a135580912
[MASTER] Add Master decoder
2022-07-21 10:51:01 +08:00
f03ed3ce11
[Transform] RandomFlip
2022-07-21 10:51:01 +08:00
d5a2d20574
[Enchance] ce ignore char
2022-07-21 10:51:01 +08:00
b44869059b
[SATRN] SATRN Backbone
2022-07-21 10:51:01 +08:00
401088913b
[SATRN] SATRN Encoder
2022-07-21 10:51:01 +08:00
35e5138b5d
Cleanup test tmp files in test crnn decoder
2022-07-21 10:51:01 +08:00
dfe93dc7d2
[Transform] ScaleAspectJitter
2022-07-21 10:51:01 +08:00
da175b44a4
[Fix] Fix RandomRotate
2022-07-21 10:51:01 +08:00
50f229d9fe
[NRTR] NRTR Encoder
2022-07-21 10:51:01 +08:00
8614070e36
[NRTR] NRTR Decoder
2022-07-21 10:51:01 +08:00
d41921f03d
[NRTR] NRTR backbone
2022-07-21 10:51:01 +08:00
25e819f6bf
[Fix] Fix TextDetRandomCrop
2022-07-21 10:51:01 +08:00
b3b1ef146b
[Fix] Check transform's unit test and visualize
2022-07-21 10:51:01 +08:00
d859fcad1c
[Update] Add toy dataset in 2.0 form for test
2022-07-21 10:51:00 +08:00
2a852f23b5
[Fix] fix hmean iou
2022-07-21 10:51:00 +08:00
b585dbcdd7
Fix score field in DBPostprocessor
2022-07-21 10:51:00 +08:00
a4952a6dd6
Fix RandomCrop
2022-07-21 10:51:00 +08:00
38eef984c2
[Refactor]CELoss
2022-07-21 10:51:00 +08:00
f4a8e0f3a9
[Fix] fix metric and ut
2022-07-21 10:51:00 +08:00
8396b2014e
Refactor FPNC
2022-07-21 10:51:00 +08:00
3a9f9e6b61
Handling a corner case in offset_polygon
2022-07-21 10:51:00 +08:00
32ef9cc3cf
[DBNet] Add DBHead
2022-07-21 10:51:00 +08:00
7a66a84b64
[DBNet] Add DBPostProcessor
2022-07-21 10:51:00 +08:00
cd3d173b18
[DBNet] Add DBLoss
2022-07-21 10:51:00 +08:00
747b2a14dc
Refactor ResNet backbone
2022-07-21 10:51:00 +08:00
43c50eee82
fix loss
2022-07-21 10:51:00 +08:00
1e1da7b395
[DBNet] Add MaskedSmmothL1Loss, MasedBalancedBCELoss and MaskedDiceLoss
2022-07-21 10:50:59 +08:00
0f0f68baf1
Fix crop_polygon, Resize and poly2shapely
2022-07-21 10:50:59 +08:00
bbbefaeb31
build LabelData in baseprocessor
2022-07-21 10:50:59 +08:00
7582fdea41
[Refactor] CTCLoss
2022-07-21 10:50:59 +08:00
3aae157aec
[Refactor] crnn decoder
2022-07-21 10:50:59 +08:00
f173cd3543
[Refactor] Refactor WordMetric and CharMetric
2022-07-21 10:50:59 +08:00
4fd048aa24
[Fix] fix base recog loss
2022-07-21 10:50:59 +08:00
fe43259a05
[Refactor] train and test
2022-07-21 10:50:59 +08:00
ee48713a89
[Refactor] TextDetLocalVisualizer
2022-07-21 10:50:59 +08:00
c78be99f6b
[Refactor] Refactor TextRecogVisualizer
2022-07-21 10:50:59 +08:00
7e7a526f37
New Hmean-iou metric
2022-07-21 10:50:59 +08:00
f47f3eff03
fix polygon type
2022-07-21 10:50:58 +08:00
05e31e09bc
[Fix] base decoder forget passing dictionary
2022-07-21 10:50:58 +08:00
4706cc7eca
[Refactor] Refactor SquareResizePad
2022-07-21 10:50:58 +08:00
2f4679e908
LoadAnnotations
2022-07-21 10:50:58 +08:00
be30df5d50
Rename TextRecog directories
2022-07-21 10:50:58 +08:00
f820a50752
Rename TextDet directories
2022-07-21 10:50:58 +08:00
84a61ba816
RescaleToHeight and PadToWidth
2022-07-21 10:50:58 +08:00
a05e3f19c5
[Feature] TextRecogPostprocessor
2022-07-21 10:50:58 +08:00
e8f57d6540
[Feature] PackDet/RecogInput
2022-07-21 10:50:58 +08:00
5dc791adbb
[Refactor] Refactor randomscaling
2022-07-21 10:50:58 +08:00
d2808e6b84
[refactor] Refactor Crop-Related Operations
2022-07-21 10:50:58 +08:00
7b6778c5d8
add torchvisionwrapper
2022-07-21 10:50:58 +08:00
0b5d2df310
[Refactor] BaseDecoder
2022-07-21 10:50:58 +08:00
6cd38a038f
[Refactor] base recog loss
2022-07-21 10:50:57 +08:00
ac4eb34843
[Refactor] RandomCropFlip
2022-07-21 10:50:57 +08:00
