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
7553fbe948
Fix validation loss logging ( #1494 )
2022-04-22 15:25:32 +08:00
cb06ff1911
Fix potential bugs in accuracy.py ( #1496 )
2022-04-21 10:18:37 +08:00
618d3c3bcc
[Enhancement] MMCV maximum_version set to 1.6 ( #1480 )
...
* [Enhancement] MMCV maximum_version set to 1.6
* [Enhancement] MMCV maximum_version set to 1.6
2022-04-19 16:19:56 +08:00
5b605b086d
[Fix] Register optimizer constructor with mmseg ( #1456 )
...
* [fix] register optimizer onstructor with mmseg
* fix lint
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* Update tests/test_core/test_optimizer.py
* Update tests/test_core/test_optimizer.py
* Update tests/test_core/test_optimizer.py
* Update tests/test_core/test_optimizer.py
* fix lint
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
2022-04-16 16:45:17 +08:00
cd18b6d479
[Fix] Support single cahnnel `pred` for Binary Cross Entropy Loss ( #1454 )
...
* [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
23ae1ebab6
[Fix] Input previous results for the last cascade_decode_head ( #1450 )
...
* [Fix] Input previous results for the latter cascade_decode_head
* minors
2022-04-13 21:16:29 +08:00
3f797072d8
[Enhance] Add extra dataloader settings in configs ( #1435 )
...
* [Enhance] Add extra dataloader settings in configs
* val default samples
* val default samples
* del unuse
* del unused
2022-04-13 13:30:10 +08:00
91b1bcb9d8
Avoid converting label ids twice by label map during evaluation ( #1417 )
...
* Avoid converting label ids twice by label map during evaluation
* Update mmseg/datasets/custom.py
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
* lint
Co-authored-by: Miao Zheng <76149310+MeowZheng@users.noreply.github.com>
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-04-12 18:26:25 +08:00
4841933454
[Fix] inconsistent dtype ofseg_label in stdc decode ( #1463 )
2022-04-10 14:18:16 +08:00
28488851fd
fix bug about label_map ( #1445 )
...
* fix bug about label_map
* Update mmseg/datasets/pipelines/loading.py
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
* lint
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-04-09 21:11:47 +08:00
3432ea98db
Add DistSamplerSeedHook for when runner is EpochBasedRunner ( #1449 )
...
* Add DistSamplerSeedHook for when runner is EpochBasedRunner
* add comment
2022-04-06 22:04:11 +08:00
be8f073c84
[Feature] Add with cp to mit and vit ( #1431 )
...
* 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
6670672345
Bump version to v0.23.0 ( #1439 )
...
* Bump version to v0.23.0
* new contributor
* rephrase
* tyoi
* typo
* get_started
* typo
* rephrase
* rephrase
* rephrase
2022-04-01 15:43:19 +08:00
a82ebad0f6
[Fix] Add avg_non_ignore in cross entropy loss ( #1409 )
...
* [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
24f1563571
[Feature] Add BEiT backbone ( #1404 )
...
* [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
30864ea23d
[Feature] Support dataset initialization with file_client ( #1402 )
...
* [Feature] Support file_client in dataset initialization
* docstring
* revise osp.exist
2022-03-28 23:53:23 +08:00
f3ae2342eb
[Enchance] Support random seed for distributed sampler ( #1411 )
...
* support random seed for distributed sampler
* move mmseg/utils/dist_util.py to mmseg/core/utils/dist_util.py
* move mmseg/utils/dist_util.py to mmseg/core/utils/dist_util.py
* change dist sampler
* change dist sampler
* fix docstring in sync_random_seed
2022-03-28 23:50:39 +08:00
98984bf855
fix typo ( #1405 )
2022-03-23 10:36:27 +08:00
1b24ad656f
[Feature] Add multi machine `dist_train`. ( #1383 )
...
* Add training startup documentation
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
2022-03-18 10:55:49 +08:00
3d0c2eb385
Support #1375 : add demo/image_demo.py support for STARE ( #1376 )
...
