Kevin Wang
|
37c5d371c7
|
Fix some browse dataset script bugs and draw textdet gt instance with ignore flags (#1701)
* [Enhancement] textdet draw gt instance with ignore flags
* [Fix] 明确key值定义，防止后续使用img_path时得到lmdb格式中的img_key导致图片无法读取
* [Fix] fix five browse_dataset.py script bugs
* [Fix] fix some pr problems
* [Fix] keep img_path attribute
* [Fix] 防止width很大text很小时，font_size过大显示不全（做keep_ratio的resize然后padding到固定尺寸时可能出现此类情况）
|
2023-02-17 15:40:24 +08:00 |
liukuikun
|
1127240108
|
[Feature] Support auto import modules from registry. (#1731)
* [Feature] Support auto import modules from registry.
* limit mmdet version
* location parrent dir if it not exist
|
2023-02-17 10:28:34 +08:00 |
|
liukuikun
|
f820470415
|
[Feature] Rec TTA (#1401)
* Support TTA for recognition
* updata readme
* updata abinet readme
* updata train_test doc for tta
|
2023-02-16 10:27:07 +08:00 |
|
liukuikun
|
7cea6a6419
|
[Enchancement] Only keep meta and state_dict when publish model (#1729)
* Only keep meta and state_dict when publish model
* simpy code
|
2023-02-15 19:45:12 +08:00 |
Ikko Eltociear Ashimine
|
b3be8cfbb3
|
Fix typo in ilst_converter.py (#1711)
* Fix typo in ilst_converter.py
splited -> splitted
* Fix typo in ilst_converter.py
|
2023-02-11 09:09:38 +08:00 |
Xinyu Wang
|
c38618bf51
|
[Feature] Support browse_dataset.py to visualize original dataset (#1503)
* update browse dataset
* enhance browse_dataset
* update docs and fix original mode
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
|
2022-12-16 22:34:23 +08:00 |
Tong Gao
|
c957ded662
|
[Fix] Auto scale lr (#1584)
|
2022-12-01 14:07:10 +08:00 |
|
Tong Gao
|
cfce57ad87
|
[Feature] Add config generator (#1552)
* [Feature] Add config generator
* update icdar2013
* fix ut
* simplify design
* cfg generator
* update
* fix
|
2022-11-21 14:23:20 +08:00 |
DingNing@sanmenxia
|
29107ef81d
|
[Feature] Add print_config.py to the tools (#1547)
* add print_config.py to the tools
* fix bugs
|
2022-11-17 15:35:01 +08:00 |
|
Xinyu Wang
|
8864fa174b
|
[Feature] Add Dataset Preparer (#1484)
* add data preparer
* temporarily ignore data preparer test
* update
* fix comments
* update doc; add script to generate dataset zoo doc
* fix comments; update scripts
* apply comments
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* apply comments
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* coco parser
* fix comments
* add fileio tests
* fix test
* add tests for parsers and dumpers
* add test for data preparer
* fix a bug
* update icdar txt parser
* rename icdar txt parser
* fix comments
* fix test
* fix comments
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
Co-authored-by: liukuikun <641417025@qq.com>
|
2022-11-02 15:06:49 +08:00 |
|
Tong Gao
|
a09437adaa
|
[Fix] Fix offline_eval error caused by new data flow (#1500)
|
2022-10-28 18:56:11 +08:00 |
vansin
|
e7e46771ba
|
[WIP] support get flops and parameters in dev-1.x (#1414)
* [Feature] support get_flops
* [Fix] add the divisor
* [Doc] add the get_flops doc
* [Doc] update the get_flops doc
* [Doc] update get FLOPs doc
* [Fix] delete unnecessary args
* [Fix] delete unnecessary code in get_flops
* [Doc] update get flops doc
* [Fix] remove unnecessary code
* [Doc] add space between Chinese and English
* [Doc] add English doc of get flops
* Update docs/zh_cn/user_guides/useful_tools.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update docs/zh_cn/user_guides/useful_tools.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update docs/en/user_guides/useful_tools.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update docs/en/user_guides/useful_tools.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update docs/en/user_guides/useful_tools.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update docs/en/user_guides/useful_tools.md
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* [Docs] fix the lint
* fix
* fix docs
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
|
2022-10-09 17:47:51 +08:00 |
Qing Jiang
|
b4336204b8
|
[Fix] browse_dataset.py (#1398)
|
2022-09-21 18:56:29 +08:00 |
|
Xinyu Wang
|
ac02c20581
|
[Fix] Update all rec converters (#1284)
* init
* enable non-ascii dump
* fix
* kaist non-ascii
* fix conflicts
* fix
* update
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
