b9f9cf6558
refactor test organization ( #440 )
...
* refactor test organization
* fixed se layer
* update mmcv uper bound
2021-03-30 17:55:09 -07:00
455d163217
Save base_channels for UNet ( #450 )
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-03-30 09:52:08 -07:00
33e8357c62
Fix typo: upsampe_cfg -> upsample_cfg ( #449 )
...
* Fix typo: upsampe_cfg -> upsample_cfg
Signed-off-by: lizz <lizz@sensetime.com>
* convoluton -> convolution
Signed-off-by: lizz <lizz@sensetime.com>
* more
Signed-off-by: lizz <lizz@sensetime.com>
* ok
Signed-off-by: lizz <lizz@sensetime.com>
2021-03-30 09:51:38 -07:00
f7a5d53a4b
Include each class metrics in logs ( #445 )
...
* Include each class metrics in logs
* format
* fix the unitest
* fix the custom int class_name
* fix the custom int class_name
2021-03-29 09:53:54 -07:00
1fc3e374e2
[Bug fixed]Fix dice_loss errors ( #417 )
...
* fix training bugs
* fix unitest error
* fix error in num_classes==2 case
* delete comments
2021-03-29 09:49:54 -07:00
e86a87f060
pytorch metrics implementation ( #430 )
...
* pytorch metrics impl and test
* support list[str] input, delete unused test code and delete numpy version
* modify input data type
* add docstring and unitest of filename inputs
* add indents in docstring and use tempfile lib to create dir
* using with statement
2021-03-29 09:49:14 -07:00
6acd77e345
Add opacity option to show_result ( #425 )
2021-03-22 20:34:38 -07:00
0c31afe9eb
Support fcn dilate 6 ( #400 )
...
* Support fcn dilate 6
* Support dilate in FCNHead
* configs for cityscapse dataset
* add configs for pytorch pretrained model
* update README
* add fps test results
* add memory test results and links
* modify log names
* Update mmseg/models/decode_heads/fcn_head.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-03-20 10:32:04 -07:00
7e1b24dd32
dice loss ( #396 )
...
* dice loss
* format code, add docstring and calculate denominator without valid_mask
* minor change
* restore
2021-03-10 18:32:37 -08:00
d0a71c1509
Fix PhotoMetricDistortion docstring ( #388 )
2021-02-24 18:22:00 -08:00
0448dec5e4
Bump v0.11 ( #368 )
...
* bump to v0.11
* update readme
2021-02-02 15:09:20 -08:00
6879b0d43c
[Bug fix] Fixed ADE20k test ( #359 )
...
* [Bug fix] Fixed ADE20k test
* fixed ade cfg
2021-01-24 02:17:59 -08:00
faaf29e668
[Improvement] Move train_cfg/test_cfg inside model ( #341 )
...
* [Improvement] Move train_cfg/test_cfg inside model
* fixed config dict
* fixed config dict
2021-01-19 17:06:23 -08:00
0ee3016558
[New Feature]add lovasz loss ( #351 )
...
* add lovasz loss
* Modify as comments
* Modify paper url
* add unittest and remove Var
* impove unittest
2021-01-18 19:05:30 -08:00
ce46d70d20
memory efficient test ( #330 )
...
* memory efficient test
* implement efficient test
* merge
* Add document and docstring
* fix unit test
* add memory usage report
2021-01-09 23:47:31 -08:00
77e8ce3304
[Bug Fix] Fix TTA resize scale ( #334 )
...
* fix tta bug
* modify as suggested
* fix test_tta bug
2021-01-07 09:58:34 -08:00
9f071cade8
Bump to v0.10 ( #325 )
...
* Bump to v0.10
* change version
2021-01-02 15:29:56 -08:00
7fdb4002fa
[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 00:02:50 -08:00
94e12e8d21
Support DMNet ( #313 )
...
* Support DMNet
* fix doc and delete norm_name
2020-12-23 22:16:34 -08:00
e3f6f655d6
Support APCNet ( #299 )
...
