8dae9465a6
[Feature] Add `gt_edge_map` field. ( #2466 )
...
## Motivation
The motivation of this PR is to add `gt_edge_map` field to support
boundary loss.
## Modification
- GenerateEdge
Modify `gt_edge` field to `gt_edge_map`.
- PackSegInputs
Add `gt_edge_map` to data_sample.
- stack_batch
Pad `gt_edge_map` to max_shape.
## BC-breaking (Optional)
No
## Use cases (Optional)
Reference `GenerateEdge`.
2023-01-11 11:51:29 +08:00
f90f7a56d4
[Fix] Fix incorrect `img_shape` value assignment in RandomCrop ( #2469 )
...
## Motivation
Fix incorrect `img_shape` value assignment.
## Modification
- mmseg/datasets/transforms/transforms.py
2023-01-10 18:03:43 +08:00
2d67e51db3
CodeCamp #140 [New] [Feature] Add synapse dataset and data augmentation in dev-1.x. ( #2432 )
...
## Motivation
Add Synapse dataset in MMSegmentation.
Old PR: https://github.com/open-mmlab/mmsegmentation/pull/2372 .
2023-01-06 16:14:54 +08:00
6af2b8eab9
[Feature] Add BioMedical3DPad ( #2383 )
...
## Motivation
Add the 3d pad transform for biomedical images, which follows the design
of the nnUNet.
2023-01-03 13:37:48 +08:00
3ca690bad3
[Feature] Add BioMedicalRandomGamma ( #2406 )
...
Add the random gamma correction transform for biomedical images, which
follows the design of the nnUNet.
2023-01-02 21:29:03 +08:00
26f3df7a45
[Feature] nnUNet-style Gaussian Noise and Blur ( #2373 )
...
## Motivation
implement nnUNet-style Gaussian Noise and Blur
2023-01-02 20:43:15 +08:00
da4125587e
[Refactor] Support TTA ( #2184 )
...
* tta init
* use mmcv transform
* test city
* add multiscale
* fix merge
* add softmax to post process
* add ut
* add tta pipeline to other datasets
* remove softmax
* add encoder_decoder_tta ut
* add encoder_decoder_tta ut
* rename
* rename file
* rename config
* rm aug_test
* move flip to post process
* fix channel
2022-12-30 22:52:07 +08:00
79e8578bfc
[Feature] Add Biomedical 3D array random crop transform ( #2378 )
...
* [Feature] Add Biomedical 3D array random crop transform
* fix lint
* fix gen crop bbox
* fix gen crop bbox
* docstring
* typo
Co-authored-by: MeowZheng <meowzheng@outlook.com>
2022-12-30 22:52:07 +08:00
163277bfe0
[Feature] Support Mask2former in MMSeg 1.x ( #2255 )
...
* init commits
* fix crop size
* add seg_data2instance_data method
* add ut and update requirement
* update configs and readme
* add model-indel
* update optional requirements
* fix results
* fix lint error
* update results
* update results
* remove mmdet from requirements/optional.txt
* use try import and update README
* add docstring to overwrtied method
* minor change
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-12-05 18:34:24 +08:00
933e4d3cb6
[Feature] Support MaskFormer(NeurIPS'2021) in MMSeg 1.x ( #2215 )
...
* [Feature] Support MaskFormer(NeurIPS'2021) in MMSeg 1.x
* add mmdet try except logic
* refactor config files
* add readme
* fix config
* update models & logs
* add MMDET installation and fix info
* fix comments
* fix
* fix config norm optimizer setting
* update models & logs & unittest
* add docstring of MaskFormerHead
* wait for mmdet 3.0.0rc4
* replace seg_mask with seg_logits & add docstring for batch_input_shape
* use mmdet3.0.0rc4
* fix readme and modify config comments
* add mmdet installation in pr_stage_test.yml
* update mmcv version in pr_stage_test.yml
* add mmdet in build_cpu of pr_stage_test.yml
* modify mmdet& mmcv installation in merge_stage_test.yml
* fix typo
* update test.yml
* update test.yml
2022-12-01 19:03:10 +08:00
925faea5bf
[Fix] Fix the problem of post-processing not removing padding ( #2367 )
...
