diff --git a/.github/ISSUE_TEMPLATE/custom.md b/.github/ISSUE_TEMPLATE/custom.md new file mode 100644 index 0000000000000000000000000000000000000000..3487cff8b23a09fb37fd6375e0e0c5f278b5f47b --- /dev/null +++ b/.github/ISSUE_TEMPLATE/custom.md @@ -0,0 +1,15 @@ +--- +name: Issue template +about: Issue template for code error. +title: '' +labels: '' +assignees: '' + +--- + +请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem + +- 系统环境/System Environment： +- 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components： +- 运行指令/Command Code： +- 完整报错/Complete Error Message： diff --git a/README.md b/README.md index f6a73a7e15739443b5af7d4a73893f63ae1c0a20..f5bc7406b9649730e43e9fe5cdb5b71eba7dc3aa 100644 --- a/README.md +++ b/README.md @@ -25,7 +25,7 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools **Recent updates** -- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Live Address](https://live.bilibili.com/21689802). +- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Course Address](https://aistudio.baidu.com/aistudio/education/group/info/6758). - 2021.9.7 release PaddleOCR v2.3, [PP-OCRv2](#PP-OCRv2) is proposed. The inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server in CPU device. The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile. - 2021.8.3 released PaddleOCR v2.2, add a new structured documents analysis toolkit, i.e., [PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README.md), support layout analysis and table recognition (One-key to export chart images to Excel files). - 2021.4.8 release end-to-end text recognition algorithm [PGNet](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) which is published in AAAI 2021. Find tutorial [here](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/pgnet_en.md)；release multi language recognition [models](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md), support more than 80 languages recognition; especically, the performance of [English recognition model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/models_list_en.md#English) is Optimized. @@ -86,9 +86,9 @@ Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Andr | Model introduction | Model name | Recommended scene | Detection model | Direction classifier | Recognition model | | ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | -| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） | ch_PP-OCRv2_xx |Mobile&Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/ch/ch_PP-OCRv2_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)| -| Chinese and English ultra-lightweight PP-OCR model (9.4M) | ch_ppocr_mobile_v2.0_xx | Mobile & server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) | -| Chinese and English general PP-OCR model (143.4M) | ch_ppocr_server_v2.0_xx | Server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) | +| Chinese and English ultra-lightweight PP-OCRv2 model（11.6M） | ch_PP-OCRv2_xx |Mobile & Server|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/ch/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)| +| Chinese and English ultra-lightweight PP-OCR model (9.4M) | ch_ppocr_mobile_v2.0_xx | Mobile & server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) | +| Chinese and English general PP-OCR model (143.4M) | ch_ppocr_server_v2.0_xx | Server |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) | For more model downloads (including multiple languages), please refer to [PP-OCR series model downloads](./doc/doc_en/models_list_en.md). @@ -102,7 +102,6 @@ For a new language request, please refer to [Guideline for new language_requests - PP-OCR Industry Landing: from Training to Deployment - [PP-OCR Model and Configuration](./doc/doc_en/models_and_config_en.md) - [PP-OCR Model Download](./doc/doc_en/models_list_en.md) - - [Yml Configuration](./doc/doc_en/config_en.md) - [Python Inference for PP-OCR Model Library](./doc/doc_en/inference_ppocr_en.md) - [PP-OCR Training](./doc/doc_en/training_en.md) - [Text Detection](./doc/doc_en/detection_en.md) diff --git a/README_ch.md b/README_ch.md index 7091523d2f6e24dd4256aad9e6a978a6929f9443..4511d713e2006cf046ba53ac49269989c381795a 100755 --- a/README_ch.md +++ b/README_ch.md @@ -24,7 +24,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力 **近期更新** -- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[直播地址](https://live.bilibili.com/21689802)。 +- PaddleOCR研发团队对最新发版内容技术深入解读，9月8日晚上20:15，[课程回放](https://aistudio.baidu.com/aistudio/education/group/info/6758)。 - 2021.9.7 发布PaddleOCR v2.3，发布[PP-OCRv2](#PP-OCRv2)，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。 - 2021.8.3 发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。 - 2021.6.29 [FAQ](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/doc/doc_ch/FAQ.md)新增5个高频问题，总数248个，每周一都会更新，欢迎大家持续关注。 @@ -81,9 +81,9 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力 | 模型简介 | 模型名称 |推荐场景 | 检测模型 | 方向分类器 | 识别模型 | | ------------ | --------------- | ----------------|---- | ---------- | -------- | -| 中英文超轻量PP-OCRv2模型（13.0M） | ch_PP-OCRv2_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)| -| 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) | -| 中英文通用PP-OCR server模型（143.4M） |ch_ppocr_server_v2.0_xx|服务器端 |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) | +| 中英文超轻量PP-OCRv2模型（13.0M） | ch_PP-OCRv2_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar)| +| 中英文超轻量PP-OCR mobile模型（9.4M） | ch_ppocr_mobile_v2.0_xx |移动端&服务器端|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) | +| 中英文通用PP-OCR server模型（143.4M） |ch_ppocr_server_v2.0_xx|服务器端 |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) | 更多模型下载（包括多语言），可以参考[PP-OCR 系列模型下载](./doc/doc_ch/models_list.md) @@ -94,7 +94,6 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力 - PP-OCR产业落地：从训练到部署 - [PP-OCR模型与配置文件](./doc/doc_ch/models_and_config.md) - [PP-OCR模型下载](./doc/doc_ch/models_list.md) - - [配置文件内容与生成](./doc/doc_ch/config.md) - [PP-OCR模型库快速推理](./doc/doc_ch/inference_ppocr.md) - [PP-OCR模型训练](./doc/doc_ch/training.md) - [文本检测](./doc/doc_ch/detection.md) diff --git a/doc/banner.png b/doc/banner.png new file mode 100644 index 0000000000000000000000000000000000000000..d72b997a803a6f6fa8919cd3d4bb08afdec58a9b Binary files /dev/null and b/doc/banner.png differ diff --git a/doc/doc_ch/algorithm_overview.md b/doc/doc_ch/algorithm_overview.md index 1ffb8f340305249d5f2c8aeb2fef37dc8f590eff..f0c16618c0dd0b0f0bcc6a06d6b142a59d58e725 100755 --- a/doc/doc_ch/algorithm_overview.md +++ b/doc/doc_ch/algorithm_overview.md @@ -1,72 +1,87 @@ - -## 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))（ppocr推荐） -- [x] EAST([paper](https://arxiv.org/abs/1704.03155)) -- [x] SAST([paper](https://arxiv.org/abs/1908.05498)) +- [x] DB([paper]( https://arxiv.org/abs/1911.08947)) [2]（ppocr推荐） +- [x] EAST([paper](https://arxiv.org/abs/1704.03155))[1] +- [x] SAST([paper](https://arxiv.org/abs/1908.05498))[4] - [x] PSENet([paper](https://arxiv.org/abs/1903.12473v2)） 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)| -|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)| -|PSE|MobileNetV3|82.20%|70.48%|75.89%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)| +|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[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%|[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%|[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%|[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%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)| +|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)| +|PSE|MobileNetV3|82.20%|70.48%|75.89%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_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%|[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))（ppocr推荐） -- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085)) -- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html)) -- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1)) -- [x] SRN([paper](https://arxiv.org/abs/2003.12294)) -- [x] NRTR([paper](https://arxiv.org/abs/1806.00926v2)) +- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7]（ppocr推荐） +- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))[10] +- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11] +- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))[12] +- [x] SRN([paper](https://arxiv.org/abs/2003.12294))[5] +- [x] NRTR([paper](https://arxiv.org/abs/1806.00926v2))[13] - [x] SAR([paper](https://arxiv.org/abs/1811.00751v2)) -- [x] SEED([paper](https://arxiv.org/pdf/2005.10977.pdf)) +- [x] SEED([paper](https://arxiv.org/pdf/2005.10977.pdf)) -参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下： +参考[DTRB][3](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下： |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) | -|SAR|Resnet31| 87.2% | rec_r31_sar | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) | -|SEED| Aster_Resnet | 85.2% | rec_resnet_stn_bilstm_att | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.