* Support APCNet
* code optimization
* add apcnet configs
* add benchmark
* add readme and model zoo
* fix doc
2020-12-17 23:23:45 -08:00
061a2955dd
Support resize data augmentation according to original image size ( #291 )
...
* Support resize data augmentation according to original image size (img_scale=None and retio_range is tuple)
* fix docstring
* fix bug
* add unittest
* img_scale=None in TTA
* fix bug
* add unittest
* fix typos
* fix bug
2020-12-14 20:23:18 -08:00
7970e0ff11
Bugfix: num of augmentations and image meta not match when run TTA on CPU ( #276 )
...
* add inference test
* fix E501 line too long (81 > 79 characters
* fix wrong config path
* fix num of augmentations (2) != num of image meta (1)
* Update test_inference.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-12-13 23:51:42 -08:00
1fb54ac8c0
change 'reduct' to 'reduce' ( #298 )
2020-12-13 10:06:01 -08:00
90465128ce
Bump to 0.9.0 ( #285 )
...
* Bump to 0.9.0
* add version
2020-12-01 21:10:55 -08:00
0066ce884f
[Feature]add CLAHE transform ( #229 )
...
* add CLAHE transform
* fix syntax error
* fix syntax error
* restore
* add a test
* modify cv2 to mmcv
* add docstring
* modify
* restore
* fix mmcv.clahe error
* change mmcv version to 1.3.0
* fix bugs
* add all data transformers to __init__
* fix __init__
* fix test_transform
2020-12-01 21:08:16 -08:00
4dc809adf2
[Feature] add AdjustGamma transform ( #232 )
...
* add AdjustGamma transform
* restore
* change cv2 to mmcv
* simplify AdjustGamma
* fix syntax error
* modify
* fix syntax error
* change mmcv version to 1.3.0
* fix lut function name error
* fix syntax error
* fix range
2020-12-01 20:14:01 -08:00
993be2523b
add dice evaluation metric ( #225 )
...
* add dice evaluation metric
* add dice evaluation metric
* add dice evaluation metric
* support 2 metrics
* support 2 metrics
* support 2 metrics
* support 2 metrics
* fix docstring
* use np.round once for all
2020-11-23 19:21:22 -08:00
8d568fbc0d
[Bug Fix] Add missing transforms in __init__.py ( #260 )
2020-11-18 12:22:46 +08:00
61e1d5c814
[Enhancement] Support ignore_index for sigmoid BCE ( #210 )
...
* [Enhancement] Add args check for ignore_index
* Support ignore_index
2020-11-17 16:14:03 +08:00
300f42d006
fix _resize_seg bug in Resize data transforms ( #246 )
2020-11-16 17:28:41 +08:00
2bd51e60fd
[Feature] Add Rerange transform ( #228 )
...
* add rerange transform
* restore
* delete rerange config
* delete rerange config hint
* add min < max assert
* restore
2020-11-10 02:30:07 -08:00
7c68bca595
[Feature] Add Rgb2Gray transform ( #227 )
...
* add transformer Rgb2Gray
* restore
* fix self.weights
* restore
* fix code
* restore
* fix syntax error
* restore
2020-11-08 23:23:34 -08:00
3d18775113
[Feature] Add RandomRotate transform ( #215 )
...
* add RandomRotate for transforms
* change rotation function to mmcv.imrotate
* refactor
* add unittest
* fixed test
* fixed docstring
* fixed test
* add more test
* fixed repr
* rename to prob
* fixed unittest
Co-authored-by: hkzhang95 <GodBlessZhk@outlook.com>
2020-11-07 09:53:12 -08:00
0d1092105f
Bump to v0.8 ( #226 )
...
* Bump to v0.8
* add version
2020-11-04 16:18:02 -08:00
f5eb7f2627
[New model] Support CGNet ( #223 )
...