79186b61ec
ImgAug: ignores->ignored
2022-07-21 10:50:57 +08:00
178030bad6
[Refactor] Refactor transform.RandomRotate
2022-07-21 10:50:57 +08:00
f29853d9cd
[Feature] Add Resize
2022-07-21 10:50:57 +08:00
6478499073
add mode to rescale_polygon(s)
2022-07-21 10:50:57 +08:00
df2f7b69db
Add recognition data migrator
2022-07-21 10:50:57 +08:00
7b09da485b
[Fix] Support textrecog, add more tests
2022-07-21 10:50:57 +08:00
0f041d4250
[Fix] updata LabelData import
2022-07-21 10:50:57 +08:00
f6b72b244b
Add ImgAug and tests
2022-07-21 10:50:57 +08:00
cb85f857aa
Add BaseTextDetPostProcessor
2022-07-21 10:50:57 +08:00
f0c6d44ce8
Add dump_ocr_data
2022-07-21 10:50:56 +08:00
98bc90bd1c
[Feature] TextRecogSample
2022-07-21 10:50:56 +08:00
c920edfb3a
[Refactor] split labelconverter to Dictionary
2022-07-21 10:50:56 +08:00
c47c5711c1
[Feature] TextDetSample
2022-07-21 10:50:56 +08:00
41c1671e7b
Refactor PyramidRescale
2022-07-21 10:50:56 +08:00
b5fc589320
Add CI
2022-07-21 10:50:55 +08:00
69e6c80558
move tests to old_tests, add empty test folders
2022-07-21 10:50:55 +08:00
1ad4caa7cb
[Enhancement] Allow choosing metrics to report in text recognition tasks ( #989 )
...
* [Enhancement] Allow choosing metrics to report in text recognition tasks
* add acc support
* refine docstr
2022-05-05 16:10:38 +08:00
061d353b2a
[Model] Add MASTER ( #807 )
...
* fix #794 : add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* Fix linting
* after git rebase main
* after git rebase main
* fix conflict add MASTER
* fix conflict add MASTER
* after git rebase main
* fix conflict add MASTER
* fix conflict add MASTER
* fix conflict add MASTER
* after git rebase main
* add GCAModule to plugins
* coexist master and master_old
* fix merge mmocr 0.5.0 conflict
* fix lint error
* update
* [fix] remove remains in __init__
* [update] update code in review
* update readme for master
* Add docstr to MasterDecoder, refined MasterDecoder, remove MASTERLoss
* Unify the output length of MasterDecoder in train and test mode; add test for it, remove MasterLoss
* update readme
* update
* update metafile,README,demo/README,config,ocr.py
* Update mmocr/utils/ocr.py
* update
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
Co-authored-by: Mountchicken <mountchicken@outlook.com>
2022-05-05 16:06:15 +08:00
fbc138d2d3
[Feature] Add DBNet++ ( #973 )
...
* add dbnet++
* fix docstring
* fix some param names
* fix
* fix docstring
* add init
* add doc; remove configs
* add dbnet++ to readme
* fix readme
* update config
* update readme
* update readme
* update ocr.py
* update metafile.yml
* update readme
* update readme
* move to dbnetpp
* fix paths
* fix head level
* fix typo
* update demo.md
* Update configs/textdet/dbnetpp/README.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* fix typo
* fix link
2022-05-05 14:39:20 +08:00
6b180db93d
[Enhancement] Automatically report mean scores when applicable ( #995 )
2022-05-05 12:57:19 +08:00
a2d741b8a7
[Feature] Add labelme converter for textdet and textrecog ( #972 )
...
* add labelme converter
* move to common
* add labelme sample annos
* add doc
* remove useless field generated by labelme to reduce size
* add recog_format option; add skip ignored instances while cropping
* set warp as false by default
* update doc
* fix typo
Co-authored-by: xinke-wang <wangxinyu2017@gmail.com>
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
2022-05-03 17:28:22 +08:00
c91763ad09
[Fix] update label.lmdb ( #991 )
...