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|[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|[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|[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|[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|[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|[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 |[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 |[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 | [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 | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) | +|SAR|Resnet31| 87.2% | rec_r31_sar | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) | +|SEED|Aster_Resnet| 85.2% | rec_resnet_stn_bilstm_att | [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.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_ch/angle_class.md b/doc/doc_ch/angle_class.md index 8142d7dcca62511811603303d6a4bfe2e914269b..723d0d2ce5a8c25699c085c32004aa827b188fd9 100644 --- a/doc/doc_ch/angle_class.md +++ b/doc/doc_ch/angle_class.md @@ -11,7 +11,7 @@ ## 1. 方法介绍 文本方向分类器主要用于图片非0度的场景下，在这种场景下需要对图片里检测到的文本行进行一个转正的操作。在PaddleOCR系统内， 文字检测之后得到的文本行图片经过仿射变换之后送入识别模型，此时只需要对文字进行一个0和180度的角度分类，因此PaddleOCR内置的 -文字角度分类器**只支持了0和180度的分类**。如果想支持更多角度，可以自己修改算法进行支持。 +文本方向分类器**只支持了0和180度的分类**。如果想支持更多角度，可以自己修改算法进行支持。 0和180度数据样本例子： @@ -72,8 +72,6 @@ train/cls/train/word_002.jpg 180 ## 3. 启动训练 -### 启动训练 - 将准备好的txt文件和图片文件夹路径分别写入配置文件的 `Train/Eval.dataset.label_file_list` 和 `Train/Eval.dataset.data_dir` 字段下，`Train/Eval.dataset.data_dir`字段下的路径和文件里记载的图片名构成了图片的绝对路径。 PaddleOCR提供了训练脚本、评估脚本和预测脚本。 diff --git a/doc/doc_ch/config.md b/doc/doc_ch/config.md index dcd0318ed908375c896d7a6730cd72db4cc4b848..40c63905c3f03070a9dcbf0176ada31378b14fee 100644 --- a/doc/doc_ch/config.md +++ b/doc/doc_ch/config.md @@ -36,10 +36,10 @@ | pretrained_model | 设置加载预训练模型路径 | ./pretrain_models/CRNN/best_accuracy | \ | | checkpoints | 加载模型参数路径 | None | 用于中断后加载参数继续训练 | | use_visualdl | 设置是否启用visualdl进行可视化log展示 | False | [教程地址](https://www.paddlepaddle.org.cn/paddle/visualdl) | -| infer_img | 设置预测图像路径或文件夹路径 | ./infer_img | \| -| character_dict_path | 设置字典路径 | ./ppocr/utils/ppocr_keys_v1.txt | 如果为空，则默认使用小写字母+数字作为字典 | +| infer_img | 设置预测图像路径或文件夹路径 | ./infer_img | \|| +| character_dict_path | 设置字典路径 | ./ppocr/utils/ppocr_keys_v1.txt | 如果为空，则默认使用小写字母+数字作为字典 | | max_text_length | 设置文本最大长度 | 25 | \ | -| use_space_char | 设置是否识别空格 | True | | +| use_space_char | 设置是否识别空格 | True | \| | | label_list | 设置方向分类器支持的角度 | ['0','180'] | 仅在方向分类器中生效 | | save_res_path | 设置检测模型的结果保存地址 | ./output/det_db/predicts_db.txt | 仅在检测模型中生效 | @@ -176,7 +176,7 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi --dict {path/of/dict} \ # 字典文件路径 -o Global.use_gpu=False # 是否使用gpu ... - + ``` 意大利文由拉丁字母组成，因此执行完命令后会得到名为 rec_latin_lite_train.yml 的配置文件。 @@ -191,21 +191,21 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi epoch_num: 500 ... character_dict_path: {path/of/dict} # 字典文件所在路径 - + Train: dataset: name: SimpleDataSet data_dir: train_data/ # 数据存放根目录 label_file_list: ["./train_data/train_list.txt"] # 训练集label路径 ... - + Eval: dataset: name: SimpleDataSet data_dir: train_data/ # 数据存放根目录 label_file_list: ["./train_data/val_list.txt"] # 验证集label路径 ... - + ``` 目前PaddleOCR支持的多语言算法有： @@ -214,12 +214,12 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi | :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | | rec_chinese_cht_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 中文繁体 | | rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语（区分大小写） | -| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 | +| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 | | rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 | | rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 | | rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 | | rec_latin_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 拉丁字母 | -| rec_arabic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 阿拉伯字母 | +| rec_arabic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 阿拉伯字母 | | rec_cyrillic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 斯拉夫字母 | | rec_devanagari_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 梵文字母 | diff --git a/doc/doc_ch/detection.md b/doc/doc_ch/detection.md index e69f7355390f5c16cb1b498389a6552b5d40ca0a..cfc9d52bf280400982a9fcd9941ddc4cce3f5e5c 100644 --- a/doc/doc_ch/detection.md +++ b/doc/doc_ch/detection.md @@ -1,22 +1,24 @@ -# 目录 -- [1. 