700b5d7a60
[Fix] Revert a wrong setting in db_r18 cfg ( #978 )
2022-04-27 10:30:46 +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
d901b37035
[Fix] Add num_classes to configs of ABINet ( #805 )
...
* [Fix] Add num_classes to configs of ABINet
* add comments
2022-03-16 17:17:02 +08:00
a36de7b48e
[Fix] Add necessary keys to test_pipelines to enable test-time visualization ( #754 )
2022-01-26 21:02:31 +08:00
976b976e4a
[Docs] update readme according to standard ( #742 )
...
* config/readme standard
* add ABINet linking
* fix linking error, delete unused cite and adjust note sytle
* union note format
* Remove > before paper link when generating docs
2022-01-25 23:02:59 +08:00
ad3957bb41
[Enhancement] Speed up training ( #739 )
2022-01-19 20:14:41 +08:00
5176e1bd5a
[Fix] fix link ( #726 )
2022-01-12 10:25:07 +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
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
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
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
69d5040590
[Docs] Update model readme ( #604 )
...
* update satrn
* Add intro and pic to readmes
* update stats.py
* abstract for tps
* Fix CRNN and TPS CRNN readme
2021-11-30 16:40:18 +08:00
5654079839
[Fix] Fix DBNet_r50 config ( #625 )
2021-11-26 12:26:32 +00:00
3188e53404
[Refactor] refactor textrecog config structure ( #617 )
...
* refactor configs of textrecog
* remove duplicate key in config _base_
* fix typo
* rename dataset config file
2021-11-25 16:27:45 +08:00
98c5bff1e0
[Feature] Save results to json file for kie. ( #589 )
...
* save results json for kie
* update config
* Fix KIE inference bug
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2021-11-15 20:28:13 +08:00
18fde080c4
[Fix] Modify algorithm "sar" weights path in metafile ( #581 )
...
Original model `sar_r31_parallel_decoder_academic` weights path in sar/metafile.yml belongs to crnn which should be modified.
2021-11-12 12:55:56 +08:00
a9fde9146f
[Feature] Improve dbnet r50 by fixing std ( #578 )
2021-11-11 19:10:12 +08:00
34bd6b9bbb
[Docs] Docs for KIE CloseSet & OpenSet ( #573 )
...
* add kie docs
* fix paths
* sync cn docs
* fix layout error
2021-11-11 17:39:27 +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
5fb1268a06
unify task names in metafiles ( #548 )
2021-11-03 15:03:37 +08:00
dab5725d70
fix paper field in metafiles ( #550 )
2021-11-03 15:02:31 +08:00
2f983eca83
[Fix] Fix PyTorch 1.6 incompatible checkpoints ( #540 )
...
* fix pt1.6 incompatible checkpoints
* fix satrn metafile
2021-10-27 19:12:52 +08:00
abfe75dc62
[Fix] Update checkpoint links for SATRN ( #518 )
2021-10-10 11:26:37 +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
8c72d80164
[Fix] Fix image export in test.py for KIE models ( #486 )
...
* Fix image export in test.py for sdmgr model
* fix pretrained
2021-09-18 18:24:55 +08:00
4c43f3fc47
[Docs] Fix a model link and add the metafile for SATRN ( #473 )
...
* update model link
* add metafile
2021-09-01 03:01:11 +00:00
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
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
884755d05d
Fix #112 : Remove the need of drop_orientation_info in data preprocessing steps ( #375 )
...
* ctw1500 ignore orientation
* restore maskrcnn config
* ignore_orientation support for icdar datasets
* update docs
* ignore orientation for total text
* Add LoadOCRImageFromFile
* Fix typo
* simplify design
* remove LoadOCRImageFromFile
* update chinese docs
2021-07-20 23:02:25 +08:00
6d97d8286e
Update nrtr batch size ( #370 )
2021-07-16 15:06:36 +08:00
1a5a880abb
fix nrtr cfg ( #356 )
2021-07-08 13:30:58 +08:00
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
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
ae90deab68
fix bug in sdmgr config ( #316 )
2021-06-23 16:58:56 +08:00
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
50a25e718a
update ckpt link ( #287 )
2021-06-15 20:28:09 +08:00
8dcc56955f
Ignore img processing for KIE without visual ( #260 )
...
* Ignore img processing for KIE without visual
Signed-off-by: lizz <lizz@sensetime.com>
* Add ResizeNoImg
Signed-off-by: lizz <lizz@sensetime.com>
* Tune speed
Signed-off-by: lizz <lizz@sensetime.com>
2021-06-10 10:07:33 +08:00
d4ba5b8c9b
fix fcenet readme ( #270 )
2021-06-09 20:03:16 +08:00
18e7ecc379
add fce ic15 ( #258 )
2021-06-03 15:00:38 +08:00
17aa9ecc7f
update metafile ( #228 )
2021-05-22 16:10:21 +08:00
ecfc1c7ebf
fix #216 : default ignore -100 ( #221 )
...
