From fa4fd1fd426fd037f45cbd5c43ea6e3398cf5595 Mon Sep 17 00:00:00 2001 From: Tong Gao Date: Tue, 6 Dec 2022 14:01:39 +0800 Subject: [PATCH] [Enhancement] Update textrecog config and readme (#1597) * [Dataset Preparer] Add TextSpottingConfigGenerator * update init * [Enhancement] Update textrecog configs and raedme * cfg * fix --- configs/textrecog/_base_/datasets/cute80.py | 4 ++-- configs/textrecog/_base_/datasets/icdar2013.py | 14 ++++++++++---- configs/textrecog/_base_/datasets/icdar2015.py | 14 ++++++++++---- configs/textrecog/_base_/datasets/iiit5k.py | 7 +++---- configs/textrecog/_base_/datasets/svt.py | 10 ++++++++-- configs/textrecog/_base_/datasets/svtp.py | 10 ++++++++-- configs/textrecog/abinet/README.md | 10 +++++----- configs/textrecog/crnn/README.md | 8 ++++---- configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py | 2 -- configs/textrecog/master/README.md | 8 ++++---- configs/textrecog/nrtr/README.md | 12 ++++++------ configs/textrecog/robust_scanner/README.md | 8 ++++---- configs/textrecog/sar/README.md | 10 +++++----- configs/textrecog/satrn/README.md | 10 +++++----- 14 files changed, 74 insertions(+), 53 deletions(-) diff --git a/configs/textrecog/_base_/datasets/cute80.py b/configs/textrecog/_base_/datasets/cute80.py index 5b06964c..9d96e36f 100644 --- a/configs/textrecog/_base_/datasets/cute80.py +++ b/configs/textrecog/_base_/datasets/cute80.py @@ -1,8 +1,8 @@ -cute80_textrecog_data_root = 'data/rec/ct80/' +cute80_textrecog_data_root = 'data/cute80' cute80_textrecog_test = dict( type='OCRDataset', data_root=cute80_textrecog_data_root, - ann_file='test_labels.json', + ann_file='textrecog_test.json', test_mode=True, pipeline=None) diff --git a/configs/textrecog/_base_/datasets/icdar2013.py b/configs/textrecog/_base_/datasets/icdar2013.py index ea740887..e002b328 100644 --- a/configs/textrecog/_base_/datasets/icdar2013.py +++ b/configs/textrecog/_base_/datasets/icdar2013.py @@ -1,15 +1,21 @@ -icdar2013_textrecog_data_root = 'data/rec/icdar_2013/' +icdar2013_textrecog_data_root = 'data/icdar2013' icdar2013_textrecog_train = dict( type='OCRDataset', data_root=icdar2013_textrecog_data_root, - ann_file='train_labels.json', - test_mode=False, + ann_file='textrecog_train.json', pipeline=None) icdar2013_textrecog_test = dict( type='OCRDataset', data_root=icdar2013_textrecog_data_root, - ann_file='test_labels.json', + ann_file='textrecog_test.json', + test_mode=True, + pipeline=None) + +icdar2013_857_textrecog_test = dict( + type='OCRDataset', + data_root=icdar2013_textrecog_data_root, + ann_file='textrecog_test_857.json', test_mode=True, pipeline=None) diff --git a/configs/textrecog/_base_/datasets/icdar2015.py b/configs/textrecog/_base_/datasets/icdar2015.py index d139181b..d1268ceb 100644 --- a/configs/textrecog/_base_/datasets/icdar2015.py +++ b/configs/textrecog/_base_/datasets/icdar2015.py @@ -1,15 +1,21 @@ -icdar2015_textrecog_data_root = 'data/rec/icdar_2015/' +icdar2015_textrecog_data_root = 'data/icdar2015' icdar2015_textrecog_train = dict( type='OCRDataset', data_root=icdar2015_textrecog_data_root, - ann_file='train_labels.json', - test_mode=False, + ann_file='textrecog_train.json', pipeline=None) icdar2015_textrecog_test = dict( type='OCRDataset', data_root=icdar2015_textrecog_data_root, - ann_file='test_labels.json', + ann_file='textrecog_test.json', + test_mode=True, + pipeline=None) + +icdar2015_1811_textrecog_test = dict( + type='OCRDataset', + data_root=icdar2015_textrecog_data_root, + ann_file='textrecog_test_1811.json', test_mode=True, pipeline=None) diff --git a/configs/textrecog/_base_/datasets/iiit5k.py b/configs/textrecog/_base_/datasets/iiit5k.py index ad52c807..f1ef085e 100644 --- a/configs/textrecog/_base_/datasets/iiit5k.py +++ b/configs/textrecog/_base_/datasets/iiit5k.py @@ -1,15 +1,14 @@ -iiit5k_textrecog_data_root = 'data/rec/IIIT5K/' +iiit5k_textrecog_data_root = 'data/iiit5k' iiit5k_textrecog_train = dict( type='OCRDataset', data_root=iiit5k_textrecog_data_root, - ann_file='train_labels.json', - test_mode=False, + ann_file='textrecog_train.json', pipeline=None) iiit5k_textrecog_test = dict( type='OCRDataset', data_root=iiit5k_textrecog_data_root, - ann_file='test_labels.json', + ann_file='textrecog_test.json', test_mode=True, pipeline=None) diff --git a/configs/textrecog/_base_/datasets/svt.py b/configs/textrecog/_base_/datasets/svt.py index 14f1aaf4..259b9edd 100644 --- a/configs/textrecog/_base_/datasets/svt.py +++ b/configs/textrecog/_base_/datasets/svt.py @@ -1,8 +1,14 @@ -svt_textrecog_data_root = 'data/rec/svt/' +svt_textrecog_data_root = 'data/svt' + +svt_textrecog_train = dict( + type='OCRDataset', + data_root=svt_textrecog_data_root, + ann_file='textrecog_train.json', + pipeline=None) svt_textrecog_test = dict( type='OCRDataset', data_root=svt_textrecog_data_root, - ann_file='test_labels.json', + ann_file='textrecog_test.json', test_mode=True, pipeline=None) diff --git a/configs/textrecog/_base_/datasets/svtp.py b/configs/textrecog/_base_/datasets/svtp.py index 3a3aaa4c..a917beaf 100644 --- a/configs/textrecog/_base_/datasets/svtp.py +++ b/configs/textrecog/_base_/datasets/svtp.py @@ -1,8 +1,14 @@ -svtp_textrecog_data_root = 'data/rec/svtp/' +svtp_textrecog_data_root = 'data/svtp' + +svtp_textrecog_train = dict( + type='OCRDataset', + data_root=svtp_textrecog_data_root, + ann_file='textrecog_train.json', + pipeline=None) svtp_textrecog_test = dict( type='OCRDataset', data_root=svtp_textrecog_data_root, - ann_file='test_labels.json', + ann_file='textrecog_test.json', test_mode=True, pipeline=None) diff --git a/configs/textrecog/abinet/README.md b/configs/textrecog/abinet/README.md index 3959ebd5..8920c0f3 100644 --- a/configs/textrecog/abinet/README.md +++ b/configs/textrecog/abinet/README.md @@ -34,11 +34,11 @@ Linguistic knowledge is of great benefit to scene text recognition. However, how ## Results and models -| methods | pretrained | | Regular Text | | | Irregular Text | | download | -| :----------------------------------------------: | :--------------------------------------------------: | :----: | :----------: | :----: | :----: | :------------: | :----: | :------------------------------------------------- | -| | | IIIT5K | SVT | IC13 | IC15 | SVTP | CT80 | | -| [ABINet-Vision](/configs/textrecog/abinet/abinet-vision_20e_st-an_mj.py) | - | 0.9523 | 0.9057 | 0.9369 | 0.7886 | 0.8403 | 0.8437 | [model](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet-vision_20e_st-an_mj/abinet-vision_20e_st-an_mj_20220915_152445-85cfb03d.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet-vision_20e_st-an_mj/20220915_152445.log) | -| [ABINet](/configs/textrecog/abinet/abinet_20e_st-an_mj.py) | [Pretrained](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_pretrain-45deac15.pth) | 0.9603 | 0.9382 | 0.9547 | 0.8122 | 0.8868 | 0.8785 | [model](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_20e_st-an_mj/abinet_20e_st-an_mj_20221005_012617-ead8c139.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_20e_st-an_mj/20221005_012617.log) | +| methods | pretrained | | Regular Text | | | Irregular Text | | download | +| :--------------------------------------------: | :------------------------------------------------: | :----: | :----------: | :-------: | :-------: | :------------: | :----: | :----------------------------------------------- | +| | | IIIT5K | SVT | IC13-1015 | IC15-2077 | SVTP | CT80 | | +| [ABINet-Vision](/configs/textrecog/abinet/abinet-vision_20e_st-an_mj.py) | - | 0.9523 | 0.9196 | 0.9369 | 0.7896 | 0.8403 | 0.8437 | [model](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet-vision_20e_st-an_mj/abinet-vision_20e_st-an_mj_20220915_152445-85cfb03d.