1
0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00

129 Commits

Author SHA1 Message Date
xiexinch
55b0c3aef5 fix cgnet configs and encnet forward error 2022-07-07 14:18:17 +08:00
xiexinch
761e1a9983 minor change 2022-07-05 20:43:33 +08:00
limengzhang.vendor
c5ad7fb0b7 [Fix] Delete all **kwargs in Segmentor Forward function 2022-06-22 08:24:13 +00:00
zhengmiao
ffa0616a68 [Refactory] KNet head 2022-06-20 04:04:48 +00:00
zhengmiao
b23982d1b3 [Refactory] Refactory BaseSegmentor based BaseModel 2022-06-19 06:32:09 +00:00
linfangjian.vendor
6ca42737b6 [Fix] Fix pred 2022-06-14 02:53:46 +00:00
linfangjian.vendor
dd9c411335 [Refactor] Refactor decode_head and segmentors and add preprocess_cfg 2022-06-10 14:02:40 +00:00
MeowZheng
ee025ea33b [Fix]Add build head 2022-06-08 13:05:41 +08:00
linfangjian.vendor
7a32d610e4 [Refactor] Refactor all registries 2022-05-10 12:15:20 +00:00
wangbin
578d4d0c42 [Fix] Fix the bug in binary_cross_entropy ()
* [Fix] Fix the bug in binary_cross_entropy

 Fix the bug in binary_cross_entropy
'label.max() <= 1' should mask out ignore_index, since the ignore_index often set as 255.

* [Fix] Fix the bug in binary_cross_entropy, add comments

As the ignore_index often set as 255, so the binary class label check should mask out ignore_index.

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* [Fix] Fix the bug in binary_cross_entropy

As the ignore_index often set as 255, so the binary class label check should mask out ignore_index.

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-04-29 19:32:12 +08:00
Yuan Liu
43b8a1d8dc [Feature]: Add MAE ()
* [Fix]: Fix lint

* [WIP]: Add mae seg config

* [Feature]: Add MAE seg

* [Fix]: Fix mae dataset img scale bug

* [Fix]: Fix lint

* [Feature]: Change mae config to mae_segmentation's config

* [Feature]: Add interpolate pe when loading

* [Fix]: Fix pos_embed not used bug

* [Fix]: Fix lint

* [Fix]: Init rel pos embed with zeros

* [Fix]: Fix lint

* [Fix]: Change the type name of backbone to MAE

* [Fix]: Delete ade20k_512x512.py

* [Fix]: Use mmseg provided ade20k.py

* [Fix]: Change 1 sample per gpu to 2 samples per gpu

* [Fix]: Fix conflict

* [Refactor]: Use the TransformerEncoderLayer of  BEiT

* [Feature]: Add UT

* [Fix]: Change the default value of qv bias to False

* [Fix]: Initialize relative pos table with zeros

* [Fix]: Delete redundant code in mae

* [Fix]: Fix lint

* [Fix]: Rename qkv_bias to qv_bias

* [Fix]: Add docstring to weight_init of MAEAttention

* [Refactor]: Delete qv_bias param

* [Fix]: Add reference to fix_init_weight

* [Fix]: Fix lint

* [Fix]: Delete extra crop size

* [Refactor]: Rename mae

* [Fix]: Set bias to True

* [Fix]: Delete redundant params

* [Fix]: Fix lint

* [Fix]: Fix UT

* [Fix]: Add resize abs pos embed

* [Fix]: Fix UT

* [Refactor]: Use build layer

* [Fix]: Add licsense and fix docstring

* [Fix]: Fix docstring

* [Feature]: Add README metafile

* [Fix]: Change 640 to 512

* [Fix]: Fix README

* fix readme of MAE

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-04-28 00:54:20 +08:00
Miao Zheng
d90e700284 [Refactor] Add build_pos_embed and build_layers for BEiT ()
* [Refactor] Add build_pos_embed and build_layers for BEiT