* Support #1375 : add demo/image_demo.py support for STARE
* Update mmseg/core/evaluation/class_names.py
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-03-15 22:42:20 +08:00
17b500f9df
[Feature] add nlc2nchw2nlc and nchw2nlc2nchw ( #1249 )
...
* [Feature] add nlc2nchw2nlc and nchw2nlc2nchw
* add example
* add test, add **kwargs to make it more universal
2022-03-10 20:27:28 +08:00
2e28db0dcb
[Feature] Support K-Net ( #1289 )
...
* 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
7dba7a2620
[Feature]: Add diff seeds to diff ranks and set torch seed in worker_init_fn ( #1362 )
2022-03-10 09:41:16 +08:00
e518d25e73
Bump v0.22.1 ( #1361 )
2022-03-09 20:05:44 +08:00
66b379015f
[Fix] Fix the bug that when all pixels in an image is ignored, the ac… ( #1336 )
...
* [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
a7c2f680e8
Bump v0.22.0 ( #1347 )
...
* change version to v0.22.0
* change version to v0.22.0
* add mmcls version in get_started.md
* add mmcls installation and move PR1299 into enhancement
* add mmcls installation and move PR1299 into enhancement
* remove MMCLS and make mmcv <=1.5.0 version in get_started.md
* fix typo
2022-03-04 22:17:29 +08:00
7ddd2fe2ec
[Feature] Support ConvNext ( #1216 )
...
* upload original backbone and configs
* ConvNext Refactor
* ConvNext Refactor
* convnext customization refactor with mmseg style
* convnext customization refactor with mmseg style
* add ade20k_640x640.py
* upload files for training
* delete dist_optimizer_hook and remove layer_decay_optimizer_constructor
* check max(out_indices) < num_stages
* add unittest
* fix lint error
* use MMClassification backbone
* fix bugs in base_1k
* add mmcls in requirements/mminstall.txt
* add mmcls in requirements/mminstall.txt
* fix drop_path_rate and layer_scale_init_value
* use logger.info instead of print
* add mmcls in runtime.txt
* fix f string && delete
* add doctring in LearningRateDecayOptimizerConstructor and fix mmcls version in requirements
* fix typo in LearningRateDecayOptimizerConstructor
* use ConvNext models in unit test for LearningRateDecayOptimizerConstructor
* add unit test
* fix typo
* fix typo
* add layer_wise and fix redundant backbone.downsample_norm in it
* fix unit test
* give a ground truth lr_scale and weight_decay
* upload models and readme
* delete 'backbone.stem_norm' and 'backbone.downsample_norm' in get_num_layer()
* fix unit test and use mmcls url
* update md2yml.py and metafile
* fix typo
2022-03-04 15:52:01 +08:00
2d66179630
[Feature] Add `min_size` arg in `Resize` to keep the shape after resize bigger than slide window ( #1318 )
...
* [Feature] add setr_resize
* fix a bug
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
* fix
2022-03-01 16:25:48 +08:00
9947a3974c
fix dnl_head export onnx inference difference type Cast error ( #1161 )
...
* 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
4912ea2b0a
[Feature] Support kenerl updation for some decoder heads. ( #1299 )
...
* [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
e5cd755481
[Enhancement] Revise pre-commit-hooks ( #1315 )
2022-02-23 23:44:27 +08:00
4f4e7728b0
[Feature] Support iSAID aerial dataset. ( #1115 )
...
* support iSAID aerial dataset
* Update and rename docs/dataset_prepare.md to 博士/dataset_prepare.md
* Update dataset_prepare.md
* fix typo
* fix typo
* fix typo
* remove imgviz
* fix wrong order in annotation name
* upload models&logs
* upload models&logs
* add load_annotations
* fix unittest coverage
* fix unittest coverage
* fix correct crop size in config
* fix iSAID unit test
* fix iSAID unit test
* fix typos
* fix wrong crop size in readme
* use smaller figure as test data
* add smaller dataset in test data
* add blank in docs
* use 0 bytes pseudo data
* add footnote and comments for crop size
* change iSAID to isaid and add default value in it
* change iSAID to isaid in _base_
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-02-17 19:07:32 +08:00
2056caa790
[Fix] Fix wrong palette value in vaihingen ( #1292 )
2022-02-16 22:41:39 +08:00
346f70da5f
[Fix] Make accuracy take into account ignore_index ( #1259 )
...