* add img_padding_size
* minor change
* add pad_shape to data_samples
2022-12-01 16:35:39 +08:00
0cdab7297e
Merge pull request #2339 from xiexinch/resize-shortest-edge
...
[Feature] Add ResizeShortestEdge transform
2022-12-01 16:06:23 +08:00
925110044c
[Enhance] Make scipy as a default dependency in runtime in dev-1.x
2022-11-30 21:51:38 +08:00
721afaec31
add docstring
2022-11-24 16:22:07 +08:00
68e3b25560
use mmcv.RandomChoiceResize as entry
2022-11-24 14:55:25 +08:00
721f4d01f3
add ut
2022-11-23 15:15:38 +08:00
8fed7f543f
add data_preprocessor ut
2022-11-17 11:10:40 +08:00
b21df463d4
[Feature] LIP dataset ( #2187 )
...
* [WIP] LIP dataset
* wip
* keep473
* lip dataset prepare
* add ut and test data
2022-10-31 20:47:52 +08:00
3d8fd35e26
[Feature]Add Decathlon dataset ( #2227 )
...
* [Feature]Add Decathlon dataset
* fix test data
* add file
* remove order
* revise default value for prefix
* modify example
* revise based on comments
* add comments for ut
2022-10-26 20:10:42 +08:00
ac9ee8c355
[Feature]Generate Edge for dataset ( #2210 )
...
* [WIP]Generate Edge for dataset
* add ut
* add repr
* add inti
2022-10-20 16:45:31 +08:00
25604a151b
[Feature] Support PoolFormer in MMSegmentation 2.0 ( #2191 )
...
* [Feature] 2.0 PoolFormer
* fix mmcls version
* fix ut error
* fix ut
* fix ut
2022-10-19 13:08:07 +08:00
20c7dc689c
[Feature] Add BioMedical data loading ( #2176 )
...
* [WIP] Add BioMedical data loading
* add depends nibabel
* fix bug
* fix ut
* fix
* add test data
* xyz2zyx zyx2xyz
* format
* remove ignore empty
* remove ignore empty
* remove with seg in LoadBiomedicalAnnotation
* float32
* docstring
* toxyz
* docstring
2022-10-18 16:30:08 +08:00
f3cd44bebf
[Fix] Fix ResizeToMultiple transform in MMSeg 1.x ( #2185 )
2022-10-14 15:37:35 +08:00
8b392946bb
[Doc] Add evaluation doc ( #2077 )
...
* introduction
* add evaluator doc and fix typo
* fix ut
* add test dataflow
* add runner reference
* add dataloader config
* fix typo
* minor change
2022-10-13 14:55:04 +08:00
b3b7629d38
[Fix] Fix binary segmentation ( #2101 )
...
* add out_channels
* fix forward
* add decode_head ut
* add segmentor ut
* refine postprocess
* fix
2022-09-27 16:49:38 +08:00
2a183283f5
[Enhancement]Add `out_file` in add_datasample to directly save image ( #2090 )
...
* [Enhancement]Add `out_file` in add_datasample to for save vis image directly
* comments
* ut
2022-09-20 15:23:13 +08:00
230246f557
[Refactor] Add pyupgrade pre-commit hook ( #2078 )
...
* add pyupgrade hook
* run pyupgrade precommit hook
2022-09-19 14:06:29 +08:00
8ce7055d1a
[Fix] Fix mmengine dump of tversky ut in dev-1.x ( #2001 )
2022-08-31 12:01:55 +08:00
ee7f340dff
[Feature] Support Tversky Loss in dev-1.x branch ( #2000 )
2022-08-31 10:58:21 +08:00
032ad84375
[Fix] Config name in ut ( #1978 )
...
* [Fix] Config name in ut
* lint
2022-08-26 21:20:26 +08:00
8de0050f25
[Refactor] data flow ( #1956 )
...
* [WIP] Refactor data flow
* model return
* [WIP] Refactor data flow
* support data_samples is optional
* fix benchmark
* fix base
* minors
* rebase
* fix api
* ut
* fix api inference
* comments
* docstring
* docstring
* docstring
* fix bug of slide inference
* add assert c > 1
2022-08-26 15:54:23 +08:00
50546da85c
[Fix]Remove modules from mmcv.runner and mmcv.utils ( #1966 )
...