* loss
* fix
* hotfix
2022-04-29 23:26:32 +08:00
92ef554a82
[Feature] Add recog2lmdb and new toy dataset files ( #979 )
...
* loss
* fix
* add img2lmdb and test files
* update
* add reference
* fix lint
* fix typo
* use total_numer instead to fit mmocr's lmdbloader
* reorganize and update
* fix lint
* update test file
* refactor and update
* fix test
* update doc in tools
* fix lint
* update old lmdb test file
* update
* mask the unittest for recog2lmdb and use json format for label_only
* remove if __name__
* fix case, doc, typo, formats
* fix typos
* fix docs and variable names
* Apply suggestions from code review
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
* update test_loader.py and fix a bug
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
2022-04-29 22:30:36 +08:00
d8549ade85
[Feature] Support loading images and labels from lmdb file ( #982 )
...
* loss
* fix
* add LoadImageFromLMDB
* update
* new version
* add json
* fix bug
* Compatible with older versions
* modify test_loader
* add docstring and update test_loader
* fix a bug
* fix docstring and update doc
* update
* Update mmocr/datasets/utils/backend.py
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
* Update docs/en/tutorials/dataset_types.md
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
* fix lint
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
2022-04-29 15:46:36 +08:00
064a2b8c45
[Feature] Support computing mean scores in UniformConcatDataset ( #981 )
...
* Get avg results in UniformConcatDataset
* add docstr
* Fix
* fix test
* fix typo
2022-04-29 14:48:21 +08:00
0c8fa52b22
[Fix] Fix ImgAug transform ( #949 )
...
* [Fix] Fix bbox case in ImgAug
* Finialize the augmentation and add tests
2022-04-28 22:52:11 +08:00
888f700134
[Enhancement] Support dynamic threshold range in eval_hmean ( #962 )
...
* [Enhancement] Support dynamic threshold range in eval_hmean
* upgrade textdetdataset, add deprecate warning
2022-04-22 17:07:36 +08:00
b11fa80d82
[Fix] correct meta key ( #926 )
...
* correct meta key
* fix test metakey
2022-04-18 09:09:09 +08:00
c79a62487d
[Feature] Add Tesserocr Inference ( #814 )
...
* append tesserocr to requirements list, but may encounter build error at windows platform
* simply save
* 2022.3.4
* opencv-python==4.5.5 can cause cv2.error when print_result=True
* append MMOCR.tesseract_det_inference()
* argument check append
* fix lint error
* update commentary
* lint fix
* requirement remove opencv
* handle tessdata problem
* support tesseract recognition
* fix some bugs
* fix imshow bug
* support batch mode(fake)
* modify annotation
* refactor BaseRecognizer for show_result
* append pytest
* Mock tesseract
* Fix test
* remove \n from Tesseract
* normalize text score
* update docs
2022-03-28 22:50:53 +08:00
37833ada4b
[Fix] Support loading space character from dict file ( #854 )
...
* [Feature] Support loading dict file with space character
* fix tests
* clean up \\r in tests
* add DICT37 and DICT91
* update docstr
2022-03-22 17:44:32 +08:00
72f9454573
[Refactor] Refactor ResNets ( #809 )
2022-03-18 10:36:03 +08:00
680dff373e
[Feature] Support jsonl in recognition converter ( #844 )
2022-03-18 09:22:32 +08:00
402e8f1162
[Feature] Support loading annotation file with petrel/http backend ( #793 )
...
* add petrel backend for ann_file loading
* support icdar dataset
* add http backend
* name back
* fix pytest
* support load lmdb file on ceph
* refactor
* add close for lmdb
* add log and warning msg
* rename
* typo
* update
* fix
2022-03-07 19:18:02 +08:00
fb77352eb2
[Fix] Standardize the type of torch.device in ocr.py ( #800 )
2022-03-03 14:18:33 +08:00
3110ab7863
[Enhancement] Add windows CI ( #790 )
...
* [Enhancement] Add windows CI
* [Enhancement] Add windows CI
* update
* update
* update
* [Fix] using assert will keep lmdb file opend and fail to cleanup in test_loader.py
* [Fix] map size should be small on windows in lmdb_util.py
* [Fix] Fix some bugs
* [Fix] Fix some bugs
* [Fix] Fix some bugs
* remove comments & fix bugs
Co-authored-by: Mountchicken <mountchicken@outlook.com>
2022-03-02 10:34:15 +08:00
5582e17feb
[Enhancement] Automatically infer device for inference if not speicifed ( #781 )
...