* make accuracy take into account ignore_index
* add UT for accuracy
2022-02-15 00:39:59 +08:00
b16310182b
[Fix] Fix type in Swin Transformer ( #1274 )
2022-02-09 19:08:32 +08:00
a39f5856ce
Bump v0.21.1 ( #1273 )
...
* Bump v0.21.1
* add improvements in changelog
* add improvements in changelog
* fix cn readme
* change changelog
2022-02-09 17:17:55 +08:00
82a80880d2
[Improve] Add exception for PointRend for support CPU-only usage ( #1271 )
...
* [Improve] Add exception for PointRend for support CPU-only usage
* fixed linting
2022-02-09 00:52:56 -05:00
66b778c064
[Improve] Use MMCV load_state_dict func in ViT/Swin ( #1272 )
...
* [Improve] Use MMCV load_state_dict func in ViT/Swin
* use CheckpointLoader instead
2022-02-09 00:52:42 -05:00
b4314f98c1
[Enhancement] Upgrade isort in pre-commit hook ( #1270 )
2022-02-08 19:06:33 +08:00
29cfcd145c
Bump v0.21.0 ( #1258 )
...
* change version to v0.21.0
* change version to v0.21.0
* change version to v0.21.0
* change version to v0.21.0
2022-01-29 18:30:13 +08:00
ecda117ea5
[Enhance] New-style CPU training and inference. ( #1251 )
...
* [Enhance] New-style CPU training and inference.
* assert mmcv version
* SyncBN to BN in training and testing
* SyncBN to BN in training and testing
* upload untracked files to this branch
* delete gpu_ids
* fix bugs
* assert args.gpu_id in train.py
* use cfg.gpu_ids = [args.gpu_id]
* use cfg.gpu_ids = [args.gpu_id]
* fix typo
* fix typo
* fix typos
2022-01-28 23:03:01 +08:00
02d2790145
delete unnecessary lines of STDCHead ( #1231 )
2022-01-28 10:53:11 +08:00
8ea3d64c65
add multi-processes script ( #1238 )
2022-01-27 21:18:55 +08:00
cb1bf9f372
[Feature] Support Segmenter ( #955 )
...
* 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 (#1 )
* [Feature] Change options to cfg-option (#1129 )
* [Feature] Change option to cfg-option
* add expire date and fix the docs
* modify docstring
* [Fix] Add <!-- [ABSTRACT] --> in metafile #1127
* [Fix] Fix correct num_classes of HRNet in LoveDA dataset #1136
* Bump to v0.20.1 (#1138 )
* bump version 0.20.1
* bump version 0.20.1
* [Fix] revise --option to --options #1140
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
4b905cbe2f
[Feature] Support ISPRS Vaihingen Dataset. ( #1171 )
...
* Add Vaihingen
* upload models&logs of vaihingen
* fix unit test
* fix dataset pipeline
* fix unit test coverage
* fix vaihingen docstring
2022-01-22 20:27:51 +08:00
5b310a0074
[Fix] Add `COCOStuffDataset` in `class_names.py`. ( #1222 )
...
* add cocostuff in class_names
* add more class names
2022-01-22 18:03:24 +08:00
Yuan Liu
Miao Zheng
FangjianLin
Mladen Fernežir
Wang Xinjiang
Rockey
panfeng-hover
Yzichen
jiangyitong
MengzhangLI
Xiangxu-0103
CCODING
sshuair
Waterman0524
Hyeokjoon Kwon
Jerry Jiarui XU
rstrudel