* added cgnet
* added testing for cgnet
* git test
* add cgnet
* fix __init__
* rename FGlo with GlobalContextExtractor
* add readme.md and rename bn with norm
* delete cg_head
* fix a language mistake
* rename cgnet_m3n21.py to cgnet.py
* modify README.md
* modify list to tuple
* add fcn_head test
* add assert to fcn_head
* blank
* fix fcn_head assert bug
* add
* add cgnet to README.md and model_zoo.md
* modify cgnet README.md
Co-authored-by: KID <wps_@mail.nankai.edu.cn>
2020-11-03 00:05:25 -08:00
8a174a3511
fix dataset jpg bug ( #213 )
...
* fix dataset jpg bug
* fix syntax error
2020-10-28 11:58:44 -07:00
e384ef578a
Add runner type ( #118 )
...
* Add runner_type option
* pre-commit
* Fix max_iters
* Add by_epoch to EvalHook
* Add test_eval_hook for epoch runner
* Remove runner-type arg from tools/train
* Add missing every_n_iters check for epoch mode
* Bump mmcv min version
* Use build_runner
* Use interval in tests
* Update test_eval_hook.py
* Use every_n_epochs instead of every_n_iters. Update DistEvalHook
* Add test_dist_eval_hook_epoch
* Fix tests
* Add DeprecationWarning
* Update docs
* Replace DeprecationWarning with UserWarning
2020-10-25 15:18:46 -07:00
3bdc276888
Define blood vessel dataset and fix filename bug ( #203 )
...
* fix filename bug
* define blood vessel dataset
* redo debug
* fix small bug
* rename dataset
Co-authored-by: yamengxi <yamengxi@sensetime.com>
2020-10-22 17:27:40 -07:00
651da35c0e
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>
2020-10-21 11:24:38 -07:00
5a76a715f1
add missing 0.7 ( #188 )
2020-10-11 18:08:40 +08:00
118fd9ddf0
Support custom palette ( #157 )
...
* Fix split
* Update tests/test_data/test_dataset.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-09-30 18:02:08 +08:00
f86c24d806
[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
f95079ba8a
[Enhance] Migrate to MMCV DepthwiseSeparableConv ( #158 )
...
* Add D16-MG124 models
* Use MMCV DepthSepConv
* add OHEM
* add warmup
* fixed test
* fixed test
* change to bs 16
* revert config
* add models
* seperate
2020-09-25 19:56:10 +08:00
7f8bc7935c
Fix cpu inference ( #152 )
...
* Add missing map_location
* Add docstring
* Update mmseg/apis/inference.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* Update inference.py
* Update inference.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-09-25 01:34:40 +08:00
746c8d3785
Use img_prefix and seg_prefix for loading ( #153 )
...
* Use img_prefix and seg_prefix for loading
* flake8
* Fix split
2020-09-25 00:48:16 +08:00
08f30ea497
add support for 4D output ( #150 )
2020-09-23 17:01:20 +08:00
a2738fd9be
Add Pascal Context to mmsegmentation ( #133 )
...
* Add Pascal Context to mmsegmentation
* Add benchmark result to Pascal Context
* fix mmcv version
* fix code syntax
* fix code syntax again
* Update mmseg/models/segmentors/encoder_decoder.py
update hint
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* update comment
* fix pascal context model path
* fix model path mistake again
* fix model path mistake again
* fix model path mistakes again
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-09-22 14:56:13 +08:00
768c3ee650
fix acc and iou compute nan problem ( #116 )
...
* fix acc and iou compute nan problem
* fix acc and iou compute nan problem
* add nan_to_num args for mean_iou
* add nan_to_num args for mean_iou
* add nan_to_num args for mean_iou
* add nan_to_num args for mean_iou
* add nan_to_num args for mean_iou
* Update mmseg/core/evaluation/mean_iou.py
* Update mean_iou.py
* Update mean_iou.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-09-22 01:04:46 +08:00
e3f6d575ef
[Enhance] Use MMCV collect_env ( #137 )
2020-09-19 21:32:41 +08:00
b8c2f913e4
Add support for custom classes ( #71 )
...