* [Enhancement] Automatically infer device for inference if not speicifed
* update docs
* fix unit test
2022-02-16 20:42:47 +08:00
0f5c7d38f8
[Fix] Disable worker in the dataloader of gpu unit test
2022-02-16 20:42:22 +08:00
c466e6f82d
[Enhancement] Upgrade isort ( #771 )
...
* [Enhancement] Upgrade isort
* Fix files
2022-02-09 23:22:14 +08:00
d871eed79e
[Enhancement] Add setup multi-processing both in train and test. ( #757 )
2022-01-26 20:34:19 +08:00
82488024db
[Feature] Add bezier_to_polygon and sort_points to box_util ( #703 )
2022-01-17 15:26:55 +08:00
fb1892a1ae
[Fix] fix bug of show_results in single_gpu_test ( #667 )
...
* move single_gpu_test to mmocr/apis
* fix show result in single_gpu_test
* add unittest
* add docstring
* add unittest for kie
* avoid re-define
* remove skipif
* add skip
* fix conflict
* fix with comment
* add note in readme
* update
2021-12-23 03:30:01 +00:00
f8dfbd4177
[Fix] Support both ConcatDataset and UniformConcatDataset ( #675 )
...
* support UniformConcatDataset
* update
* rm useless
* handle 2d-list datasets
2021-12-22 12:32:02 +00:00
9104667112
[Model] Full ABINet Framework ( #651 )
...
Co-authored-by: liukuikun <24622904+Harold-lkk@users.noreply.github.com>
2021-12-15 11:21:54 +08:00
a4237ad568
[Enhancement] Support muitiple pipelines for different datasets ( #657 )
...
* support multi pipelines
* support different pipelines
* fix
* fix replace_image_to_tensor
* remove redundant check
* update
* add copyright
* not in-place modify
2021-12-14 12:29:43 +00:00
7874531db3
[Refactor] refactor textdet postprocess ( #640 )
...
* refactor textdet postprocess using build_postprocessor
* update docstring
* update docstring
* update postprocess docstring
* compatible with previous configs
* rename to BaseTextDetector
* rename to DRRGPostprocessor
* fix
* update warning
* fix
* fix conflict
* rename back
* rename warpper to utils
* fix doc
2021-12-14 17:35:44 +08:00
5caa945a8d
fix #614 : textsnake targets ( #660 )
...
* fix #614 : textsnake targets
* fix lint
* add textsnake_targets test cases
* init with eps
* fix test coverage
2021-12-13 17:45:30 +08:00
c6c4acd39b
[Fix] fix type check ( #650 )
...
* fix check type
* add notice
2021-12-09 12:45:59 +08:00
fec986aba0
[Enhancement] Use shape from loaded image ( #652 )
...
* use shape from loaded image
* complete unittest
* add params as gate
* add comment
* add assert
2021-12-09 01:34:09 +00:00
0a1787d6bc
[Refactor] refactor transformer modules ( #618 )
...
* base refactor
* update config
* modify implementation of nrtr
* add config file
* add mask
* add operation order
* fix contiguous bug
* update config
* fix pytest
* fix pytest
* update readme
* update readme and metafile
* update docstring
* fix norm cfg and dict size
* rm useless
* use mmocr builder instead
* update pytest
* update
* remove useless
* fix ckpt name
* fix path
* include all config file into pytest
* update inference
* Update test_recog_config.py
2021-12-04 17:12:31 +08:00
5a8859fe66
[Refactor] Refactor text detection config ( #626 )
...
* refactor textdet configs
* remove duplicate keys in _base_
* remove import from config
* syncbn to bn on cpu
* minimize change
2021-12-03 19:37:43 +08:00
d3d56182c6
fix #630 : Add input size check to model_inference ( #633 )
...
* fix #630 : Add input size check to model_inference
* fix #630 : Added exception when receiving empty image
2021-12-02 03:00:23 +00:00
809661ea28
[Enhancement] CircleCI Setup ( #611 )
...
* Add .circleci/config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* fix unit test
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
* Updated config.yml
2021-11-23 19:54:38 +08:00
a50b0c9fb9
[Feature] Support openset kie ( #498 )
...
* add openset kie dataset
* updare readme
* add anno convert script
* update docstring
* update script
* add & update docstring
* fix typo
* update docstring format
2021-11-11 14:47:38 +08:00
9f42d78db7
[Feature] Save filename in text detection test results ( #570 )
...
* save filename in textdet test results
* fix pytest
2021-11-11 14:07:07 +08:00
aa4b5b5574
[Fix] Allow invalid polygons in intersection and union by default ( #471 )
...
