-trained models, it is necessary to convert keys.
We provide a script [`swin2mmseg.py`](../../tools/model_converters/swin2mmseg.py) in the tools directory to convert the key of models from [the official repo](https://github.com/SwinTransformer/Swin-Transformer-Semantic-Segmentation) to MMSegmentation style.
```shell
python tools/model_converters/swin2mmseg.py ${PRETRAIN_PATH} ${STORE_PATH}
```
E.g.
```shell
python tools/model_converters/swin2mmseg.py https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth pretrain/swin_base_patch4_window7_224.pth
```
This script convert model from `PRETRAIN_PATH` and store the converted model in `STORE_PATH`.
[WIP] Add Swin Transformer (#511) * add Swin Transformer * add Swin Transformer * fixed import * Add some swin training settings. * Fix some filename error. * Fix attribute name: pretrain -> pretrained * Upload mmcls implementation of swin transformer. * Refactor Swin Transformer to follow mmcls style. * Refactor init_weigths of swin_transformer.py * Fix lint * Match inference precision * Add some comments * Add swin_convert to load official style ckpt * Remove arg: auto_pad * 1. Complete comments for each block; 2. Correct weight convert function; 3. Fix the pad of Patch Merging; * Clean function args. * Fix vit unit test. * 1. Add swin transformer unit tests; 2. Fix some pad bug; 3. Modify config to adapt new swin implementation; * Modify config arg * Update readme.md of swin * Fix config arg error and Add some swin benchmark msg. * Add MeM and ms test content for readme.md of swin transformer. * Fix doc string of swin module * 1. Register swin transformer to model list; 2. Modify pth url which keep meta attribute; * Update swin.py * Merge config settings. * Modify config style. * Update README.md Add ViT link * Modify main readme.md Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com> Co-authored-by: sennnnn <201730271412@mail.scut.edu.cn> Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-07-01 23:41:55 +08:00
## Results and models
### ADE20K
| Method | Backbone | Crop Size | pretrain | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | -------- | --------- | ---------- | ------- | -------- | --- | --- | -------------- | ----- | ------------: | -------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| UperNet | Swin-T | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 5.02 | 21.06 | 44.41 | 45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542.log.json) |
| UperNet | Swin-S | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 6.17 | 14.72 | 47.72 | 49.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015.log.json) |
| UperNet | Swin-B | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 7.61 | 12.65 | 47.99 | 49.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340.log.json) |
| UperNet | Swin-B | 512x512 | ImageNet-22K | 224x224 | 16 | 160000 | - | - | 50.31 | 51.9 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650.log.json) |
| UperNet | Swin-B | 512x512 | ImageNet-1K | 384x384 | 16 | 160000 | 8.52 | 12.10 | 48.35 | 49.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020.log.json) |
| UperNet | Swin-B | 512x512 | ImageNet-22K | 384x384 | 16 | 160000 | - | - | 50.76 | 52.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth) &#124; [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459.log.json) |