mirrors
/
mmsegmentation
mirror of https://github.com/open-mmlab/mmsegmentation.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
mmsegmentation/mmseg/models/utils/__init__.py

16 lines
648 B
Python
Raw Normal View History

[Feature] Segformer backbone re-implementation (#594) * [Feature]Segformer re-implementation * Using act_cfg and norm_cfg to control activation and normalization * Split this PR into several little PRs * Fix lint error * Remove SegFormerHead * parameters init refactor * 1. Refactor segformer backbone parameters init; 2. Remove rebundant functions and unit tests; * Remove rebundant codes * 1. Remove rebundant codes; 2. Modify module name; * Refactor the backbone of segformer using mmcv.cnn.bricks.transformer.py * Fix some code logic bugs. * Add mit_convert.py to match pretrain keys of segformer. * Resolve some comments. * 1. Add some assert to ensure right params; 2. Support flexible peconv position; * Add pe_index assert and fix unit test. * 1. Add doc string for MixVisionTransformer; 2. Add some unit tests for MixVisionTransformer; * Use hw_shape to pass shape of feature map. * 1. Fix doc string of MixVisionTransformer; 2. Simplify MixFFN; 3. Modify H, W to hw_shape; * Add more unit tests. * Add doc string for shape convertion functions. * Add some unit tests to improve code coverage. * Fix Segformer backbone pretrain weights match bug. * resolve the shape convertion functions doc string. * Add pad_to_patch_size arg. * Modify default value of pad_to_patch_size arg.
2021-07-20 00:40:40 +08:00
from .ckpt_convert import mit_convert, swin_convert, vit_convert
[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
from .embed import PatchEmbed
[New model] Support MobileNetV3 (#268) * delete markdownlint * Support MobileNetV3 * fix import * add mobilenetv3 head and configs * Modify MobileNetV3 to semantic segmentation version * modify mobilenetv3 configs * add std configs * fix Conv2dAdaptivePadding bug * add configs * add unitest and fix bugs * fix lraspp unitest bugs * restore * fix unitest * add MobileNetV3 docstring * add mmcv * add mmcv * fix syntax bug * fix unitest bug * fix unitest bug * fix unitest bugs * fix docstring * add configs * restore * delete unnecessary assert * modify unitest * delete benchmark
2020-12-26 16:02:50 +08:00
from .inverted_residual import InvertedResidual, InvertedResidualV3
[Feature] Support MobileNetV2 backbone (#86) * [Feature] Support MobileNetV2 backbone * Fixed import * Fixed test * Fixed test * Fixed dilate * upload model * update table * update table * update bibtex * update MMCV requirement
2020-09-04 15:35:52 +08:00
from .make_divisible import make_divisible
init commit
2020-07-07 20:52:19 +08:00
from .res_layer import ResLayer
refactor test organization (#440) * refactor test organization * fixed se layer * update mmcv uper bound
2021-03-31 08:55:09 +08:00
from .se_layer import SELayer
init commit
2020-07-07 20:52:19 +08:00
from .self_attention_block import SelfAttentionBlock
[Feature] Segformer backbone re-implementation (#594) * [Feature]Segformer re-implementation * Using act_cfg and norm_cfg to control activation and normalization * Split this PR into several little PRs * Fix lint error * Remove SegFormerHead * parameters init refactor * 1. Refactor segformer backbone parameters init; 2. Remove rebundant functions and unit tests; * Remove rebundant codes * 1. Remove rebundant codes; 2. Modify module name; * Refactor the backbone of segformer using mmcv.cnn.bricks.transformer.py * Fix some code logic bugs. * Add mit_convert.py to match pretrain keys of segformer. * Resolve some comments. * 1. Add some assert to ensure right params; 2. Support flexible peconv position; * Add pe_index assert and fix unit test. * 1. Add doc string for MixVisionTransformer; 2. Add some unit tests for MixVisionTransformer; * Use hw_shape to pass shape of feature map. * 1. Fix doc string of MixVisionTransformer; 2. Simplify MixFFN; 3. Modify H, W to hw_shape; * Add more unit tests. * Add doc string for shape convertion functions. * Add some unit tests to improve code coverage. * Fix Segformer backbone pretrain weights match bug. * resolve the shape convertion functions doc string. * Add pad_to_patch_size arg. * Modify default value of pad_to_patch_size arg.
2021-07-20 00:40:40 +08:00
from .shape_convert import nchw_to_nlc, nlc_to_nchw
add unet (#161) * add unet * add unet * add unet * update test_unet * update test_unet * update test_unet * update test_unet * fix bugs * add init method for unet * add test of UNet init_weights method * add registry * merge upsample * fix test * Update mmseg/models/backbones/unet.py Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com> * Update mmseg/models/backbones/unet.py Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com> * split UpConvBlock from UNet * use reversed * rename upsample module * rename upsample module * rename upsample module * rename upsample module Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-10-22 02:24:38 +08:00
from .up_conv_block import UpConvBlock
init commit
2020-07-07 20:52:19 +08:00
[Enhance] Refactor inverted residual (#164) * [Enhance] Unifed InvertedResidual in MobileNetV2 and FastSCNN * [Enhance] Unifed InvertedResidual in MobileNetV2 and FastSCNN
2020-09-28 00:33:51 +08:00
__all__ = [
add unet (#161) * add unet * add unet * add unet * update test_unet * update test_unet * update test_unet * update test_unet * fix bugs * add init method for unet * add test of UNet init_weights method * add registry * merge upsample * fix test * Update mmseg/models/backbones/unet.py Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com> * Update mmseg/models/backbones/unet.py Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com> * split UpConvBlock from UNet * use reversed * rename upsample module * rename upsample module * rename upsample module * rename upsample module Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-10-22 02:24:38 +08:00
'ResLayer', 'SelfAttentionBlock', 'make_divisible', 'InvertedResidual',
[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
'UpConvBlock', 'InvertedResidualV3', 'SELayer', 'vit_convert',
[Feature] Segformer backbone re-implementation (#594) * [Feature]Segformer re-implementation * Using act_cfg and norm_cfg to control activation and normalization * Split this PR into several little PRs * Fix lint error * Remove SegFormerHead * parameters init refactor * 1. Refactor segformer backbone parameters init; 2. Remove rebundant functions and unit tests; * Remove rebundant codes * 1. Remove rebundant codes; 2. Modify module name; * Refactor the backbone of segformer using mmcv.cnn.bricks.transformer.py * Fix some code logic bugs. * Add mit_convert.py to match pretrain keys of segformer. * Resolve some comments. * 1. Add some assert to ensure right params; 2. Support flexible peconv position; * Add pe_index assert and fix unit test. * 1. Add doc string for MixVisionTransformer; 2. Add some unit tests for MixVisionTransformer; * Use hw_shape to pass shape of feature map. * 1. Fix doc string of MixVisionTransformer; 2. Simplify MixFFN; 3. Modify H, W to hw_shape; * Add more unit tests. * Add doc string for shape convertion functions. * Add some unit tests to improve code coverage. * Fix Segformer backbone pretrain weights match bug. * resolve the shape convertion functions doc string. * Add pad_to_patch_size arg. * Modify default value of pad_to_patch_size arg.
2021-07-20 00:40:40 +08:00
'mit_convert', 'swin_convert', 'PatchEmbed', 'nchw_to_nlc', 'nlc_to_nchw'
[Enhance] Refactor inverted residual (#164) * [Enhance] Unifed InvertedResidual in MobileNetV2 and FastSCNN * [Enhance] Unifed InvertedResidual in MobileNetV2 and FastSCNN
2020-09-28 00:33:51 +08:00
]