* Update mmseg/models/backbones/beit.py
2022-04-27 11:37:03 +08:00
Miao Zheng
f64c7c331b [Refactor] Refactor transfomer encode layer in ViT and BEiT backbone ()
* [Refactor] Refactor transfomer encoder layer

* fix ffn cfg

* fix drop path cfg

* private init func

* fix qv bias

* fix qkv bias

* fix qkv bias

* wH->Wh
2022-04-23 17:35:05 +08:00
Mladen Fernežir
9e17a0d364 Fix validation loss logging () 2022-04-22 15:25:32 +08:00
Wang Xinjiang
b5d8c7dc6c Fix potential bugs in accuracy.py () 2022-04-21 10:18:37 +08:00
Rockey
23b7cfc59d [Fix] Support single cahnnel pred for Binary Cross Entropy Loss ()
* [Fix] Fix the bug that binary cross entropy loss doesn't support single channel input

* imcrease coverage

* modify implementation

* increase coverage

* add assert

* modify implementation

* enshollow condition judge

* fix
2022-04-14 11:26:02 +08:00
Miao Zheng
cc3a0528fe [Fix] Input previous results for the last cascade_decode_head ()
* [Fix] Input previous results for the latter cascade_decode_head

* minors
2022-04-13 21:16:29 +08:00
Miao Zheng
a09df2c39d [Fix] inconsistent dtype ofseg_label in stdc decode () 2022-04-10 14:18:16 +08:00
jiangyitong
7b6953fd5f [Feature] Add with cp to mit and vit ()
* add with cp to mit and vit

* add test unit

Co-authored-by: jiangyitong <jiangyitong1@sensetime.com>
2022-04-01 21:01:45 +08:00
MengzhangLI
cc89c8d18d [Fix] Add avg_non_ignore in cross entropy loss ()
* [Fix] Add avg_non_ignore in cross entropy loss

* [Fix] Add avg_non_ignore in cross entropy loss

* add docstring

* fix ut

* fix docstring and comments

* fix

* fix bce

* fix avg_factor in BCE and add more ut

* add avg_non_ignore

* add more ut

* fix part of ut

* fix part of ut

* test avg_non_ignore would not affect ce/bce when reduction none/sum

* test avg_non_ignore would not affect ce/bce when reduction none/sum/mean

* re-organize ut

* re-organize ut

* re-organize ut

* re-organize hardcode case

* fix parts of comments

* fix another parts of comments

* fix
2022-03-30 18:32:47 +08:00
FangjianLin
d1b8eae35e [Feature] Add BEiT backbone ()
* [Feature] Add BEiT backbone

* fix

* fix

* fix

* fix

* add readme

* fix

* fix

* fix

* fix

* fix

* add link

* fix memory

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix test_beit.py

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix
2022-03-30 15:25:10 +08:00
Xiangxu-0103
7a8227b747 fix typo () 2022-03-23 10:36:27 +08:00
Rockey
42df28c7bd [Feature] add nlc2nchw2nlc and nchw2nlc2nchw ()
* [Feature] add nlc2nchw2nlc and nchw2nlc2nchw

* add example

* add test, add **kwargs to make it more universal
2022-03-10 20:27:28 +08:00
MengzhangLI
054dc66145 [Feature] Support K-Net ()
* knet first commit

* fix import error in knet

* remove kernel update head from decoder head

* [Feature] Add kenerl updation for some decoder heads.

* [Feature] Add kenerl updation for some decoder heads.

* directly use forward_feature && modify other 3 decoder heads

* remover kernel_update attr

* delete unnecessary variables in forward function

* delete kernel update function

* delete kernel update function

* delete kernel_generate_head

* add unit test & comments in knet.py

* add copyright to fix lint error

* modify config names of knet

* rename swin-l 640

* upload models&logs and refactor knet_head.py

* modify docstrings and add some ut

* add url, modify docstring and add loss ut

* modify docstrings
2022-03-10 20:05:37 +08:00
Rockey
6665b42159 [Fix] Fix the bug that when all pixels in an image is ignored, the ac… ()
* [Fix] Fix the bug that when all pixels in an image is ignored, the accuracy calculation raises ZeroDivisionError

* use eps

* all close

* add ignore test

* add eps
2022-03-09 13:20:46 +08:00
sshuair
06b3533ee5 fix dnl_head export onnx inference difference type Cast error ()
* fix export onnx inference difference type Cast error

* fix export onnx inference difference type Cast error.

