liukuikun
6fe4ee82f2
[Refactor] text detection and text recognition dataset
2022-07-21 10:50:57 +08:00
gaotongxiao
98d9d39505
Migrate configs to new styles
2022-07-21 10:50:57 +08:00
gaotongxiao
cb85f857aa
Add BaseTextDetPostProcessor
2022-07-21 10:50:57 +08:00
gaotongxiao
6a260514e8
Add coco data migrator for detection
2022-07-21 10:50:57 +08:00
gaotongxiao
2c23098b29
Refactor SingleStageTextDetector and update model classes
2022-07-21 10:50:57 +08:00
gaotongxiao
26da038d49
Add BaseTextDetHead
2022-07-21 10:50:57 +08:00
gaotongxiao
9c3d741712
[CI] Run pytest in diff_coverage_test.sh
2022-07-21 10:50:56 +08:00
gaotongxiao
f0c6d44ce8
Add dump_ocr_data
2022-07-21 10:50:56 +08:00
liukuikun
98bc90bd1c
[Feature] TextRecogSample
2022-07-21 10:50:56 +08:00
liukuikun
c920edfb3a
[Refactor] split labelconverter to Dictionary
2022-07-21 10:50:56 +08:00
liukuikun
c47c5711c1
[Feature] TextDetSample
2022-07-21 10:50:56 +08:00
xinke-wang
f7cea9d40f
add docstring
2022-07-21 10:50:56 +08:00
gaotongxiao
6f3aed95a6
[CI] Force py files being added/modified to meet our UT and docstr coverage requirements
2022-07-21 10:50:56 +08:00
xinke-wang
b5c5ddd3e0
update docstring
2022-07-21 10:50:56 +08:00
gaotongxiao
536dfdd4bd
Add PyUpgrade pre-commit hook
2022-07-21 10:50:56 +08:00
gaotongxiao
593d7529a3
Revert "[CI] Force py files being added/modified to meet our UT and docstr coverage requirements"
...
This reverts commit 2b5c32704f5898c9fa488b5fc48116cad1c66217
2022-07-21 10:50:56 +08:00
gaotongxiao
d98648c06f
[CI] Force py files being added/modified to meet our UT and docstr coverage requirements
2022-07-21 10:50:56 +08:00
wangxinyu.vendor
41c1671e7b
Refactor PyramidRescale
2022-07-21 10:50:56 +08:00
liukuikun
23458f8a47
[Refactor] union to MODELS
2022-07-21 10:50:56 +08:00
gaotongxiao
3f24e34a5d
remove some deprecated files causing import errors
2022-07-21 10:50:56 +08:00
liukuikun
13bd2837ae
refactor MODELS
2022-07-21 10:50:56 +08:00
liukuikun
a90b9600ce
[Refactor] refactor DATASETS and TRANSFORMS
2022-07-21 10:50:55 +08:00
gaotongxiao
b5fc589320
Add CI
2022-07-21 10:50:55 +08:00
liukuikun
324b7e4e80
add registy file and inherit all registy
2022-07-21 10:50:55 +08:00
gaotongxiao
69e6c80558
move tests to old_tests, add empty test folders
2022-07-21 10:50:55 +08:00
~akA,4}3(V
73222b270c
[Fix] Update lmdb_converter and ct80 cropped image source in document ( #1164 )
...
* fix #1088 : replace txt2lmdb.py with lmdb_converter.py in eng doc
* fix #536 : add ct80 cropped image source
* update ct80 link
update ct80 link to permanent link
2022-07-20 19:25:39 +08:00
Tong Gao
107e9d2f48
[Docs] Limit markdown version ( #1172 )
2022-07-20 19:24:17 +08:00
Jaylin Lee
1755dad193
[Fix] Fixed docstring syntax error of line 19 & 21 ( #1157 )
...
* Fixed docstring syntax error of lineno 19 & 21
* pre-commit
2022-07-16 21:33:09 +08:00
leezeeyee
4c1790b3c6
[Fix] fix typo of --lmdb-map-size default value ( #1147 )
...