* fix #216 : default ignore -100
* update ckpt
2021-05-20 21:53:49 +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
1240169f18
update metafile ( #183 )
2021-05-14 00:17:33 +08:00
7e0d48df11
fix metafiles ( #182 )
2021-05-13 17:28:59 +08:00
cc27d8254b
Add metafiles ( #179 )
...
* add metafiles
* add metafiles
* add metafiles
* fix metafile errors
* fix metafiles
* Update metafile.yml
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-05-13 02:46:26 +00:00
df5493a79e
refactor tps config ( #135 )
...
* refactor tps config
* recover tps
* add ckpt of tps
2021-05-12 06:14:24 +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
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
e7847bd8b9
Visualise toy ( #137 )
...
* added img_norm_cfg key-value pair for toy data visualization
* add ori_filename
2021-04-28 12:42:08 +00:00
20cda15bcd
add img_norm_cfg to config ( #136 )
2021-04-28 17:56:00 +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
a019058503
fix #51 : revised readme.md for dbnet ( #54 )
...
* fix #51 : revised readme.md for dbnet
* Update configs/textdet/dbnet/README.md
Co-authored-by: jeffreykuang <kuangzhh@gmail.com>
2021-04-13 11:53:57 +08:00
7dc5695d6d
Add methods to readme
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-10 18:04:36 +08:00
3993d77c95
fix iss21: error in crnn inference
2021-04-08 21:45:57 +08:00
0206781bb6
Fix readthedocs generation ( #14 )
...
* Fix readthedocs
* Fix doc
* md format
2021-04-08 15:49:46 +08:00
b1e20d8d39
fix #62 : update panet readme
2021-04-07 12:38:37 +08:00
c88126f0d2
fix #60 : update readme
2021-04-07 10:19:36 +08:00
0b2aa3aec6
fix #55 : update nrtr readme ( #56 )
2021-04-06 14:39:06 +00:00
4958f4df56
fix #39 : update crnn & robustscanner. ( #54 )
2021-04-06 13:53:46 +00:00
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
b64f3906c0
add Dockerfile ( #50 )
2021-04-06 08:46:01 +00:00
5ace2048ea
out_size -> output_size
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-06 13:22:33 +08:00
03720f46c3
fix #35 : add nrtr readme; update nrtr config ( #36 )
2021-04-06 03:14:30 +00:00
0f00378f9a
Feature/iss 33 ( #34 )
...
* fix #33 : update dataset.md
* fix #33 : pytest for transformer related
2021-04-05 23:54:57 +08:00
3b443cf6f9
[feature]: add nrtr ( #28 )
...
* [feature]: add nrtr
* Rename nrtr_top_dataset.py to nrtr_toy_dataset.py
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-04-05 20:19:45 +08:00
cb1b2c2fa6
fix #24 : rm img_meta from inference ( #25 )
2021-04-05 18:01:43 +08:00
a48399aebe
format again
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-05 16:39:31 +08:00
49b52c9d8a
f-str
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-05 16:37:14 +08:00
4f5cde9120
fix #21 : update readme of segocr
2021-04-05 16:34:09 +08:00
3727cab712
fix #21 : update sdmgr readme and config
2021-04-05 16:09:13 +08:00
9af0bed144
fix #21 : refactor kie dataset & add show_results
2021-04-05 16:07:29 +08:00
9d62bdf84c
Format readme ( #23 )
...
* Format readme
Signed-off-by: lizz <lizz@sensetime.com>
* try
Signed-off-by: lizz <lizz@sensetime.com>
* Remove redudant config link
Signed-off-by: lizz <lizz@sensetime.com>
2021-04-05 16:06:06 +08:00
b10bb9eb6a
Enhance/synthtext pretrain ( #20 )
...
* fix 19: add synthtext pretrained model
* fix 19: setup.cfg linting
2021-04-04 21:15:21 +08:00
12df13244d
fix #17 : update ckpt path of psenet ( #18 )
2021-04-04 14:27:37 +08:00
b7dac0f6fd
Merge pull request #7 from jeffreykuang/feature/textdet
...
[feature]: add textdet
2021-04-03 01:07:29 +08:00
31f1c007c0
[feature]: add textdet
2021-04-03 01:03:52 +08:00
50287450ab
Merge pull request #5 from yuexy/feature/crnn_and_robustscanner
...
[feature]: add CRNN and RobustScanner
2021-04-03 00:55:27 +08:00
d594ab122e
[feature]: add CRNN and RobustScanner
2021-04-03 00:52:49 +08:00
b8156a3a77
[feature]: add code for kie and textsnake config
2021-04-03 00:44:12 +08:00
4ecd0cea8a
add sar, seg and other components
2021-04-02 23:54:57 +08:00
Tong Gao
garvan2021
liukuikun
Hongbin Sun
Shouping Shan
LvTianlei
lizz
Zyq-scut
Jianyong Chen
hq_wei
quincylin1
kang sheng
lizz
yuexy
jeffreykuang
YueXy