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet-vision_20e_st-an_mj/20220915_152445.log) | +| [ABINet](/configs/textrecog/abinet/abinet_20e_st-an_mj.py) | [Pretrained](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_pretrain-45deac15.pth) | 0.9603 | 0.9397 | 0.9557 | 0.8146 | 0.8868 | 0.8785 | [model](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_20e_st-an_mj/abinet_20e_st-an_mj_20221005_012617-ead8c139.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/abinet/abinet_20e_st-an_mj/20221005_012617.log) | ```{note} 1. ABINet allows its encoder to run and be trained without decoder and fuser. Its encoder is designed to recognize texts as a stand-alone model and therefore can work as an independent text recognizer. We release it as ABINet-Vision. diff --git a/configs/textrecog/crnn/README.md b/configs/textrecog/crnn/README.md index aa0f2561..0482c9fd 100644 --- a/configs/textrecog/crnn/README.md +++ b/configs/textrecog/crnn/README.md @@ -33,10 +33,10 @@ Image-based sequence recognition has been a long-standing research topic in comp ## Results and models -| methods | | Regular Text | | | | Irregular Text | | download | -| :----------------------------------------------------: | :----: | :----------: | :----: | :-: | :----: | :------------: | :----: | :-------------------------------------------------------------------------------------------: | -| methods | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | | -| [CRNN](/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py) | 0.8053 | 0.8053 | 0.8739 | | 0.5556 | 0.6093 | 0.5694 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/crnn_mini-vgg_5e_mj_20220826_224120-8afbedbb.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/20220826_224120.log) | +| methods | | Regular Text | | | | Irregular Text | | download | +| :----------------------------------------------------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :-------------------------------------------------------------------------------------: | +| methods | IIIT5K | SVT | IC13-1015 | | IC15-2077 | SVTP | CT80 | | +| [CRNN](/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py) | 0.8053 | 0.7991 | 0.8739 | | 0.5571 | 0.6093 | 0.5694 | [model](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/crnn_mini-vgg_5e_mj_20220826_224120-8afbedbb.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_mini-vgg_5e_mj/20220826_224120.log) | ## Citation diff --git a/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py b/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py index 4e8665a5..5dffa009 100644 --- a/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py +++ b/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py @@ -11,7 +11,6 @@ _base_ = [ '../_base_/schedules/schedule_adadelta_5e.py', '_base_crnn_mini-vgg.py', ] - # dataset settings train_list = [_base_.mjsynth_textrecog_test] test_list = [ @@ -21,7 +20,6 @@ test_list = [ ] default_hooks = dict(logger=dict(type='LoggerHook', interval=50), ) - train_dataloader = dict( batch_size=64, num_workers=24, diff --git a/configs/textrecog/master/README.md b/configs/textrecog/master/README.md index db2bd680..39b388ae 100644 --- a/configs/textrecog/master/README.md +++ b/configs/textrecog/master/README.md @@ -35,10 +35,10 @@ Attention-based scene text recognizers have gained huge success, which leverages ## Results and Models -| Methods | Backbone | | Regular Text | | | | Irregular Text | | download | -| :----------------------------------------------------------------: | :-----------: | :----: | :----------: | :----: | :-: | :----: | :------------: | :----: | :------------------------------------------------------------------: | -| | | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | | -| [MASTER](/configs/textrecog/master/master_resnet31_12e_st_mj_sa.py) | R31-GCAModule | 0.9490 | 0.8967 | 0.9517 | | 0.7631 | 0.8465 | 0.8854 | [model](https://download.openmmlab.com/mmocr/textrecog/master/master_resnet31_12e_st_mj_sa/master_resnet31_12e_st_mj_sa_20220915_152443-f4a5cabc.