* Allow invalid polygons in intersection and union by default
* update docs
2021-09-28 10:57:12 +08:00
0881c2d2a2
[Fix] Add zero division handler in poly utils, remove Polygon3 ( #448 )
...
* Add check to avoid zero div in iou computation
* replace polygon3 with shapely
* remove req of Polygon3
2021-08-25 13:14:58 +08:00
7c1bf45c63
[Fix] fix inconsisent training/eval state after SyncBN->BN ( #453 )
2021-08-25 13:14:03 +08:00
8f377f2fa2
[Feature] Add Satrn ( #405 )
...
* Add SATRN
* Create satrn_small_academic.py
* Update README.md
* change config name
* Update mmocr/models/textrecog/backbones/shallow_cnn.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update configs/textrecog/satrn/satrn_academic.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update configs/textrecog/satrn/satrn_small.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update shallow_cnn.py
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update test_ocr_encoder.py
* change keep_aspect_ratio=False
* Update transformer_layer.py
* Update configs/textrecog/satrn/satrn_small.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update configs/textrecog/satrn/satrn_academic.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update mmocr/models/textrecog/layers/transformer_layer.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update transformer_layer.py
* Apply suggestions from code review
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update transformer_layer.py
* update satrn readme
* add satrn to ocr.py
* add satrn_sm and fix configs
* add a test for config
* add copyright info
* use mmocr registry
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2021-08-19 22:02:58 +08:00
7571763376
[Refactor] Use MMOCR's registry ( #436 )
...
* [Refactor] Use MMOCR's registry
1. Define MMOCR's registries as a child of MMDet's
2. Register all models to MMOCR's own registries
3. Modify some model configs so that some models in MMDet can be
correctly located
4. Remove some outdated demo scripts
* add detectors
2021-08-19 19:17:15 +08:00
b8f7ead74c
[Enhancement] Add copyright info ( #439 )
...
* add copyright info
2021-08-17 17:39:30 +08:00
9b5b25ef71
[Fix] fix a bug of DBNet when text repr type is poly ( #421 )
...
* fix dbnet bug when text repr type is poly
* add db_decode unit test
2021-08-13 21:39:53 +08:00
80a0536c7c
[Enhancement] Add tests for ocr.py ( #428 )
...
* minor fix to ocr.py
* add test for ocr.py
2021-08-13 09:55:33 +08:00
906faec372
update digit_version and add a test ( #427 )
2021-08-12 08:53:45 +00:00
7bbb14f0d1
[Fix] Replace SyncBN with BN for inference ( #420 )
...
* add revert_sync_batchnorm
* replace SyncBN in inference and test scripts
* add tests
* hide BatchNormXd
2021-08-10 22:19:17 +08:00
f24be6c614
fix bug of dice loss: loss always 1 if empty target ( #408 )
2021-08-04 06:05:31 +00:00
3707d67106
support batch inference for crnn and segocr ( #407 )
...
* support batch inference for crnn and segocr
2021-08-03 16:52:58 +08:00
4f7270e574
Fix #282 : Support init_cfg & update depreciated configs ( #365 )
...
* update coco ref
* init_cfg for dbnet
* initcfg for mask_rcnn
* textsnake init_cfg
* fix dbnet
* panet initcfg
* psenet initcfg
* fcenet initcfg
* drrg initcfg
* add init_cfg to detectors
* update maskrcnn config file to support mmdet
* fix init_cfg of fce_head
* crnn initcfg
* init_weights in training
* nrtr initcfg
* robust_scanner initcfg
* sar init_cfg
* seg init_cfg
* tps_crnn init_cfg
* sdmgr initcfg
* ner init_cfg
* fix textsnake
* sdmgr initcfg
* move "pretrained" to "init_cfg" for config files
* Moduleslist update
* fix seg
* ner init_cfg
* fix base
* fix encode decode recognizer
* revert dbnet config
* fix crnn
* fix base.py
* fix robust_scanner
* fix panet
* fix test
* remove redundant init_weights() in fcehead
* clean up
* relex mmdet version in workflow
* Add dependency version check
* Update mmocr/models/textdet/dense_heads/pse_head.py
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-07-20 23:18:25 +08:00
44fed8590b
fix bug: remove tail whitespace from gt label ( #358 )
...
* fix bug: remove tail whitespace from gt label
* remove useless
* refactor
2021-07-09 13:24:34 +00:00
20f65fb521
use unifor_concat_datase instead of concat_dataset ( #343 )
...
* use unifor_concat_datase instead of concat_dataset
* add unittest for uniform_concat_dataset
2021-07-03 16:03:37 +08:00
97ac619e68
[Fix] Fix unit tests, remove temporary files ( #328 )
...