* [WIP] mmcv-clean
* [WIP]Remove modules from mmcv.runner and mmcv.utils
* wip
* fix import mmengine
* remove ut
* loadcheckpoint in mae
2022-08-25 15:15:21 +08:00
e0499d5a77
[Fix] Fix repo based on refactoring standard ( #1869 )
...
* [Fix] Fix repo based on refactory standard
* fix ut
2022-08-19 20:50:02 +08:00
167f94a70b
rename data to structures ( #1854 )
2022-08-19 20:50:02 +08:00
ecab73a892
[Feature] Add P1 DataTransform ( #1843 )
...
* [Feature] Add P1 DataTransform
* fix unit test error
* fix @cache_randomness location
2022-08-19 20:50:01 +08:00
76c5ce1396
[Fix] Fix after iter `SegVisualizationHook` ( #1908 )
...
* [Fix] Fix after iter `SegVisualizationHook`
* ut
2022-08-10 21:02:09 +08:00
85ef7b905a
[Fix] Fix LoacalVisualizer UT ( #1851 )
2022-08-01 19:53:13 +08:00
1479d0a87b
[Fix] Add skip op if NO CUDA in local visualizer ( #1850 )
2022-08-01 18:15:58 +08:00
7369d50049
[Fix] Fix SegLocalVisualizer gt_sem_seg cuda tensor error ( #1845 )
...
* [Fix] Fix SegLocalVisualizer gt_sem_seg cuda tensor error
* fix ut error and add config visualizer dict
* fix ut error
2022-08-01 15:03:01 +08:00
5d9650838e
[Fix] Fix demo scripts ( #1815 )
...
* [Feature] Add SegVisualizer
* change name to visualizer_example
* fix inference api
* fix video demo and refine inference api
* fix
* mmseg compose
* set default device to cuda:0
* fix import
* update dir
* rm engine/visualizer ut
* refine inference api and docs
* rename
Co-authored-by: MengzhangLI <mcmong@pku.edu.cn>
2022-07-29 18:37:20 +08:00
3bbdd6dc4a
[Fix] Fix unit test image file path error ( #1835 )
2022-07-28 16:30:29 +08:00
6873f9ece8
[Feature] Add SegVisualizer ( #1792 )
...
* [Feature] Add SegVisualizer
* change name to visualizer_example
* fix typo
* refactor folder structure
2022-07-27 16:28:09 +08:00
6758b148b3
[Fix] Fix DATASETS not imported error ( #1827 )
2022-07-26 14:46:59 +08:00
3cf2bbda2a
[Fix] Change CustomDataset to BaseSegDataset ( #1791 )
2022-07-26 12:01:40 +08:00
ba4d1d62aa
[Feature] Add LoadImageFromNdArray pipeline ( #1810 )
...
* add load image from ndarray pipeline
* fix import
2022-07-22 19:40:00 +08:00
4de57b49c5
[Fix] Fix register_all_modules and imports ( #1793 )
...
* [Fix] Fix register_all_modules and imports
* fix transforms import
2022-07-21 22:44:42 +08:00
4b76f277a6
[Refactory] MMSegmentation Content
2022-07-15 15:47:29 +00:00
89d6f89dfc
Merge branch 'linfangjian/refactor_citysmetric' into 'refactor_dev'
...
[Refactor] Refactor cityscapes metrics
See merge request openmmlab-enterprise/openmmlab-ce/mmsegmentation!46
2022-06-28 03:21:33 +00:00
6053345b3d
[Refactor] Refactor cityscapes metrics
2022-06-28 03:21:33 +00:00
f2bac79f03
[Refactor] Refactor DatasetWrapper
2022-06-27 14:36:18 +00:00
Wencheng Wu
谢昕辰
王永韬
legendchilli
Fivethousand
Haoyu Wang
Jin Ye
MengzhangLI
Miao Zheng
zhengmiao
linfangjian.vendor
limengzhang.vendor