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/master/master_resnet31_12e_st_mj_sa/20220915_152443.log) | +| Methods | Backbone | | Regular Text | | | | Irregular Text | | download | +| :-------------------------------------------------------------: | :-----------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :---------------------------------------------------------------: | +| | | IIIT5K | SVT | IC13-1015 | | IC15-2077 | SVTP | CT80 | | +| [MASTER](/configs/textrecog/master/master_resnet31_12e_st_mj_sa.py) | R31-GCAModule | 0.9490 | 0.8887 | 0.9517 | | 0.7650 | 0.8465 | 0.8889 | [model](https://download.openmmlab.com/mmocr/textrecog/master/master_resnet31_12e_st_mj_sa/master_resnet31_12e_st_mj_sa_20220915_152443-f4a5cabc.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/master/master_resnet31_12e_st_mj_sa/20220915_152443.log) | ## Citation diff --git a/configs/textrecog/nrtr/README.md b/configs/textrecog/nrtr/README.md index 86bfe04e..300e4a40 100644 --- a/configs/textrecog/nrtr/README.md +++ b/configs/textrecog/nrtr/README.md @@ -34,12 +34,12 @@ Scene text recognition has attracted a great many researches due to its importan ## Results and Models -| Methods | Backbone | | Regular Text | | | | Irregular Text | | download | -| :------------------------------------------------------------: | :-------------------: | :----: | :----------: | :----: | :-: | :----: | :------------: | :----: | :--------------------------------------------------------------: | -| | | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | | -| [NRTR](/configs/textrecog/nrtr/nrtr_modality-transform_6e_st_mj.py) | NRTRModalityTransform | 0.9150 | 0.8825 | 0.9369 | | 0.7232 | 0.7783 | 0.7500 | [model](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_modality-transform_6e_st_mj/nrtr_modality-transform_6e_st_mj_20220916_103322-bd9425be.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_modality-transform_6e_st_mj/20220916_103322.log) | -| [NRTR](/configs/textrecog/nrtr/nrtr_resnet31-1by8-1by4_6e_st_mj.py) | R31-1/8-1/4 | 0.9483 | 0.8825 | 0.9507 | | 0.7559 | 0.8016 | 0.8889 | [model](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by8-1by4_6e_st_mj/nrtr_resnet31-1by8-1by4_6e_st_mj_20220916_103322-a6a2a123.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by8-1by4_6e_st_mj/20220916_103322.log) | -| [NRTR](/configs/textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj.py) | R31-1/16-1/8 | 0.9470 | 0.8964 | 0.9399 | | 0.7357 | 0.7969 | 0.8854 | [model](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj/nrtr_resnet31-1by16-1by8_6e_st_mj_20220920_143358-43767036.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj/20220920_143358.log) | +| Methods | Backbone | | Regular Text | | | | Irregular Text | | download | +| :---------------------------------------------------------: | :-------------------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :-----------------------------------------------------------: | +| | | IIIT5K | SVT | IC13-1015 | | IC15-2077 | SVTP | CT80 | | +| [NRTR](/configs/textrecog/nrtr/nrtr_modality-transform_6e_st_mj.py) | NRTRModalityTransform | 0.9147 | 0.8841 | 0.9369 | | 0.7246 | 0.7783 | 0.7500 | [model](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_modality-transform_6e_st_mj/nrtr_modality-transform_6e_st_mj_20220916_103322-bd9425be.