* use yapf format

* use same device type with pairwise_weight
2022-03-01 10:16:08 +08:00
MengzhangLI
2717ee62f9 [Feature] Support kenerl updation for some decoder heads. ()
* [Feature] Add kenerl updation for some decoder heads.

* [Feature] Add kenerl updation for some decoder heads.

* directly use forward_feature && modify other 3 decoder heads

* remover kernel_update attr

* delete unnecessary variables in forward function

* delete kernel update function

* delete kernel update function

* delete unnecessary docstrings

* modify comments in self._forward_feature()

* modify docstrings in self._forward_feature()

* fix docstring

* modify uperhead
2022-02-27 11:35:29 +08:00
Miao Zheng
b97cfa77d2 [Enhancement] Revise pre-commit-hooks () 2022-02-23 23:44:27 +08:00
Hyeokjoon Kwon
4d451a09dc [Fix] Make accuracy take into account ignore_index ()
* make accuracy take into account ignore_index

* add UT for accuracy
2022-02-15 00:39:59 +08:00
MengzhangLI
4de0c3708d [Fix] Fix type in Swin Transformer () 2022-02-09 19:08:32 +08:00
Jerry Jiarui XU
b405ce0506 [Improve] Add exception for PointRend for support CPU-only usage ()
* [Improve] Add exception for PointRend for support CPU-only usage

* fixed linting
2022-02-09 00:52:56 -05:00
Jerry Jiarui XU
548eec9580 [Improve] Use MMCV load_state_dict func in ViT/Swin ()
* [Improve] Use MMCV load_state_dict func in ViT/Swin

* use CheckpointLoader instead
2022-02-09 00:52:42 -05:00
MengzhangLI
46898b8e8a delete unnecessary lines of STDCHead () 2022-01-28 10:53:11 +08:00
rstrudel
ee47c41740 [Feature] Support Segmenter ()
* segmenter: add model

* update

* readme: update

* config: update

* segmenter: update readme

* segmenter: update

* segmenter: update

* segmenter: update

* configs: set checkpoint path to pretrain folder

* segmenter: modify vit-s/lin, remove data config

* rreadme: update

* configs: transfer from _base_ to segmenter

* configs: add 8x1 suffix

* configs: remove redundant lines

* configs: cleanup

* first attempt

* swipe CI error

* Update mmseg/models/decode_heads/__init__.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* segmenter_linear: use fcn backbone

* segmenter_mask: update

* models: add segmenter vit

* decoders: yapf+remove unused imports

* apply precommit

* segmenter/linear_head: fix

* segmenter/linear_header: fix

* segmenter: fix mask transformer

* fix error

* segmenter/mask_head: use trunc_normal init

* refactor segmenter head

* Fetch upstream ()

* [Feature] Change options to cfg-option ()

* [Feature] Change option to cfg-option

* add expire date and fix the docs

* modify docstring

* [Fix] Add <!-- [ABSTRACT] --> in metafile 

* [Fix] Fix correct num_classes of HRNet in LoveDA dataset 

* Bump to v0.20.1 ()

* bump version 0.20.1

* bump version 0.20.1

* [Fix] revise --option to --options 

Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>

* decode_head: switch from linear to fcn

* fix init list formatting

* configs: remove variants, keep only vit-s on ade

* align inference metric of vit-s-mask

* configs: add vit t/b/l

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* Update mmseg/models/decode_heads/segmenter_mask_head.py

Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>

* model_converters: use torch instead of einops

* setup: remove einops

* segmenter_mask: fix missing imports

* add necessary imported init funtion

* segmenter/seg-l: set resolution to 640

* segmenter/seg-l: fix test size

* fix vitjax2mmseg

* add README and unittest

* fix unittest

* add docstring

* refactor config and add pretrained link

* fix typo

* add paper name in readme

* change segmenter config names

* fix typo in readme

* fix typos in readme

* fix segmenter typo

* fix segmenter typo

* delete redundant comma in config files

* delete redundant comma in config files

* fix convert script

* update lateset master version

Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: Rockey <41846794+RockeyCoss@users.noreply.github.com>
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-01-26 13:50:51 +08:00
jbwang1997
44d4c3877e [Fix] Set random seed for generating palette if not given. ()
* Fix colors

* fix comments

* Add comments

* Add comments. Add random seed in datasets
2021-12-23 09:51:50 +08:00
MengzhangLI
c1e72513c9 [Feature] Support STDC Network (new) ()
* refactor stdc code

* update key

* fix backbone inference

* remove comments

* fixing errors

* fixing version conflict

* fux typo

* use STDCHead

* upload models&logs

* adding model converters script and fix unittest

* fix error

* fix error

* fix error

* delete redundant keys in config

* fix errors in configs and unittest

* fix errors in configs and unittest

* fix errors in configs and unittest

* change Memory name

* refactor stdc2mmseg

* change name to STDC

* refactor stdc

* refactor stdc

* stdc refactor

* stdc refactor

* stdc refactor

* stdc refactor

* stdc refactor

* stdc refactor

* refactor stdc

* stdc refactor

Co-authored-by: xiexinch <xinchen.xie@qq.com>
2021-12-10 23:09:32 +08:00
Lxinyang
cd246e3635 [Feature] Support Twins (NeurIPS2021) ()
* debug

* debug

* debug

* this is a debug step, and needs to be recovered

* need recover

* git

* debug

* git

* git

* git

* git

* git

* git

* debug need recover

* debug

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debugf

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* git

* git

* use config small/base/large

* debug

* debug

* git

* debug

* git

* debug

* debug

* debug args

* debug

* debug

* git

* git

* debug

* git

* git

* git

* git

* git

* debug

* debug

* git

* debug

* git

* debug

* debug

* debug

* debug

* git

* debug

* git

* git

* debug

* debug

* git

* git

* git

* git

* debug

* debug

* debug

* debug

* git

* debug

* debug

* git

* git

* debug

* debug

* git

* debug

* debug

* debug

* git

* debug

* debug

* debug

* Please enter the commit message for your changes. Lines starting

* git

* git

* debug

* debug

* debug

* git

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* fix pre-commit error

* fix error

* git

* git

* git

* git

* git

* git

* debug

* debug

* debug

* debug

* debug

* debug

* git

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* git

* git

* git

* debug

* debug

* debug

* git

* git

* git

* git

* git

* git

* git

* git

* git

* debug

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* fix unittest error

* fix config errors

* fix twins2mmseg bug

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* git

* fix init_weights() in twins.py

* git

* git

* git

* git

* fix comment

* fix comment

* fix comment

* fix comment

* fix unit test coverage in TwinsPR

* Add Twins README

* Add Twins README

* twins refactor

* twins refactor

* delete init_cfg in FFN

* delete init_cfg in FFN

* Update mmseg/models/backbones/twins.py

* Update mmseg/models/backbones/twins.py

* Update mmseg/models/backbones/twins.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* Update mmseg/models/backbones/twins.py

* add conference name

Co-authored-by: linxinyang <linxinyang@meituan.com>
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-12-09 19:18:10 +08:00
Rockey
a370777e3b [Fix] Fix the bug that mit cannot process init_cfg ()
* [Fix] Fix the bug that mit cannot process init_cfg

* fix error
2021-12-08 23:17:43 -08:00
Rockey
0ad0303ebc [Fix] Remove the inplace operation in uper_head and fpn_neck ()
* [Fix] Remove the inplace operation in  uper_head

