91440718de
add comment
2022-11-22 22:38:10 +08:00
589d8ac224
[Fix] Fix KNet IterativeDecodeHead bug in v0.x branch
2022-11-22 12:40:19 +08:00
62bcc1ae6c
Merge branch 'open-mmlab:master' into custom/face_occlusion
2022-11-08 19:13:41 +09:00
7b09967fcc
Merge pull request #2257 from xiexinch/bumpv0.29.1
...
bumpv0.29.1
2022-11-03 16:19:52 +08:00
47c7ed5dec
bumpv0.29.1
2022-11-03 14:37:38 +08:00
280b1755c4
Merge branch 'open-mmlab:master' into custom/face_occlusion
2022-11-01 22:28:22 +09:00
b42c487767
[Doc] Update FAQ doc about binary segmentation and ReduceZeroLabel ( #2206 )
...
* [Doc] Update FAQ doc about binary segmentation and ReduceZeroLabel
* update
* modify
* fix typo and add modification
* fix typo
* fix comments
* fix order
* fix
* fix
* Update docs/en/faq.md
* Update docs/zh_cn/faq.md
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-10-28 21:44:37 +08:00
c222684c29
Merge branch 'open-mmlab:master' into custom/face_occlusion
2022-10-26 22:48:58 +09:00
8dbbdd8c17
[Feature] Add model ensemble tools ( #2218 )
...
* [Feature] Add model ensemble tool
* [Enhance] Add en and zh_cn instructions for model_ensemble
* [Enhance] Add default-value for --out and modify instruction
* [Enhance] Add arg-type for --out
* [Enhance] Delete redundant code
2022-10-24 19:03:48 +08:00
1fc898c7df
formatting
2022-10-18 08:49:07 +09:00
1ca1780f5a
fix format
2022-10-17 01:47:59 +00:00
d5e79fa0ef
Merge branch 'open-mmlab:master' into custom/face_occlusion
2022-10-11 14:58:01 +09:00
356215bf58
Bump v0.29.0 ( #2167 )
...
* bump v0.29.0
* remove 2159
2022-10-10 14:06:25 +08:00
abb0932966
Fix lint ( #2159 )
2022-10-08 17:36:56 +08:00
2eb13c6906
Improve structure and readability for FCNHead ( #2142 )
2022-10-08 16:31:17 +08:00
0391dcd105
Upgrade pre commit hooks master ( #2155 )
...
* Upgrade pre commit hooks
* Upgrade pre commit hooks
* mim install mmcv-full
* install mim
* install mmcv-full
* test mmcv-full 1.6.0
* fix timm
* fix timm
* fix timm
2022-10-08 16:29:12 +08:00
9d2312b4ac
added if statement to account for IterableDatasets doing distributed training ( #2151 )
2022-10-08 12:14:01 +08:00
e9e196f3c9
add custom dataset
2022-09-20 08:47:02 +00:00
ee25adc2c1
fix ( #2075 )
2022-09-15 15:16:46 +08:00
ecd1ecb6ba
[Fix] Fix mmseg.api.inference inference_segmentor ( #1849 )
...
* [Fix] Fix mmseg.api.inference inference_segmentor
Motivation
Fix inference_segmentor not working with multiple images path or images. List[str/ndarray]
Modification
- process images if instance is list
* fix typo
* Update mmseg/apis/inference.py
Co-authored-by: Hakjin Lee <nijkah@gmail.com>
Co-authored-by: Hakjin Lee <nijkah@gmail.com>
2022-09-14 00:13:43 +08:00
b51670b613
Bump v0.28.0 ( #2047 )
...
* bump v0.28.0
* update
2022-09-08 16:54:12 +08:00
c1c942e8fc
[Fix] Fix binary segmentation when `num_classes==1` ( #2016 )
...
* fix binary
* add ut
* fix ut
* restore metric computation
* remove metric ut update
* set out_channels by num_classes
* replace num_classes in encoder_decoder
* update props setting and fix ut
* update ut
* minor change
* update warning
2022-09-08 14:43:21 +08:00
74e13cfa61
[Fix] Fix decode head forward_train error. ( #1997 )
2022-08-30 20:43:10 +08:00
acff83909f
[Feature] Support Tversky Loss ( #1986 )
2022-08-30 20:17:50 +08:00
eeeaff9421
Bump v0.27.0 ( #1836 )
...
* Bump v0.26.1
* update version
* fix mmcv requirement
2022-07-28 21:04:01 +08:00
0e37281884
[Enhancement] Modify MMCV version requirement ( #1764 )
...
* modify mmcv version requirement
* minor change
* change max mmcv version
2022-07-13 19:40:32 +08:00
e3b5b5ee38
remove show=False parameter in test_fn ( #1741 )
2022-07-07 09:21:27 +08:00
17056b636f
Bump v0.26.0 ( #1731 )
2022-07-01 20:31:52 +08:00
dca46fec9a
[Feature] Dedicated MMSegWandbHook for MMSegmentation (Weights and Biases Integration) ( #1603 )
...
* wandb integration
* wandb integration
* Update mmseg/core/hook/wandblogger_hook.py
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
* trying to fix circular import issue
* Update mmseg/core/hook/wandblogger_hook.py docstring
Try to activate the CI.
