a90b9600ce
[Refactor] refactor DATASETS and TRANSFORMS
2022-07-21 10:50:55 +08:00
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
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
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
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
13986f497d
[Feature] Add ArT ( #1006 )
...
* add art
* fix typo
2022-05-17 23:59:15 +08:00
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
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
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
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
06b73cf71a
[Fix] Fix TotalText Anno version issue ( #945 )
...
* fix tt converter version issue; fix typos in docs
* remove incorrect descriptions
* fix docstring & incorrect file name
* fix docstring identation
2022-04-23 23:57:21 +08:00
9c54e7eb00
[Feature] Add RCTW dataset converter ( #914 )
...
* add rctw
* fix typos
2022-04-18 09:27:18 +08:00
b4a9a87eee
[Enhancement] More customizable fields in dataloaders ( #933 )
...
* [Enhancement] More customizable fields in val and test dataloaders
* update default_loader_cfg
2022-04-18 09:24:07 +08:00
20fc909fc4
[Feature] Add LSVT Data Converter ( #896 )
...
* add lsvt
* fix name
* fix name
* update
* add lsvt
* set default val 0
* fix a bug
* fix typos
* fix file name
* fix lint
* fix lint
2022-04-18 09:15:42 +08:00
3179e4d6bd
[Feature] Add analyze_logs in tools and its description in docs ( #899 )
...
* Create analyze_logs.py
* Update tools.md
* fix lint and typo
* Update analyze_logs.py
* Add arg table and demo log file
* Delete line66 for lint error
* fix captial letters
* update doc
* fix markdown indentation
* Add log_analysis_demo.png to demo/resources
* Add log_analysis_demo.png and two links in table
* Improve epoch-based metric
* fix lint error
* fix lint error(tabs and spaces)
* check code lints and format
Co-authored-by: Mountchicken <mountchicken@outlook.com>
Co-authored-by: xinke-wang <wangxinyu2017@gmail.com>
2022-04-02 22:40:39 +08:00
4c57bd35ac
[Docs] Fix the misleading description in test.py ( #908 )
...
* [Docs] Fix misleading description in test.py
* update docs
2022-04-02 11:31:48 +08:00
bea8587f3f
[Feature] Add ReCTS Data Converter ( #892 )
2022-03-30 15:24:37 +08:00
6ef3ecd300
[Feature] Add COCO Text v2 Data Converter ( #872 )
2022-03-30 15:22:53 +08:00
ec7b8420bf
[Feature] Add MTWI Data Converter ( #867 )
2022-03-30 15:18:04 +08:00
4ab411e84c
[Feature] Add Vintext Converter ( #864 )
2022-03-30 15:16:04 +08:00
a682ca5dfd
[Feature] Add BID Converter ( #862 )
...
* newdataset
* d
* add docs
* fix bugs and docs
* fix bugs
* fix docs and add annotation format in load_txt_file
* fix funsd
* change _ to -
* update doc and and add ignores to store verticle instances
* update doc
* using crops instead of dst_imgs
* replace test with val
* fix docstring
* fix doc
* update doc
* fix padding size
* update doc
* update doc
* update tree structure
* add - before after
* add optional
* add tab before bash
* set val-ratio to 0.
* fix docstring
* fix lint
* revert docs
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-03-30 15:14:44 +08:00
7a8cf99524
[Feature] Add IC13 (Focused Scene Text) Data Converter ( #861 )
...
* add ic13 data converter
* fix extension
* add docs
* fix doc
* fix doc
* update docs
* move directory tree
* fix indentation
* revert docs
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-03-30 15:13:29 +08:00
692425e79d
[Feature] Add IC11 (Born-digital Images) Data Converter ( #857 )
...
* add IC11 (born-digital images) converter
* fix
* fix format
* add docs; fix format;
* fix doc
* doc string
* fix docs
* move directory tree
* fix indentation
* revert docs
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-03-30 15:12:40 +08:00
347a8090e2
[Feature] Add KAIST Converter ( #835 )
...
* add KAIST converter
* support jsonl; save filtered imgs to ignores
* add docs
* fix doc; add annotation format docstring; fix jsonl ascii
* fix docstring
* update doc for preserve vertical
* fix doc
* move directory tree
* move directory tree
* fix indentation
* set default val to 0
* im -> img
* fix det val default rate
* revert docs
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-03-30 15:11:04 +08:00
e780563ed7
[Feature] Add ILST Converter ( #833 )
...
