diff --git a/doc/doc_ch/algorithm_overview.md b/doc/doc_ch/algorithm_overview.md index e8f23b54e50be7ac2f5388a726ed6540d2c159c3..6f19c6aa0e204d5af2e785f91f67257576f3d6db 100755 --- a/doc/doc_ch/algorithm_overview.md +++ b/doc/doc_ch/algorithm_overview.md @@ -1,12 +1,20 @@ - -## 算法介绍 +# 两阶段算法 + +- [两阶段算法](#-----) + * [1. 算法介绍](#1) + + [1.1 文本检测算法](#11) + + [1.2 文本识别算法](#12) + * [2. 模型训练](#2) + * [3. 模型推理](#3) + + + +## 1. 算法介绍 本文给出了PaddleOCR已支持的文本检测算法和文本识别算法列表，以及每个算法在**英文公开数据集**上的模型和指标，主要用于算法简介和算法性能对比，更多包括中文在内的其他数据集上的模型请参考[PP-OCR v2.0 系列模型下载](./models_list.md)。 -- [1.文本检测算法](#文本检测算法) -- [2.文本识别算法](#文本识别算法) + - -### 1.文本检测算法 +### 1.1 文本检测算法 PaddleOCR开源的文本检测算法列表： - [x] DB([paper]( https://arxiv.org/abs/1911.08947)) [2]（ppocr推荐） @@ -16,27 +24,25 @@ PaddleOCR开源的文本检测算法列表： 在ICDAR2015文本检测公开数据集上，算法效果如下： |模型|骨干网络|precision|recall|Hmean|下载链接| | --- | --- | --- | --- | --- | --- | -|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)| -|EAST|MobileNetV3|79.42%|80.64%|80.03%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)| -|DB|ResNet50_vd|86.41%|78.72%|82.38%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)| -|DB|MobileNetV3|77.29%|73.08%|75.12%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)| -|SAST|ResNet50_vd|91.39%|83.77%|87.42%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)| +|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)| +|EAST|MobileNetV3|79.42%|80.64%|80.03%|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)| +|DB|ResNet50_vd|86.41%|78.72%|82.38%|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)| +|DB|MobileNetV3|77.29%|73.08%|75.12%|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)| +|SAST|ResNet50_vd|91.39%|83.77%|87.42%|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)| 在Total-text文本检测公开数据集上，算法效果如下： |模型|骨干网络|precision|recall|Hmean|下载链接| | --- | --- | --- | --- | --- | --- | -|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)| +|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)| **说明：** SAST模型训练额外加入了icdar2013、icdar2017、COCO-Text、ArT等公开数据集进行调优。PaddleOCR用到的经过整理格式的英文公开数据集下载： * [百度云地址](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (提取码: 2bpi) * [Google Drive下载地址](https://drive.google.com/drive/folders/1ll2-XEVyCQLpJjawLDiRlvo_i4BqHCJe?usp=sharing) -PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训练/评估中的文本检测部分](./detection.md)。 + - - -### 2.文本识别算法 +### 1.2 文本识别算法 PaddleOCR基于动态图开源的文本识别算法列表： - [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7]（ppocr推荐） @@ -50,16 +56,26 @@ PaddleOCR基于动态图开源的文本识别算法列表： |模型|骨干网络|Avg Accuracy|模型存储命名|下载链接| |---|---|---|---|---| -|Rosetta|Resnet34_vd|80.9%|rec_r34_vd_none_none_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_none_ctc_v2.0_train.tar)| -|Rosetta|MobileNetV3|78.05%|rec_mv3_none_none_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_none_ctc_v2.0_train.tar)| -|CRNN|Resnet34_vd|82.76%|rec_r34_vd_none_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar)| -|CRNN|MobileNetV3|79.97%|rec_mv3_none_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar)| -|StarNet|Resnet34_vd|84.44%|rec_r34_vd_tps_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_ctc_v2.0_train.tar)| -|StarNet|MobileNetV3|81.42%|rec_mv3_tps_bilstm_ctc|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_ctc_v2.0_train.tar)| -|RARE|MobileNetV3|82.5%|rec_mv3_tps_bilstm_att |[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)| -|RARE|Resnet34_vd|83.6%|rec_r34_vd_tps_bilstm_att |[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)| -|SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar) | -|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) | - - -PaddleOCR文本识别算法的训练和使用请参考文档教程中[模型训练/评估中的文本识别部分](./recognition.md)。 +|Rosetta|Resnet34_vd|80.9%|rec_r34_vd_none_none_ctc|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_none_ctc_v2.0_train.tar)| +|Rosetta|MobileNetV3|78.05%|rec_mv3_none_none_ctc|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_none_ctc_v2.0_train.tar)| +|CRNN|Resnet34_vd|82.76%|rec_r34_vd_none_bilstm_ctc|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar)| +|CRNN|MobileNetV3|79.97%|rec_mv3_none_bilstm_ctc|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar)| +|StarNet|Resnet34_vd|84.44%|rec_r34_vd_tps_bilstm_ctc|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_ctc_v2.0_train.tar)| +|StarNet|MobileNetV3|81.42%|rec_mv3_tps_bilstm_ctc|[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_ctc_v2.0_train.tar)| +|RARE|MobileNetV3|82.5%|rec_mv3_tps_bilstm_att |[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)| +|RARE|Resnet34_vd|83.6%|rec_r34_vd_tps_bilstm_att |[预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)| +|SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn | [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar) | +|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) | + + + +## 2. 模型训练 + +PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训练/评估中的文本检测部分](./detection.md)。文本识别算法的训练和使用请参考文档教程中[模型训练/评估中的文本识别部分](./recognition.md)。 + + + +## 3. 模型推理 + +上述模型中除PP-OCR系列模型以外，其余模型仅支持基于Python引擎的推理，具体内容可参考[基于Python预测引擎推理](./inference.md) + diff --git a/doc/doc_en/algorithm_overview_en.md b/doc/doc_en/algorithm_overview_en.md index 8e8f0d3f8c36885515ea65f17e910c31838bc603..45aa8784eb7c65347c663eedb0cfb3df1f820dd4 100755 --- a/doc/doc_en/algorithm_overview_en.md +++ b/doc/doc_en/algorithm_overview_en.md @@ -1,5 +1,14 @@ +# Two-stage Algorithm + +- [1. Algorithm Introduction](#1-algorithm-introduction) + * [1.1 Text Detection Algorithm](#11-text-detection-algorithm) + * [1.2 Text Recognition Algorithm](#12-text-recognition-algorithm) +- [2. Training](#2-training) +- [3. Inference](#3-inference) + -## Algorithm introduction + +## 1. Algorithm Introduction This tutorial lists the text detection algorithms and text recognition algorithms supported by PaddleOCR, as well as the models and metrics of each algorithm on **English public datasets**. It is mainly used for algorithm introduction and algorithm performance comparison. For more models on other datasets including Chinese, please refer to [PP-OCR v2.0 models list](./models_list_en.md). @@ -8,7 +17,8 @@ This tutorial lists the text detection algorithms and text recognition algorithm - [2. Text Recognition Algorithm](#TEXTRECOGNITIONALGORITHM) -### 1. Text Detection Algorithm + +### 1.1 Text Detection Algorithm PaddleOCR open source text detection algorithms list: - [x] EAST([paper](https://arxiv.org/abs/1704.03155))[2] @@ -38,7 +48,7 @@ On Total-Text dataset, the text detection result is as follows: For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./detection_en.md) -### 2. Text Recognition Algorithm +### 1.2 Text Recognition Algorithm PaddleOCR open-source text recognition algorithms list: - [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7] @@ -63,4 +73,12 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r |SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn |[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar)| |NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) | -Please refer to the document for training guide and use of PaddleOCR text recognition algorithms [Text recognition model training/evaluation/prediction](./recognition_en.md) +Please refer to the document for training guide and use of PaddleOCR + +## 2. Training + +For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./detection_en.md). For text recognition algorithms, please refer to [Text recognition model training/evaluation/prediction](./recognition_en.md) + +## 3. Inference + +Except for the PP-OCR series models of the above models, the other models only support inference based on the Python engine. For details, please refer to [Inference based on Python prediction engine](./inference_en.md)