* fix unit tests, remove temp files
* use tempfile package and fix typo
* all files clear
2021-06-26 22:51:50 +08:00
8999c56159
Fix kie_test_imgs script for novisual ( #319 )
...
* Fix kie_test_imgs script for novisual
Signed-off-by: lizz <lizz@sensetime.com>
* Fix test
Signed-off-by: lizz <lizz@sensetime.com>
2021-06-24 07:22:34 +00:00
7c4eb7e056
fix #253 : speedup; fix assert ( #263 )
...
* fix #253 : speedup; fix assert
* fix #253 : speedup; fix assert
* add unittest for bug fix block
2021-06-23 08:16:57 +00:00
82f64a5b62
support batch inference during testing ( #310 )
...
* support batch inference during testing
* fix unittest
* update docs using url
* set cfg for train, val and test
* update docs
* update docs and test.py
* samples_per_gpu as global setting
* changes revert
2021-06-23 11:34:29 +08:00
9582f93c70
Support ocr box stitching ( #290 )
...
* ocr box stitching
* rename a varible
* add a demo
* move functions to box_util
add test
2021-06-19 19:28:14 +08:00
a86ab115e4
fix unit tests ( #300 )
2021-06-18 18:27:20 +08:00
f1b003ddb1
[Feature] Add deployment evaluation ( #291 )
...
* add deployment evaluation
* fix lint
* remove cpu unit tests for trt and onnx
* use pytest.mark to skip cpu unit test
* move to mmocr/core
* emm... renamed to wrappers
* renamed to deploy_utils
* renamed unit test to test_deploy_utils
* fix lint
* using pytest.mark.importorskip
2021-06-18 12:27:10 +08:00
d57f279083
[Fix] Correct isort setup ( #288 )
...
* isort
* remove tools from setup.cfg
2021-06-16 19:44:01 +08:00
3bfbb2b619
fix #113 : textsnake decode error ( #264 )
...
* fix #113 : textsnake decode error
* fix unittest test cases
2021-06-15 08:09:05 +00:00
0131b3290f
[Feature] Add onnx and tensorrt export tool ( #278 )
...
* add onnx and tensorrt export
* fix lint
* delete batch input to avoid dbnet error
* resolve unittest
* fix lint
* export unittest
2021-06-15 07:51:36 +00:00
18e7ecc379
add fce ic15 ( #258 )
2021-06-03 15:00:38 +08:00
36e92ebe70
Speed up sort_vertex ( #239 )
...
* Speed up sort_vertex
Signed-off-by: lizz <lizz@sensetime.com>
* Fix test
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-25 19:58:05 +08:00
b10b6408ef
Add list_from_file and list_to_file ( #226 )
...
* Add list_from_file and list_to_file
Signed-off-by: lizz <lizz@sensetime.com>
* Add test list_to_file and list_from_file
* more
* Fix tests
2021-05-24 06:01:42 +00:00
0bd32889d4
fix #212 : improve drrg ( #224 )
2021-05-21 18:36:44 +08:00
8c60e4b4d1
update fcenet ( #214 )
...
* update fcenet
* fix typos
* fix
2021-05-18 21:52:34 +08:00
9e0595f70b
Test more on cpu ( #217 )
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-18 21:47:32 +08:00
673aadc355
Hbsun/feature iss205 ( #210 )
...
* fix #205 : remove act2fn
* fix pytest
2021-05-18 15:15:35 +08:00
24c590bb04
Ner task ( #148 )
...
* update ner standard code format
* add pytest
* fix pre-commit
* Annotate the dataset section
* fix pre-commit for dataset
* rm big files and add comments in dataset
* rename configs for ner task
* minor changes if metric
* Note modification
* fix pre-commit
* detail modification
* rm transform
* rm magic number
* fix warnings in pylint
* fix pre-commit
* correct help info
* rename model files
* rename err fixed
* 428_tag
* Adjust to more general pipline
* update unit test rate
* update
* Unit test coverage over 90% and add Readme
* modify details
* fix precommit
* update
* fix pre-commit
* update
* update
* update
* update result
* update readme
* update baseline config
* update config and small minor changes
* minor changes in readme and etc.
* back to original
* update toy config
* upload model and log
* fix pytest
* Modify the notes.
* fix readme
* Delete Chinese punctuation
* add demo and fix some logic and naming problems
* add To_tensor transformer for ner and load pretrained model in config
* delete extra lines
* split ner loss to MaskedCrossEntropyLoss and MaskedFocalLoss
* update config
* fix err
* updata
* modify noqa
* update new model report
* fix err in ner demo
* Update ner_dataset.py
* Update test_ner_dataset.py
* Update ner_dataset.py
* Update ner_transforms.py
* rm toy config and data
* add comment
* add empty
* fix conflict
* fix precommit
* fix pytest
* fix pytest err
* Update ner_dataset.py
* change dataset name to cluener2020
* move the postprocess in metric to convertor
* rm __init__ etc.