|
2022-09-01 13:17:01 +08:00 |
|
Xinyu Wang
|
e72edd6dcb
|
[Docs] Useful Tools (#1349)
* init useful tools
* apply comments
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* update link
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
Co-authored-by: liukuikun <liukuikun@sensetime.com>
|
2022-08-31 15:51:12 +08:00 |
|
liukuikun
|
bf042f8267
|
[Feture] kie visualizer (#1267)
* kie visualizer
* add textspotting visualizer
* Fix
* fix
* Some fixes
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
|
2022-08-29 20:13:06 +08:00 |
|
Tong Gao
|
b32412a9e9
|
[Refactor] MMEngine directory tree (#1317)
|
2022-08-25 11:46:04 +08:00 |
|
Tong Gao
|
b0b6dadc00
|
[Fix] mmcv.utils -> mmengine.utils (#1295)
* [Fix] mmcv.utils -> mmengine.utils
* mmcv -> mmengine
|
2022-08-22 14:13:22 +08:00 |
|
Tong Gao
|
7fcfa09431
|
[Fix] Support customize runner and visualization in train/test.py, an… (#1279)
* [Fix] Support customize runner and visualization in train/test.py, and update configs missing from dataflow refactor
* Fix vis
* Apply suggestions from code review
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
* [Config] Refactor & fix DB, DBPP, DRRG configs (#1181)
* refactor base datasets, fix drrg config
* rename
* update dbnet and drrg
* fix
* fix
* Raise Error
Co-authored-by: Xinyu Wang <45810070+xinke-wang@users.noreply.github.com>
|
2022-08-22 10:48:50 +08:00 |
|
Tong Gao
|
c7a4298c32
|
[Fix] Replace mmcv.fileio with mmengine (#1292)
|
2022-08-19 16:53:14 +08:00 |
|
Tong Gao
|
97f6c1d5d6
|
[Fix] Fix browse_dataset (#1271)
|
2022-08-10 17:48:49 +08:00 |
|
liukuikun
|
37ff38e7aa
|
[Fix] fix base name and dist_xx (#1253)
* fix base name and dist_xx
* update registry
|
2022-08-04 15:25:54 +08:00 |
liukuikun
|
1b33ff5d76
|
[Feat] support fp16 auto resume and auto scale lr
|
2022-07-21 10:58:03 +08:00 |
wangxinyu
|
20e999e3b9
|
[Tools] Update tools dir structure
|
2022-07-21 10:58:02 +08:00 |
|
gaotongxiao
|
eb2d5b525a
|
Migrate part of old_tests
|
2022-07-21 10:57:31 +08:00 |
|
xinyu
|
efd81b7a5a
|
fix bug
|
2022-07-21 10:57:17 +08:00 |
|
liukuikun
|
d50d2a46eb
|
[Processing]remove segocr and split processing
|
2022-07-21 10:57:17 +08:00 |
|
jiangqing.vendor
|
ee1212a5cd
|
[TODO] update recog data_migrator
|
2022-07-21 10:57:17 +08:00 |
|
xinyu
|
23e1f2432a
|
update utils
|
2022-07-21 10:57:16 +08:00 |
|
wangxinyu
|
de78a8839f
|
Remove useless
|
2022-07-21 10:55:46 +08:00 |
|
wangxinyu
|
8313e698d2
|
[Feature] Add offline eval script
|
2022-07-21 10:51:04 +08:00 |
|
xinke-wang
|
24575de140
|
init
|
2022-07-21 10:51:03 +08:00 |
|
gaotongxiao
|
1af7f94a63
|
P3: Update textdet data conversion scripts
|
2022-07-21 10:51:01 +08:00 |
|
jiangqing.vendor
|
8ac235677e
|
[Update] Update data_migrator to suit MJ dataset
|
2022-07-21 10:51:00 +08:00 |
|
jiangqing.vendor
|
22d90301b8
|
[Tool] Add browse_dataset
|
2022-07-21 10:50:59 +08:00 |
|
liukuikun
|
a379d086f1
|
fix some bug
|
2022-07-21 10:50:59 +08:00 |
|
liukuikun
|
fe43259a05
|
[Refactor] train and test
|
2022-07-21 10:50:59 +08:00 |
|
Mountchicken
|
4246b1eaee
|
update
|
2022-07-21 10:50:59 +08:00 |
|
gaotongxiao
|
df2f7b69db
|
Add recognition data migrator
|
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
|
536dfdd4bd
|
Add PyUpgrade pre-commit hook
|
2022-07-21 10:50:56 +08:00 |
|
liukuikun
|
a90b9600ce
|
[Refactor] refactor DATASETS and TRANSFORMS
|
2022-07-21 10:50:55 +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 |
#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 |
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 |
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 |
|
Xinyu Wang
|
13986f497d
|
[Feature] Add ArT (#1006)
* add art
* fix typo
|
2022-05-17 23:59:15 +08:00 |
|
Qing Jiang
|
de2851e3c2
|
[Feature] Add HierText converter (#948)
* loss
* fix
* [feature] add hiertext
* fix name
* update docs
* update
* update markdown
* update doc
* update doc
* update docs
|
2022-05-05 16:31:36 +08:00 |
|
Xinyu Wang
|
b4678eb657
|
[Fix] Fix Data Converter Issues (#955)
* fix naf mask issue; fix lv path issue
* fix path
* fix ic13, ic11 path issue; fix cocotextv2 mask issue
* fix funsd format
|
2022-05-05 14:09:05 +08:00 |
Hongbin Sun
|
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 |