* Support for custom classes
* Fix test
* Fix pre-commit
* Add pipeline logic for custom classes
* Fix minor issues, fix test
* Fix issues from PR review
* Fix tests
* Remove palette as str
* Rename old_to_new_ids to label_map
* Test for load_anns
* Remove get_palette function
* fixed temp
* Add subset of palette, remove palette as arg
* minor update
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-09-16 21:33:01 +08:00
c3e4dbc2e0
Bump to version 0.6 ( #119 )
...
* Bump to version 0.6
* fixed format
2020-09-10 20:57:18 +08:00
ff98229a3d
[Feature] Support PointRend ( #109 )
...
* [Feature] Support PointRend
* add previous test
* update modelzoo
2020-09-07 19:59:44 +08:00
8ff866d60c
Add "disentangled non-local (DNL) neural networks" [ECCV2020] ( #37 )
...
* Add DNLHead
* add configs
* add weight decay mult
* add norm back
* Update README.md
* matched inference performance
* Fixed shape
* sep conv_out
* no norm
* add norm back
* complete model zoo
* add tests
* Add test forward
* Add more test
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-09-07 16:22:00 +08:00
dbca8b44a9
[Feature] Support EMANet ( #34 )
...
* add emanet
* fixed bug and typos
* add emanet config
* fixed padding
* fixed identity
* rename
* rename
* add concat_input
* fallback to update last
* Fixed concat
* update EMANet
* Add tests
* remove self-implement norm
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-09-07 13:06:59 +08:00
3c6dd9e6a4
[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
0c04f52c42
Onnx upsample ( #100 )
...
* add customized Upsample which can convert to ONNX
* support multiply decode head for hrnet
* support size for Upsample
2020-09-03 19:59:13 +08:00
b8f42c70fa
Add Semantic FPN ( #94 )
...
* Add Semantic FPN
* remove HRFPN
2020-09-03 19:56:36 +08:00
597b8a61c7
Windows Support (Experimental) ( #75 )
...
* Windows basic support
* getting_started updated for Windows.
* add experimental
* install.md restructured to seperate Windows & Linux.
* fix problems in install.md
* fix mmcv version problem.
* Fix fastscnn resize problems. (#82 )
* Fix fast_scnn resize problems
* Fix fast_scnn resize problems 1
* Fix fast_scnn resize problems 2
* test for pascal voc
* [Doc] Add annotaion format note (#77 )
* update pytorch version to 1.6.0 in install.md
* del fastscnn_pascal config
* del create_symlink=True
* Merge instructions for Linux & Windows
* mmcv version updated
* redundant newline deleted
* Update docs/install.md
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* Update docs/install.md
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2020-08-28 11:34:44 +08:00
298124566b
Update test.py ( #93 )
2020-08-25 21:12:39 +08:00
bafc0e5db6
Fixed slide inference ( #90 )
2020-08-25 20:01:01 +08:00
e951076bf2
Fix fastscnn resize problems. ( #82 )
...
* Fix fast_scnn resize problems
* Fix fast_scnn resize problems 1
* Fix fast_scnn resize problems 2
* test for pascal voc
2020-08-23 14:41:30 +08:00
c1f46a69f4
Fast-SCNN implemented ( #58 )
...
* init commit: fast_scnn
* 247917iters
* 4x8_80k
* configs placed in configs_unify. 4x8_80k exp.running.
* mmseg/utils/collect_env.py modified to support Windows
* study on lr
* bug in configs_unify/***/cityscapes.py fixed.
* lr0.08_100k
* lr_power changed to 1.2
* log_config by_epoch set to False.
* lr1.2
* doc strings added
* add fast_scnn backbone test
* 80k 0.08,0.12
* add 450k
* fast_scnn test: fix BN bug.
* Add different config files into configs/
* .gitignore recovered.
* configs_unify del
* .gitignore recovered.
* delete sub-optimal config files of fast-scnn
* Code style improved.
* add docstrings to component modules of fast-scnn
* relevant files modified according to Jerry's instructions
* relevant files modified according to Jerry's instructions
* lint problems fixed.
* fast_scnn config extremely simplified.