* precommit
* add discription in loss
* add auto download
* add http
* update
* remove some 'issert'
* replace unsqueeze
* update config
* update doc and bert.py
* update
* update demo code
Co-authored-by: weihuaqiang <weihuaqiang@sensetime.com>
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-05-18 11:33:51 +08:00
2414c65577
Add drrg ( #189 )
...
* merge drrg
* directory structure&fix redundant import
* docstrings
* fix isort
* drrg readme
* merge drrg
* directory structure&fix redundant import
* docstrings
* fix isort
* drrg readme
* add unittests&fix docstrings
* revert test_loss
* add unittest
* add unittests
* fix docstrings
* fix docstrings
* fix yapf
* fix yapf
* Update test_textdet_head.py
* Update test_textdet_head.py
* add unittests
* add unittests
* add unittests
* fix docstrings
* fix docstrings
* fix docstring
* fix unittests
* fix pytest
* fix pytest
* fix pytest
* fix variable names
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-05-18 11:15:47 +08:00
cbdd98a1e1
add fcenet ( #133 )
...
* add fcenet
* fix linting and code style
* fcenet finetune
* Update transforms.py
* Update fcenet_r50dcnv2_fpn_1500e_ctw1500.py
* Update fcenet_targets.py
* Update fce_loss.py
* fix
* add readme
* fix config
* Update fcenet_r50dcnv2_fpn_1500e_ctw1500.py
* fix
* fix readme
* fix readme
* Update test_loss.py
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-05-14 21:37:04 +08:00
97e2f27017
fix #173 : support aug test ( #178 )
...
* fix #173 : support aug test
* fix pytest
* support batch inference for both text det and recog
* update unittest
* use one img for batch infer test
2021-05-13 07:18:00 +00:00
df5493a79e
refactor tps config ( #135 )
...
* refactor tps config
* recover tps
* add ckpt of tps
2021-05-12 06:14:24 +00:00
18c54afbdc
Add support for batch inference ( #86 )
...
* Add support for numpy arrays in model_inference
* Add test for numpy ndarray inference
* Fix linting problems
* Add support for batch inference
* Add batch inference demo script
* Fix comment
* Test batch inference with paths and arrays
* lint code
* Update model_inference docstring
* Refactor model inference tests
* Change inference function to make text detectors and recognizers use the same input data types
* Change single state text detector model to support batch inference
* Lint code
* simplify inference tests
* Remove psenet from batch inference test cases to prevent the pytest being killed
* Update batch_image_demo.py
* fix bug when test with dataset
fix bug when test with dataset, for example, `./tools/dist_test.sh configs/textrecog/sar/sar_r31_parallel_decoder_academic.py <checkpoint> 1 --eval acc`
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-05-12 02:04:01 +00:00
e7f27ae317
change argument names according to convention ( #131 )
...
* change argument names according to convention
* bug fix when rename leakyRelu
2021-05-11 16:07:36 +08:00
47896a3f80
Unit tests of dbnet transform ( #163 )
...
* Add unit test for dbnet transforms
* Add unit test for dbnet transforms
* Add unit test for dbnet transforms
2021-05-11 15:21:14 +08:00
892d486d01
add model for chinese ( #156 )
...
* add model for chinese
* update readme
* update readme
* fix link error; add vis for Chinese
2021-05-09 21:49:08 +08:00
5054a3f78d
Implement iter protocol for Loader ( #150 )
...
* Implement iter protocal for Loader
Signed-off-by: lizz <lizz@sensetime.com>
* Test iter protocal
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-06 09:51:29 +00:00
47965516f0
Improve KIE ( #153 )
...
* Improve KIE
* allow data do not contain label
* Make relation float32
Signed-off-by: lizz <lizz@sensetime.com>
* Add test
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-06 09:51:10 +00:00
e29b5b8abe
Fix issue 122 ( #130 )
...
* fix #122 : textsnake targets adaptation
* fix #122 : textsnake targets adaptation
* add unittest
* fix format
* fix textsnake unittest on cpu
* fix unit test coverage
* add unit test
2021-04-29 11:02:57 +08:00
7bf88d0e25
Add TPS ( #117 )
...
