d3603e5335
Fix mIoU calculatiton range ( #471 )
...
* Fix fence(IoU) = 0 when training on PascalContextDataset59;
* Add a test case in test_metrics() of tests/test_metrics.py to test the bug caused by torch.histc;
* Update tests/test_metrics.py
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-04-14 08:37:23 -07:00
bc2dc1277a
add dynamic export and visualize to pytorch2onnx ( #463 )
...
* add dynamic export and visualize to pytorch2onnx
* update document
* fix lint
* fix dynamic error and add visualization
* fix lint
* update docstring
* update doc
* Update help info for --show
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
* fix lint
Co-authored-by: maningsheng <maningsheng@sensetime.com>
Co-authored-by: Jerry Jiarui XU <xvjiarui0826@gmail.com>
2021-04-12 11:54:59 -07:00
d283ca6fea
[Improvement] Add more CI ( #460 )
...
* add more CI
* fix missing
* remove python-version
* fixed acc
2021-04-08 19:29:00 -07:00
ac2aab74e9
Bump to v0.12 ( #455 )
2021-04-03 21:02:56 -07:00
3150dd0ce4
refactor test organization ( #440 )
...
* refactor test organization
* fixed se layer
* update mmcv uper bound
2021-03-30 17:55:09 -07:00
fcad6df7a6
Save base_channels for UNet ( #450 )
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-03-30 09:52:08 -07:00
bbb9f074f6
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
7c329fa775
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
71be1c2793
[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
d474cfde4b
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
9cbb4b1288
Add opacity option to show_result ( #425 )
2021-03-22 20:34:38 -07:00
bac0714347
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
a3b523e3fd
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
96ddb41c6e
Fix PhotoMetricDistortion docstring ( #388 )
2021-02-24 18:22:00 -08:00
45f07af4c8
Bump v0.11 ( #368 )
...
* bump to v0.11
* update readme
2021-02-02 15:09:20 -08:00
f3cf96b63e
[Bug fix] Fixed ADE20k test ( #359 )
...
* [Bug fix] Fixed ADE20k test
* fixed ade cfg
2021-01-24 02:17:59 -08:00
4423d32702
[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
c8bbd3fa95
[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
7e156454a2
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
022b055a66
[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
5eafe8f6df
Bump to v0.10 ( #325 )
...
* Bump to v0.10
* change version
2021-01-02 15:29:56 -08:00
25d8d77fab
[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
b9ba9f6ce7
Support DMNet ( #313 )
...
* Support DMNet
* fix doc and delete norm_name
2020-12-23 22:16:34 -08:00
a5d15ae228
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
55df29beab
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
d5712c4d38
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
b77623e783
change 'reduct' to 'reduce' ( #298 )
2020-12-13 10:06:01 -08:00
7678ecc333
Bump to 0.9.0 ( #285 )
...
* Bump to 0.9.0
* add version
2020-12-01 21:10:55 -08:00
26f4bed242
[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
e8d643fe3a
[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
1530af6533
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
97f10dbb04
[Bug Fix] Add missing transforms in __init__.py ( #260 )
2020-11-18 12:22:46 +08:00
ffcdfd36d0
[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
378ea27e4f
fix _resize_seg bug in Resize data transforms ( #246 )
2020-11-16 17:28:41 +08:00
365ce9e2af
[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
0588426eaa
[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
500babf958
[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
be94bbf1cc
Bump to v0.8 ( #226 )
...
* Bump to v0.8
* add version
2020-11-04 16:18:02 -08:00
86d473002f
[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
294a1f377a
fix dataset jpg bug ( #213 )
...
* fix dataset jpg bug
* fix syntax error
2020-10-28 11:58:44 -07:00
969c7fd8e4
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
464ffb77ad
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
5956451014
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
a2e9d97096
add missing 0.7 ( #188 )
2020-10-11 18:08:40 +08:00
e7240c8cf1
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
2610a11981
[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
f3f443ff71
[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
e385842557
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
51e4cdefc5
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
588a2c036a
add support for 4D output ( #150 )
2020-09-23 17:01:20 +08:00
sennnnn
q.yao
Jerry Jiarui XU
lizz
sshuair
谢昕辰
David de la Iglesia Castro
yamengxi
Junjun2016
Youqing Xiaozhua
yinchimaoliang
robin Han