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_modality-transform_6e_st_mj/20220916_103322.log) | +| [NRTR](/configs/textrecog/nrtr/nrtr_resnet31-1by8-1by4_6e_st_mj.py) | R31-1/8-1/4 | 0.9483 | 0.8918 | 0.9507 | | 0.7578 | 0.8016 | 0.8889 | [model](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by8-1by4_6e_st_mj/nrtr_resnet31-1by8-1by4_6e_st_mj_20220916_103322-a6a2a123.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by8-1by4_6e_st_mj/20220916_103322.log) | +| [NRTR](/configs/textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj.py) | R31-1/16-1/8 | 0.9470 | 0.8918 | 0.9399 | | 0.7376 | 0.7969 | 0.8854 | [model](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj/nrtr_resnet31-1by16-1by8_6e_st_mj_20220920_143358-43767036.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_resnet31-1by16-1by8_6e_st_mj/20220920_143358.log) | ## Citation diff --git a/configs/textrecog/robust_scanner/README.md b/configs/textrecog/robust_scanner/README.md index 1d104728..b36afce9 100644 --- a/configs/textrecog/robust_scanner/README.md +++ b/configs/textrecog/robust_scanner/README.md @@ -40,10 +40,10 @@ The attention-based encoder-decoder framework has recently achieved impressive r ## Results and Models -| Methods | GPUs | | Regular Text | | | | Irregular Text | | download | -| :---------------------------------------------------------------------: | :--: | :----: | :----------: | :----: | :-: | :----: | :------------: | :----: | :----------------------------------------------------------------------: | -| | | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | | -| [RobustScanner](/configs/textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real.py) | 4 | 0.9510 | 0.8934 | 0.9320 | | 0.7559 | 0.8078 | 0.8715 | [model](https://download.openmmlab.com/mmocr/textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447-7fc35929.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real/20220915_152447.log) | +| Methods | GPUs | | Regular Text | | | | Irregular Text | | download | +| :------------------------------------------------------------------: | :--: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :-------------------------------------------------------------------: | +| | | IIIT5K | SVT | IC13-1015 | | IC15-2077 | SVTP | CT80 | | +| [RobustScanner](/configs/textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real.py) | 4 | 0.9510 | 0.9011 | 0.9320 | | 0.7578 | 0.8078 | 0.8750 | [model](https://download.openmmlab.com/mmocr/textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real_20220915_152447-7fc35929.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/robust_scanner/robustscanner_resnet31_5e_st-sub_mj-sub_sa_real/20220915_152447.log) | ## References diff --git a/configs/textrecog/sar/README.md b/configs/textrecog/sar/README.md index d990de66..3d4615d9 100644 --- a/configs/textrecog/sar/README.md +++ b/configs/textrecog/sar/README.md @@ -40,11 +40,11 @@ Recognizing irregular text in natural scene images is challenging due to the lar ## Results and Models -| Methods | Backbone | Decoder | | Regular Text | | | | Irregular Text | | download | -| :-------------------------------------------------------: | :---------: | :------------------: | :----: | :----------: | :----: | :-: | :----: | :------------: | :----: | :---------------------------------------------------------: | -| | | | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | | -| [SAR](/configs/textrecog/sar/sar_r31_parallel_decoder_academic.py) | R31-1/8-1/4 | ParallelSARDecoder | 0.9533 | 0.8841 | 0.9369 | | 0.7602 | 0.8326 | 0.9028 | [model](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real_20220915_171910-04eb4e75.