* Add TPS
* Update tps_preprocessor.py
* Add licence, change variable name and format
* renamed some parameters and add tests of ocr preprocessor
* renamed params
* Update tps_preprocessor.py
* add config file and readme for TPS
2021-04-28 07:39:13 +00:00
43dcb32d4f
Hbsun/end2end demo ( #105 )
...
* add end2end demo
* fix typo
* pad box
* fix bug of crnn
* fix polygon
* update docstring
* fix bug of polygon
* updare demo api
* fix except
* rename
* fix with comments
2021-04-22 20:42:42 +08:00
f5c385b02c
fix inference bug ( #87 )
...
* fix inference bug
* add unit test for det
2021-04-19 02:07:25 +00:00
a68de2214a
Add support for numpy array inference ( #74 )
...
* Add support for numpy arrays in model_inference
* Add test for numpy ndarray inference
* Fix linting problems
* Simplify assertion in model_inference
2021-04-18 20:10:17 +08:00
524498479f
add unit test for textsnake ( #61 )
2021-04-13 21:59:19 +08:00
344cc9a38d
Add unittest for kie ( #56 )
...
* add unittest for sdmgr
* fix #36 : update datasets.md
* unittest pass
2021-04-13 13:58:31 +08:00
c345255e49
remove test for textsnake ( #8 )
2021-04-08 03:07:22 +00:00
7acfabb482
fix pytest error ( #6 )
2021-04-08 01:48:15 +08:00
44ca9c2a61
Remove usage of \ ( #49 )
...
* Remove usage of \
Signed-off-by: lizz <lizz@sensetime.com>
* rebase
Signed-off-by: lizz <lizz@sensetime.com>
* typos
Signed-off-by: lizz <lizz@sensetime.com>
* Remove test dependency on tools/
Signed-off-by: lizz <lizz@sensetime.com>
* Remove usage of \
Signed-off-by: lizz <lizz@sensetime.com>
* rebase
Signed-off-by: lizz <lizz@sensetime.com>
* typos
Signed-off-by: lizz <lizz@sensetime.com>
* Remove test dependency on tools/
Signed-off-by: lizz <lizz@sensetime.com>
* typo
Signed-off-by: lizz <lizz@sensetime.com>
* KIE in keywords
Signed-off-by: lizz <lizz@sensetime.com>
* some renames
Signed-off-by: lizz <lizz@sensetime.com>
* kill isort skip
Signed-off-by: lizz <lizz@sensetime.com>
* aggregation discrimination
Signed-off-by: lizz <lizz@sensetime.com>
* aggregation discrimination
Signed-off-by: lizz <lizz@sensetime.com>
* tiny
Signed-off-by: lizz <lizz@sensetime.com>
* fix bug: model infer on cpu
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-04-06 12:16:46 +00:00
cbb4ec349b
Textsnake tests ( #51 )
...
* add textsnake unit tests
2021-04-06 18:20:43 +08:00
03a270d2c2
fix #47 : add unit test for api ( #48 )
2021-04-06 08:04:14 +00:00
fbb5c8cda1
fix #40 : add unit test for recog config, transforms, etc. ( #44 )
2021-04-06 07:17:20 +00:00
c8793ac141
Add textdet unit tests ( #43 )
...
* Fix #41 : test fpn_cat
* Fix #41 : test fpn_cat
* Fix #41 : test fpn_cat
2021-04-06 07:16:27 +00:00
aa87b69f12
fix #37 : remove useless code ( #38 )
2021-04-06 03:40:48 +00:00
7e281521cf
skip cuda
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-06 10:58:45 +08:00
06fee8328b
fix #31 : pytest pass
2021-04-06 10:58:45 +08:00
09ffd284ee
Remove test dependency on tools
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-06 10:57:25 +08:00
b153cc01c8
Re-enable skipped test
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-06 10:57:25 +08:00
2ad699e099
fix
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-06 10:57:25 +08:00
0f00378f9a
Feature/iss 33 ( #34 )
...
* fix #33 : update dataset.md
* fix #33 : pytest for transformer related
2021-04-05 23:54:57 +08:00
31f1c007c0
[feature]: add textdet
2021-04-03 01:03:52 +08:00
4ecd0cea8a
add sar, seg and other components
2021-04-02 23:54:57 +08:00
jiangqing.vendor
liukuikun
wangxinyu
gaotongxiao
Jianquan Ye
Xinyu Wang
Hongbin Sun
garvan2021
liukuikun
yuexy
Jianyong Chen
mpena-vina
LvTianlei
liukuikun
Jiaqi Duan
AllentDan
lizz
Zyq-scut
hq_wei
Sergio Bugallo Enjamio
kang sheng
jeffreykuang
Sergio Bugallo Enjamio
jeffreykuang
lizz