* [Feature] Add ILST Converter
* [fix] typo
* add docs and remove latin
* add docs and remove latin
* fix bug
* fix bugs and docs
* fix bugs
* add annotation format in load_xml_file and change test_ratio to val_ratio
* bug fix
* fix docstring
* chane _ to -
* add ignores to store filtered vertical instances
* update doc
* update doc
* using crops instead of dst_imgs
* fix typos and remove test with val
* fix docstring
* update doc
* fix padding size
* update doc
* simplify bash
* update doc
* update doc
* remove tree
* update tree structure
* add - before after
* add optional
* add tab before bash
* set val-ratio to 0.
* Update docs/en/datasets/det.md
* fix lint
* fix lint
* revert docs
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-03-30 15:09:39 +08:00
b68afca2d4
[Feature] Add IMGUR Converter ( #825 )
...
* add IMGUR converter
* fix typo
* support jsonl; update docs
* fix recog doc overview
* move directory tree
* fix indentation
* revert docs
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-03-30 15:07:55 +08:00
ee2c3cfd46
[Feature] Add DeText Converter ( #818 )
...
* add DeText Converter
* Update tools/data/textrecog/detext_converter.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* update doc; support jsonl; fix docstrings
* update mkdir func
* fix bug
* update doc; do not filter for test val
* move directory tree
* fix indentation
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-03-30 14:43:33 +08:00
8b928cb500
[Feature] Add NAF Converter ( #815 )
...
* NAF dataset downloading command
* add NAF converter
* revert incorrect url revision
* fix typo
* support jsonl; save filtered crops; add data description in docstring; update ddoc
* remove preserve-symbol; update docs; fix special symbol filter
* move tree structure
* fix indentation
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2022-03-30 14:31:47 +08:00
bdd32c8052
[Feature] Add SROIE Converter ( #810 )
...
* add SROIE converter
* add sroie converter
* fix docstring indentation
* fix lint
* remove val split; add test split
* delete google drive timestamp
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* remove timestamp
* update docs; support jsonl; fix crop
* move tree structure
* move tree structure
* move directory tree
* fix indentation
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-03-30 13:14:23 +08:00
958e4a3e87
[Feature] Add LV Dataset Converter ( #871 )
...
* add LV converter
* add docs
* add recog converter; update doc
2022-03-29 11:50:27 +08:00
b37b1d05dd
[Fix] Use hyphen instead of underscores in script args ( #890 )
2022-03-29 10:28:38 +08:00
af9fd77980
[Fix] description in tools/data/utils/txt2lmdb.py ( #870 )
...
* loss
* fix
* fix
2022-03-23 17:30:33 +08:00
838aa47f9f
[Feature] Add args and docs for multi-machine training/testing ( #849 )
...
* add args and docs for multi-machine training/testing
* update docs
* update docs
* update docs
* update docs
* revert commit
2022-03-22 16:25:39 +08:00
680dff373e
[Feature] Support jsonl in recognition converter ( #844 )
2022-03-18 09:22:32 +08:00
c25404b358
[Enhancement] Option for different seeds on different ranks ( #820 )
2022-03-10 10:43:36 +08:00
14c75da7bd
[Feature] Add FUNSD Converter ( #808 )
...
* Add FUNSD Converter
* Update tools/data/textrecog/funsd_converter.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update tools/data/textrecog/funsd_converter.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update tools/data/textdet/funsd_converter.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* blank line between sections
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* fix incorrect docstrings
* fix docstrings & fix timer
* add --preserve-vertical arg for preserving vertical texts
* fix --preserve-vertical
* [doc] fix recog.md incorrect description
* fix docstring style
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* fix docstring spaces
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-03-04 12:25:54 +08:00
ac4462f374
[Feature] Add CurvedSyntext150k Converter ( #719 )
...
* [Feature] Add bezier_to_polygon to box_util
* Add num_sample to parameter
* add sort_point util
* update docstring
* Add curvedsyntext converter
2022-03-02 11:02:14 +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
b7a4eac65f
[Enhancement] Add deprecation message for deploy tools ( #801 )
...
* Add deprecation message for deploy tools
* move wwarning info to start
2022-02-28 16:22:47 +08:00
91f98bc645
[Enhancement] Add open-mmlab precommit hook ( #787 )
2022-02-22 12:52:04 +08:00
c466e6f82d
[Enhancement] Upgrade isort ( #771 )
...