* remove the inplace operation in fpn neck

* fix conflict

* increase the coverage
2021-12-09 12:12:31 +08:00
Han Zhang
e06cbcd8b1 [Fix] Fix dist training infinite waiting issue ()
* [] fix dist training infinite waiting issue

* print log_vars keys in assertion msg

* linting issue
2021-12-08 21:02:41 +08:00
KangBK0120
3d58196e62 [Fix] Remove unexist arg in docstring 2021-12-06 20:03:25 +08:00
Junjun2016
b8ca9b6d99 [Fix] Fix wrong init usage in transformer models ()
* fix wrong trunc_normal_init usage

* fix mit init weights

* fix vit init weights

* fix mit init weights

* fix typo

* fix swin init weights
2021-12-06 19:59:33 +08:00
Rockey
07cd6c98e0 [Feature] Add focal loss ()
* [Feature] add focal loss

* fix the bug of 'non' reduction type

* refine the implementation

* add class_weight and ignore_index; support different alpha values for different classes

* fixed some bugs

* fix bugs

* add comments

* modify test

* Update mmseg/models/losses/focal_loss.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* update test_focal_loss.py

* modified the implementation

* Update mmseg/models/losses/focal_loss.py

Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>

* update focal_loss.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-12-03 00:18:40 -08:00
MengzhangLI
6a2cfea73b [Feature] Support Real-time model ERFNet ()
* first commit

* Fixing Unittest Error

* first refactory of ERFNet

* Refactorying NonBottleneck1d Module

* uploading models&logs

* uploading models&logs

* fix partial bugs & typos

* ERFNet

* add ERFNet with FCNHead

* fix typos of ERFNet

* add name on README.md cover

* chane name to T-ITS'2017

* fix lint error
2021-12-01 23:54:39 -08:00
Junjun2016
d4ec8ef963 fix EfficientMultiheadAttention in SegFormer () 2021-11-15 04:33:28 +08:00
Rockey
bc27f24109 [Fix] Fix the bug that vit cannot load pretrain properly when using i… ()
* [Fix] Fix the bug that vit cannot load pretrain properly when using init_cfg to specify the pretrain scheme

* [Fix] fix the coverage problem

* Update mmseg/models/backbones/vit.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* [Fix] make the predicate more concise and clearer

* [Fix] Modified the judgement logic

* Update tests/test_models/test_backbones/test_vit.py

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>

* add comments

Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-11-03 10:36:09 -07:00
Junjun2016
0a06853bb6 [Feature] Support TIMMBackbone ()
* add TIMMBackbone and unittests

* add timm to tests requirements

* deprecate pt1.3.1

* reduce the unittests input of timm backbone

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* remove unittests of large models of timm backbone

* generate coverage report for all unittests env

* reduce the unittests input of timm backbone

* reduce the unittests input of timm backbone
2021-11-02 12:51:11 +08:00
MengzhangLI
992d577783 [Fix] Change self.loss_decode back to dict in Single Loss situation. ()
* fix single loss type

* fix error in ohem & point_head

* fix coverage miss

* fix uncoverage error of PointHead loss

* fix coverage miss

* fix uncoverage error of PointHead loss

* nn.modules.container.ModuleList to nn.ModuleList

* more simple format

* merge unittest def
2021-11-01 15:28:37 +08:00
Yuan Haobo
a33cbbf039 vit contiguous () 2021-10-25 18:11:48 +08:00
Junjun2016
67f1420472 [Enhancement] Add codespell pre-commit hook and fix typos ()
* add codespell pre-commit hook and fix typos

* Update mmseg/models/decode_heads/dpt_head.py

* Update mmseg/models/backbones/vit.py

* Update mmseg/models/backbones/vit.py

* fix typos

* skip formating typo

* deprecate formating

* skip ipynb

* unstage ipynb changes

* unstage ipynb changes

* fix typos in ipynb

* unstage ipynb changes
2021-10-13 06:21:17 -07:00