mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 06:26:09 +08:00
Code Issues Projects Releases Wiki Activity
mmsegmentation/configs/swin/swin-small-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py

11 lines
501 B
Python
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
_base_ = [
[Refactor] Update config names (#1964) * rename ann configs * update ann yml * update * update * update * update * update * update ann readme * update * update deeplabv3 * update readme * fix yml * fix beit
2022-08-26 18:48:56 +08:00
'./swin-tiny-patch4-window7-in1k-pre_upernet_8xb2-160k_ade20k-512x512.py'
[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
]
[Feature] Provide URLs of Swin Transformer pretrained models (#1389) * [Feature] Provide URLs of Swin Transformer pretrained models * [Feature] Add multi machine `dist_train`. (#1383) * Add training startup documentation * fix * fix * fix * fix * fix * fix * fix * fix * fix * delete pretrained=None in all six config files * [Fix] make arguments effective in tools/confusion_matrix.py (#1401) * add an argument for customizing `title' of the output figure * fix `color_theme' arguments not passing to plot function Signed-off-by: code14 <mob5566@gmail.com> * colab notebook: fix outdated link for doc (#1392) * colab notebook: fix outdated link for doc Fixed outdated link for how to customize your datasets by reorganizing data. * fix lint * fix typo (#1405) * [Fix] Fix windows-style path in `md2yml.py` in Windows pre-commit. (#1407) * test * avoid windows path * [Fix] fix the config name style description (#1414) Co-authored-by: FangjianLin <93248678+linfangjian01@users.noreply.github.com> Co-authored-by: Cody Wong <mob5566@gmail.com> Co-authored-by: Nemo Xiong <xiongnemo@126.com> Co-authored-by: Xiangxu-0103 <xuxiang0103@gmail.com> Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
2022-04-05 11:36:38 +08:00
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_small_patch4_window7_224_20220317-7ba6d6dd.pth' # noqa
[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
model = dict(
[Feature] Provide URLs of Swin Transformer pretrained models (#1389) * [Feature] Provide URLs of Swin Transformer pretrained models * [Feature] Add multi machine `dist_train`. (#1383) * Add training startup documentation * fix * fix * fix * fix * fix * fix * fix * fix * fix * delete pretrained=None in all six config files * [Fix] make arguments effective in tools/confusion_matrix.py (#1401) * add an argument for customizing `title' of the output figure * fix `color_theme' arguments not passing to plot function Signed-off-by: code14 <mob5566@gmail.com> * colab notebook: fix outdated link for doc (#1392) * colab notebook: fix outdated link for doc Fixed outdated link for how to customize your datasets by reorganizing data. * fix lint * fix typo (#1405) * [Fix] Fix windows-style path in `md2yml.py` in Windows pre-commit. (#1407) * test * avoid windows path * [Fix] fix the config name style description (#1414) Co-authored-by: FangjianLin <93248678+linfangjian01@users.noreply.github.com> Co-authored-by: Cody Wong <mob5566@gmail.com> Co-authored-by: Nemo Xiong <xiongnemo@126.com> Co-authored-by: Xiangxu-0103 <xuxiang0103@gmail.com> Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
2022-04-05 11:36:38 +08:00
backbone=dict(
init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
depths=[2, 2, 18, 2]),
[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
decode_head=dict(in_channels=[96, 192, 384, 768], num_classes=150),
auxiliary_head=dict(in_channels=384, num_classes=150))
Reference in New Issue Copy Permalink