* [Enhancement] Upgrade isort
* Fix files
2022-02-09 23:22:14 +08:00
b054f609b4
[Enhancement] Remove unnecessary custom_import from test.py ( #758 )
2022-01-27 11:02:16 +08:00
e0ff11819b
[Feat] Support specify gpu for testing and training with gpu-id instead of gpu-ids and gpus ( #756 )
...
* support set gpu number for testing and deprecate gpu_ids and gpus with gpu_id
* update gpu-ids gpus and gpu-id dostring
* add args.gpus process
* fix typo
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-01-27 10:11:14 +08:00
d871eed79e
[Enhancement] Add setup multi-processing both in train and test. ( #757 )
2022-01-26 20:34:19 +08:00
218f9f08d4
[Fix] Use yaml.safe_load instead of load ( #753 )
2022-01-26 14:29:30 +08:00
ad3957bb41
[Enhancement] Speed up training ( #739 )
2022-01-19 20:14:41 +08:00
2f429d5e40
Extend totaltext converter to support text fields ( #728 )
...
* Extend totaltext converter to support text fieldols/
* fix bug
* fix comment typo
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2022-01-14 16:00:53 +08:00
c736989615
[Feature] Extend ctw1500 converter to support text fields ( #729 )
...
* Extend ctw1500 converter to support text fieldols/
* remove args for debug
2022-01-14 15:30:48 +08:00
8c5e8c240e
[Enhancement] Disable multi-processing feature of cv2 to speed up data loading ( #721 )
2022-01-11 12:52:19 +08:00
96beda6f2d
[Docs] Add config tutorial ( #683 )
...
* Add config tutorial and reorganize dataset_type.md
* update cn docs toc
* Add misc tool
* Improve docs api menu and config docs
2021-12-28 12:41:24 +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
abbae7bfd1
fix sartrn onnxruntime test ( #679 )
...
* fix satrn test
* disable aug test for deployment test
2021-12-21 13:52:11 +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
bdbeb69076
[Fix] Remove depreciated image sanity check ( #661 )
2021-12-10 12:50:41 +08:00
1544e9bb29
[Enhancement] Remove unnecessary custom_import from train.py ( #603 )
2021-11-25 15:59:35 +08:00
e267d06281
[Fix] Always broadcast a random seed to all the processes ( #600 )
2021-11-18 22:26:21 +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
4870ca91fc
[Fix] Fix resource warning: unclosed file ( #577 )
...
* fix resource warning: unclosed file
* fix import
* Eliminate det_test_img's dependency on mmdet
Co-authored-by: gaotongxiao <gaotongxiao@gmail.com>
2021-11-12 12:36:57 +08:00
cae080734f
fix recog_test_imgs ( #574 )
2021-11-11 17:39:54 +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
80741e1479
[Feature] Add converter for the Open Images v5 text annotations by Krylov et al. ( #497 )
...
* Add converter for the OpenVINO annotations for Open Images by Krylov et al.
Open Images V5 Text Annotation and Yet Another Mask Text Spotter
Paper: https://arxiv.org/abs/2106.12326
* docs fix & add chinese docs
2021-10-28 16:49:36 +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
027cb7aac5
[Docs] TorchServe docs ( #539 )
...
* Add torchserve docs
* polish contents and fix the visiualization bug in torchserve testing
* polish content
2021-10-22 16:49:28 +08:00
5671939bbc
[Fix] fix converting to onnx bug because of changing key from img_shape to resize_shape ( #523 )
...
* fix pytorch to onnx for mmocr0.3.0
* fix pytorch to onnx for mmocr0.3.0
* modify deployment doc and fix scale_factor bug and test psenet and panet
* fix trt part
* init detector with **(cfg.model)
Co-authored-by: AllentDan <AllentDan@yeah.net>
2021-10-20 19:55:57 +08:00
75d32504e0
[Feature] Add codespell pre-commit hook and fix typos ( #520 )
...
* add spellcheck hook
* fix typos
2021-10-13 22:56:11 +08:00
7d36a7e882
[Feature] Add torchserve support for text detection and recognition ( #522 )
...
* add torchserve
* add test torchserve
* delete unused postprocess and delete parse_results
* fix bug
* fix bug
* fix bug
* Update tools/deployment/test_torchserve.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
* Update tools/deployment/mmocr_handler.py
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
Co-authored-by: Tong Gao <gaotongxiao@gmail.com>
2021-10-13 22:21:16 +08:00
f72012092f
[Docs] Enhancement & sync Chinese docs ( #492 )
...