* move import op in func
* add comments to test_fn
Co-authored-by: xiexinch <test767803@foxmail.com>
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
2022-07-01 18:29:13 +08:00
fe455c2771
[Fix] Fix typo in comments in mFscore ( #1708 )
2022-06-27 13:04:41 +08:00
e8dfa3f26b
fix OpenCV num_threads log ( #1704 )
2022-06-24 11:58:27 +08:00
a8a8fec178
[Fix] Fix liscense of SegFormer ( #1699 )
...
* [Fix] Fix liscense of SegFormer
* add liscense
* add liscense
2022-06-23 18:57:12 +08:00
6f43f4d5d3
[Enchance] support infererence with padding ( #1607 )
...
* [Enchance] support infererence with padding
* limite pad after flip when inference
* add test code
2022-06-15 11:28:09 +08:00
f3c72c6dbb
Fixed a few spelling errors ( #1656 )
...
* 修复拼写错误
* Fix lint error
* Fix lint error
* Fix lint error
2022-06-14 12:10:59 +08:00
df434bed69
fix typo ( #1667 )
2022-06-14 11:20:31 +08:00
43b4efb122
[Fix] Fix image_demo.py error ( #1640 )
...
* [Fix] Fix image_demo.py error
* [Fix] Fix image_demo.py error
* fix
* delete plt.cla()
2022-06-09 17:20:28 +08:00
60655de194
change for easy deployment of segmenter ( #1642 )
2022-06-07 18:00:13 +08:00
46326f63ce
Bump v0.25.0 ( #1636 )
...
* Bump v0.25.0
* format
* fix mmcv version
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-06-02 22:40:08 +08:00
63fa98515b
[Fix] Fix the error of BCE loss when batch size is 1. ( #1629 )
2022-05-31 18:07:29 +08:00
7628a61f92
feat(mlu): Support PyTorch backend on MLU. ( #1515 )
...
* feat(mlu): Support PyTorch backend on MLU.
* fix redundant device variable.
* Update mmseg/apis/train.py
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
* Update comments.
* Update mmseg/apis/train.py
* Update is_mlu_available flag.
* align util_distribution.py to mmdet.
* align util_distribution.py to mmdet.
* add build_dp, build_ddp testcase.
* Update mmseg/utils/util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmseg/utils/util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmseg/utils/util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update tests/test_utils/test_util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update tests/test_utils/test_util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update tests/test_utils/test_util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update tests/test_utils/test_util_distribution.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* add mmcv version check for mlu device.
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-05-25 18:11:42 +08:00
4f394b0674
[Fix] bug of resize warning when align_corners is True ( #1592 )
...
Signed-off-by: FreyWang <wangwxyz@qq.com>
2022-05-18 16:39:52 +08:00
ae0fac4a36
Bump version to v0.24.1 ( #1541 )
...
* Bump version to v0.24.1
* version.py
* changelog.md
2022-05-01 14:06:04 +08:00
9dae7e1d49
[Enhancement]Revise docstring and UT for layer decay LR ( #1540 )
...
* fix docstring
* fix ut for optimizer cosntructor
2022-05-01 13:13:53 +08:00
8be5987fdd
[Fix] Add MAE LayerDecayOptimizerConstructor ( #1539 )
2022-05-01 12:42:49 +08:00
c4c0c1f804
Bump version to v0.24.0 ( #1533 )
...
* [WIP] Bump version to v0.24.0
* changelog
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* Update docs/en/changelog.md
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* words
* typo
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-04-29 22:23:02 +08:00
061b5b4383
[Fix] Fix the bug in binary_cross_entropy ( #1527 )
...
* [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
6563cb513e
[Feature]: Add MAE ( #1307 )
...
* [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
69b28e0b59
[Refactor] Add build_pos_embed and build_layers for BEiT ( #1517 )
...
* [Refactor] Add build_pos_embed and build_layers for BEiT
* Update mmseg/models/backbones/beit.py
2022-04-27 11:37:03 +08:00
f16bb06092
[Refactory] Merge BEiT and ConvNext 's LR decay optimizer constructors ( #1438 )
...
* move layer_decay_optimizer_constructor
* fix
* fix
* merge test_core
* fix
* add DeprecationWarning
* fix DeprecationWarning
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix test
* fix
* fix
* fix
* fix
* fix ut
* fix
* fix
* Update tests/test_core/test_layer_decay_optimizer_constructor.py
* fix
* fix
* fix
* fix
Co-authored-by: MeowZheng <meowzheng@outlook.com>
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-04-27 10:43:25 +08:00
239049cf91
[Refactor] Refactor transfomer encode layer in ViT and BEiT backbone ( #1481 )
...
* [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
MengzhangLI
whooray
Miao Zheng
xiexinch
zhijiejia
jinwonkim93
jinwonkim93
Edward
Shirley Wang
Sungchul Kim
Wencheng Wu
Ayush Thakur
Qing
FreyWang
rotorliu
Xiaolin Wang
RunningLeon
Aston.He
FangjianLin
wangbin
Yuan Liu