* InvertedResidual
* fixed padding problems
* add unit test for inverted_residual
* add unit test for inverted_residual: debug 0
* add unit test for inverted_residual: debug 1
* add unit test for inverted_residual: debug 2
* add unit test for inverted_residual: debug 3
* add unit test for sep_fcn_head: debug 0
* add unit test for sep_fcn_head: debug 1
* add unit test for sep_fcn_head: debug 2
* add unit test for sep_fcn_head: debug 3
* add unit test for sep_fcn_head: debug 4
* add unit test for sep_fcn_head: debug 5
* FastSCNN type(dwchannels) changed to tuple.
* t changed to expand_ratio.
* Spaces fixed.
* Update mmseg/models/backbones/fast_scnn.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* Update mmseg/models/decode_heads/sep_fcn_head.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* Update mmseg/models/decode_heads/sep_fcn_head.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* Docstrings fixed.
* Docstrings fixed.
* Inverted Residual kept coherent with mmcl.
* Inverted Residual kept coherent with mmcl. Debug 0
* _make_layer parameters renamed.
* final commit
* Arg scale_factor deleted.
* Expand_ratio docstrings updated.
* final commit
* Readme for Fast-SCNN added.
* model-zoo.md modified.
* fast_scnn README updated.
* Move InvertedResidual module into mmseg/utils.
* test_inverted_residual module corrected.
* test_inverted_residual.py moved.
* encoder_decoder modified to avoid bugs when running PSPNet.
getting_started.md bug fixed.
* Revert "encoder_decoder modified to avoid bugs when running PSPNet. "
This reverts commit dd0aadfb
2020-08-18 23:33:05 +08:00
d9484068ce
Support ResNeSt backbone ( #47 )
...
* Support ResNeSt backbone
* fixed avg_down
* add docstring and test
* update table
* update docs and tests
* fixed test
* rename
* refactor splits
2020-08-17 00:54:01 +08:00
9ba22456d9
add pytorch2onnx part ( #12 )
...
* add pytorch2onnx part
* Update according to the latest mmcv
* add docstring
* update docs
* update docs
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-08-14 03:28:21 +08:00
4e29452dbe
Auto get version info and git hash ( #55 )
...
* Auto get version info and git hash
* bump 0.5.1 and update doc
* fixed docs
* Add change log
2020-08-11 19:23:35 +08:00
5e264c608c
Generalized OHEM ( #54 )
...
* Generalized OHEM
* remove config
* update docstring
* fixed sort prob
* fixed valid_mask
2020-08-09 23:49:23 +08:00
579f5f883e
Fix palette type. ( #27 )
2020-07-23 13:01:31 +08:00
1765c12985
Support FP16 ( #21 )
...
* Support FP16
* add miss folder
* add tests
* remove useless config
* update memory
* reduce config
* migrate fp16 to mmcv
* add model link
2020-07-20 15:17:18 +08:00
550e02b7cb
Add pypi deployment ( #11 )
...
* add pypi deployment
* remove useless jobs
* fixed typo and cleanup
* delete build.tx
* add change log
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-07-13 20:54:32 +08:00
b975d3b72a
Add test tutorial ( #9 )
...
* add test tutorial
* remote torch/torchvision from requirements
* update getting started
* rename drop_out_ratio -> dropout_ratio
2020-07-12 23:53:56 +08:00
b72a6d00ef
Add Colab Tutorial ( #7 )
...
* add badge
* Created using Colaboratory
* add read docs
* Fixed readthedocs
* fixed colab ref
* add readthedocs.txt
* add link
* fixed modelzoo link
* add missing reference
* fixed docs
* remove relative path in docs
* add colab in README.md
* update docker image
* add newline
* fixed br
2020-07-10 16:55:47 +08:00
b2724da80b
init commit
2020-07-10 02:39:01 +08:00
Jerry Jiarui XU
lizz
sshuair
谢昕辰
David de la Iglesia Castro
yamengxi
Junjun2016
Youqing Xiaozhua
yinchimaoliang
robin Han
Iago González
Han Hu
Xia Li 李夏
John Zhu
MY_
ycr
Kai Chen