* fix typo of --lmdb-map-size default value
* fix
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-07-16 21:32:15 +08:00
Qing Jiang
5657be1e1a
[Fix] Fix a bug in LmdbAnnFileBackend that cause breaking in Synthtext detection training ( #1159 )
...
* loss
* fix
* 'update'
* 'update'
2022-07-15 20:37:39 +08:00
#W[_t
1bd26f24ba
[Fix]: access params by cfg.get ( #1145 )
...
cfg.get is better way to access the params when it may not exist.
2022-07-11 19:04:05 +08:00
Nidham Tekaya
688d72fdc4
[Fix] links update ( #1141 )
...
* links update
* fix typing
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-07-08 10:42:22 +08:00
Amit Agarwal
c4a2fa5eee
[Fix] Updating edge-embeddings after each GNN layer ( #1134 )
2022-07-06 19:37:28 +08:00
rpb
7800e13fc2
[Fix] Flexible ways of getting file name ( #1107 )
...
* Flexible ways of getting file name
Address issue https://github.com/open-mmlab/mmocr/issues/1078
* fix lint
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-07-04 11:39:58 +08:00
Tong Gao
64fb6fffc0
[Fix] Metafile ( #1121 )
2022-06-28 14:22:37 +08:00
Mingyu Liu
9bdc247c0c
[Fix] Update ST_SA_MJ_train.py ( #1117 )
...
Fix a bug that results train3's parameter covering the train1 and train2
2022-06-28 14:20:21 +08:00
Yewen Zhou
fe64040581
[Fix] #1098 : normalize text recognition scores ( #1119 )
2022-06-28 14:19:19 +08:00
Qing Jiang
72a79f9350
[Fix] Fix dataset configs ( #1106 )
...
* loss
* fix
* [update] fix configs
* fix lint
2022-06-23 21:52:11 +08:00
xiefeifeihu
1f888c9e97
[Fix] Incorrect filename in labelme_converter.py ( #1103 )
...
filename value is "img_path_warpped_img" not "img_path_cropped_img" in line 120.
2022-06-22 22:05:45 +08:00
Tong Gao
d669ce2e82
[Fix] typo in setup.py ( #1095 )
2022-06-21 17:40:47 +08:00
Tong Gao
4f36bcd1aa
[CI] Remove reduntant steps ( #1091 )
2022-06-21 10:34:25 +08:00
Tong Gao
b78f5b3b26
[Enhancement] Test mim in CI ( #1090 )
2022-06-21 10:34:12 +08:00
Yewen Zhou
d068370b85
[Fix] fix #1067 : Add torchserve DockerFile and fix bugs ( #1073 )
2022-06-15 15:58:40 +08:00
Tong Gao
b1ab4c7c33
[Fix] Restrict the minimum version of OpenCV to avoid potential vulnerabity ( #1065 )
2022-06-13 23:36:33 +08:00
Max Bachmann
7c5c784a94
[Enhancement] Simplify normalized edit distance calculation ( #1060 )
...
* simplify normalized edit distance calculation
* update rapidfuzz minimum version
2022-06-10 10:16:17 +08:00
Tong Gao
d3f65aaacf
[Enhancement] Add mim to extras_requrie to setup.py, update mminstall… ( #1062 )
...
* [Enhancement] Add mim to extras_requrie to setup.py, update mminstall.txt
* update
2022-06-09 15:09:16 +08:00
Tong Gao
12558969ee
[Fix] Relax OpenCV requirement ( #1061 )
...
* update opencv req
* fix
2022-06-09 14:59:12 +08:00
liukuikun
e1e26d3f74
[Enchance] add codespell ignore and use mdformat ( #1022 )
...
* update
* update contributing
* update ci
* fix md
* update pre-commit hook
* update mdformat
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-06-09 14:58:44 +08:00
Abdelrahman Ahmad
9d7818b564
[Enhancement] Add ABINet_Vision api ( #1041 )
...
* add ABINet_Vision api
* revert change
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-06-09 11:47:09 +08:00
Tong Gao
376fe05e6c
[Docs] Update readme according to the guideline ( #1047 )
...
* [Docs] Update readme according to the guideline
* fix
* fix cn links
2022-06-01 10:24:07 +08:00