* reorder navigation links, add links to twitter and zhihu
* update chinese docs
2021-09-28 11:32:44 +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
cc0d4d32fd
[Feature] Support Chinese for kie show result ( #464 )
...
* support Chinese for kie show result
* update visualize
* add arg for draw_texts
* update font_size
2021-08-30 16:45:43 +08:00
961fbb6ca5
[Feature] Support persistent_workers option in data loader ( #459 )
...
* Support persistent_workers option in data loader
Signed-off-by: lizz <lizz@sensetime.com>
* Update test.py
* yapf bug
Signed-off-by: lizz <lizz@sensetime.com>
2021-08-25 13:12:53 +08:00
d683b14283
[Fix] Totaltext_converter: skip invalid annotations ( #438 )
...
* [Fix] Skip invalid annoataions
2021-08-20 11:23:05 +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
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
532e8f808d
Fix #416 : Fix undesired assignment to "pretrained" in test.py ( #418 )
...
* fix ocr linting
* fix undesired assignment to pretrained key
2021-08-10 14:07:41 +00:00
969c65165f
[Fix] Remove depreciated pretrained in kie_test_imgs ( #381 )
2021-07-21 15:18:59 +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
02e3b98684
fix syntext_converter ( #361 )
2021-07-12 02:07:50 +00:00
243f47dc03
add totaltext for recog and det ( #357 )
...
* add totaltext for recog and det
* add setup
* fix doc
* fix based on comments
2021-07-08 21:52:50 +08:00
68df4fbe80
[Feature] Add synthtext converter and update docs ( #351 )
...
* Add synthtext converter and update docs
* minor docs fix
2021-07-07 15:54:29 +08:00
19aefa1ae1
Added support for ConcatDataset with two workflows ( #348 )
2021-07-06 16:37:37 +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
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
e6cb750922
add TextOCR dataset converter ( #293 )
...
* textocr converter for text recog
* textocr converter for text detection
* update documentation
* remove unnecessary garbage collection lines
* multi-processing textocr converter
* json->mmcv, fix documentation
2021-06-21 03:06:10 +00:00
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
87a7dcee0a
fix #279 : save detect results ( #281 )
...
* fix #279 : save detect results
* rename
* set device as arg
* rm bash file
2021-06-15 18:30:09 +08:00
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
d7fa9544e6
added totaltext recog converter ( #273 )
...
* added totaltext recog converter
* modified datasets.md and totaltext_converter.py
* added Note to datasets.md
* deleted comments
2021-06-11 11:09:35 +08:00
bb4447585f
Add benchmark_processing script ( #261 )
...
* Flush data script
Signed-off-by: lizz <lizz@sensetime.com>
* Update tools/run_data.py
Co-authored-by: jeffreykuang <kuangzhanghui@sensetime.com>
* Update tools/run_data.py
Co-authored-by: jeffreykuang <kuangzhanghui@sensetime.com>
* Update tools/run_data.py
Co-authored-by: jeffreykuang <kuangzhanghui@sensetime.com>
* rename to benchmark_processing
Signed-off-by: lizz <lizz@sensetime.com>
Co-authored-by: jeffreykuang <kuangzhanghui@sensetime.com>
2021-06-09 17:38:53 +08:00
271129f812
Feature/iss 262 ( #266 )
...
* fix issue#262
* fix #262 : modified totaltext_converter and added totaltext for datasets.md
* fix issue#262: modified datasets.md
* fix issue#262: removed download json
* Update totaltext_converter.py
Co-authored-by: Hongbin Sun <hongbin306@gmail.com>
2021-06-08 13:13:22 +00:00
4882c8a317
dataset preparation docs ( #255 )
2021-06-01 21:59:40 +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
e0e0e648fd
Support cpu in kie visulization ( #215 )
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-18 21:48:16 +08:00
491866ea27
Make tools executable ( #209 )
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-18 15:19:08 +08:00
06b75780a0
Fix typos ( #207 )
...
Signed-off-by: lizz <lizz@sensetime.com>
2021-05-18 05:44:52 +00:00
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
liukuikun
leezeeyee
#W[_t
rpb
xiefeifeihu
Xinyu Wang
Qing Jiang
Hongbin Sun
Tong Gao
Y-M-Y
liukuikun
AllentDan
Darwin Bautista
liukuikun
lizz
quincylin1
Antonio Lanza
hq_wei