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real/20220915_171910.log) | -| [SAR](/configs/textrecog/sar/sar_r31_sequential_decoder_academic.py) | R31-1/8-1/4 | SequentialSARDecoder | 0.9553 | 0.8717 | 0.9409 | | 0.7737 | 0.8093 | 0.8924 | [model](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real_20220915_185451-1fd6b1fc.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real/20220915_185451.log) | +| Methods | Backbone | Decoder | | Regular Text | | | | Irregular Text | | download | +| :----------------------------------------------------: | :---------: | :------------------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :------------------------------------------------------: | +| | | | IIIT5K | SVT | IC13-1015 | | IC15-2077 | SVTP | CT80 | | +| [SAR](/configs/textrecog/sar/sar_r31_parallel_decoder_academic.py) | R31-1/8-1/4 | ParallelSARDecoder | 0.9533 | 0.8964 | 0.9369 | | 0.7602 | 0.8326 | 0.9062 | [model](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real_20220915_171910-04eb4e75.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real/20220915_171910.log) | +| [SAR](/configs/textrecog/sar/sar_r31_sequential_decoder_academic.py) | R31-1/8-1/4 | SequentialSARDecoder | 0.9553 | 0.9073 | 0.9409 | | 0.7761 | 0.8093 | 0.8958 | [model](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real_20220915_185451-1fd6b1fc.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real/20220915_185451.log) | ## Citation diff --git a/configs/textrecog/satrn/README.md b/configs/textrecog/satrn/README.md index 936b93d6..aae94971 100644 --- a/configs/textrecog/satrn/README.md +++ b/configs/textrecog/satrn/README.md @@ -34,11 +34,11 @@ Scene text recognition (STR) is the task of recognizing character sequences in n ## Results and Models -| Methods | | Regular Text | | | | Irregular Text | | download | -| :---------------------------------------------------------------------: | :----: | :----------: | :----: | :-: | :----: | :------------: | :----: | :--------------------------------------------------------------------------: | -| | IIIT5K | SVT | IC13 | | IC15 | SVTP | CT80 | | -| [Satrn](/configs/textrecog/satrn/satrn_shallow_5e_st_mj.py) | 0.9600 | 0.9196 | 0.9606 | | 0.8031 | 0.8837 | 0.8993 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow_5e_st_mj/satrn_shallow_5e_st_mj_20220915_152443-5fd04a4c.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow_5e_st_mj/20220915_152443.log) | -| [Satrn_small](/configs/textrecog/satrn/satrn_shallow-small_5e_st_mj.py) | 0.9423 | 0.8995 | 0.9567 | | 0.7877 | 0.8574 | 0.8507 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow-small_5e_st_mj/satrn_shallow-small_5e_st_mj_20220915_152442-5591bf27.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow-small_5e_st_mj/20220915_152442.log) | +| Methods | | Regular Text | | | | Irregular Text | | download | +| :--------------------------------------------------------------------: | :----: | :----------: | :-------: | :-: | :-------: | :------------: | :----: | :---------------------------------------------------------------------: | +| | IIIT5K | SVT | IC13-1015 | | IC15-2077 | SVTP | CT80 | | +| [Satrn](/configs/textrecog/satrn/satrn_shallow_5e_st_mj.py) | 0.9600 | 0.9181 | 0.9606 | | 0.8045 | 0.8837 | 0.8993 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow_5e_st_mj/satrn_shallow_5e_st_mj_20220915_152443-5fd04a4c.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow_5e_st_mj/20220915_152443.log) | +| [Satrn_small](/configs/textrecog/satrn/satrn_shallow-small_5e_st_mj.py) | 0.9423 | 0.9011 | 0.9567 | | 0.7886 | 0.8574 | 0.8472 | [model](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow-small_5e_st_mj/satrn_shallow-small_5e_st_mj_20220915_152442-5591bf27.pth) \| [log](https://download.openmmlab.com/mmocr/textrecog/satrn/satrn_shallow-small_5e_st_mj/20220915_152442.log) | ## Citation