文字检测](#1-----) - * [1.1 数据准备](#11-----) - * [1.2 下载预训练模型](#12--------) - * [1.3 启动训练](#13-----) - * [1.4 断点训练](#14-----) - * [1.5 更换Backbone 训练](#15---backbone---) - * [1.6 指标评估](#16-----) - * [1.7 测试检测效果](#17-------) - * [1.8 转inference模型测试](#18--inference----) -- [2. FAQ](#2-faq) - - - -# 1. 文字检测 +# 文字检测 本节以icdar2015数据集为例，介绍PaddleOCR中检测模型训练、评估、测试的使用方式。 +- [1. 准备数据和模型](#1--------) + * [1.1 数据准备](#11-----) + * [1.2 下载预训练模型](#12--------) +- [2. 开始训练](#2-----) + * [2.1 启动训练](#21-----) + * [2.2 断点训练](#22-----) + * [2.3 更换Backbone 训练](#23---backbone---) +- [3. 模型评估与预测](#3--------) + * [3.1 指标评估](#31-----) + * [3.2 测试检测效果](#32-------) +- [4. 模型导出与预测](#4--------) +- [5. FAQ](#5-faq) + + +# 1. 准备数据和模型 + ## 1.1 数据准备 @@ -83,8 +85,11 @@ wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dyg wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams ``` - -## 1.3 启动训练 + +# 2. 开始训练 + + +## 2.1 启动训练 *如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false* @@ -119,8 +124,8 @@ python3 tools/train.py -c configs/det/det_mv3_db.yml \ Global.use_amp=True Global.scale_loss=1024.0 Global.use_dynamic_loss_scaling=True ``` - -## 1.4 断点训练 + +## 2.2 断点训练 如果训练程序中断，如果希望加载训练中断的模型从而恢复训练，可以通过指定Global.checkpoints指定要加载的模型路径： ```shell @@ -129,8 +134,8 @@ python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=./you **注意**：`Global.checkpoints`的优先级高于`Global.pretrained_model`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrained_model`指定的模型。 - -## 1.5 更换Backbone 训练 + +## 2.3 更换Backbone 训练 PaddleOCR将网络划分为四部分，分别在[ppocr/modeling](../../ppocr/modeling)下。 进入网络的数据将按照顺序(transforms->backbones-> necks->heads)依次通过这四个部分。 @@ -177,8 +182,11 @@ args1: args1 **注意**：如果要更换网络的其他模块，可以参考[文档](./add_new_algorithm.md)。 - -## 1.6 指标评估 + +# 3. 模型评估与预测 + + +## 3.1 指标评估 PaddleOCR计算三个OCR检测相关的指标，分别是：Precision、Recall、Hmean（F-Score）。 @@ -190,8 +198,8 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Global.checkpoints="{pat * 注：`box_thresh`、`unclip_ratio`是DB后处理所需要的参数，在评估EAST模型时不需要设置 - -## 1.7 测试检测效果 + +## 3.2 测试检测效果 测试单张图像的检测效果 ```shell @@ -208,8 +216,8 @@ python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./ python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" ``` - -## 1.8 转inference模型测试 + +# 4. 模型导出与预测 inference 模型（`paddle.jit.save`保存的模型） 一般是模型训练，把模型结构和模型参数保存在文件中的固化模型，多用于预测部署场景。 @@ -231,10 +239,11 @@ python3 tools/infer/predict_det.py --det_algorithm="DB" --det_model_dir="./outpu python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./output/det_db_inference/" --image_dir="./doc/imgs/" --use_gpu=True ``` - -# 2. FAQ + +# 5. FAQ Q1: 训练模型转inference 模型之后预测效果不一致？ + **A**：此类问题出现较多，问题多是trained model预测时候的预处理、后处理参数和inference model预测的时候的预处理、后处理参数不一致导致的。以det_mv3_db.yml配置文件训练的模型为例，训练模型、inference模型预测结果不一致问题解决方式如下： - 检查[trained model预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116)，和[inference model的预测预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42)函数是否一致。算法在评估的时候，输入图像大小会影响精度，为了和论文保持一致，训练icdar15配置文件中将图像resize到[736, 1280]，但是在inference model预测的时候只有一套默认参数，会考虑到预测速度问题，默认限制图像最长边为960做resize的。训练模型预处理和inference模型的预处理函数位于[ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147) - 检查[trained model后处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51)，和[inference 后处理参数](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50)是否一致。 diff --git a/doc/doc_ch/inference_ppocr.md b/doc/doc_ch/inference_ppocr.md index 493a4c9868621b762895e1ee11f76ac250918453..3e46f17d3a781839dfe5e632f85aabcd03d0fd17 100644 --- a/doc/doc_ch/inference_ppocr.md +++ b/doc/doc_ch/inference_ppocr.md @@ -1,16 +1,13 @@ -# PP-OCR模型库快速推理 +# 基于Python引擎的PP-OCR模型库推理 本文介绍针对PP-OCR模型库的Python推理引擎使用方法，内容依次为文本检测、文本识别、方向分类器以及三者串联在CPU、GPU上的预测方法。 - [1. 文本检测模型推理](#文本检测模型推理) - - [2. 文本识别模型推理](#文本识别模型推理) - [2.1 超轻量中文识别模型推理](#超轻量中文识别模型推理) - [2.2 多语言模型的推理](#多语言模型的推理) - - [3. 方向分类模型推理](#方向分类模型推理) - - [4. 文本检测、方向分类和文字识别串联推理](#文本检测、方向分类和文字识别串联推理) @@ -21,12 +18,15 @@ ``` # 下载超轻量中文检测模型： -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tartar xf ch_ppocr_mobile_v2.0_det_infer.tarpython3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_ppocr_mobile_v2.0_det_infer/" +wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar +tar xf ch_PP-OCRv2_det_infer.tar +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv2_det_infer/" + ``` 可视化文本检测结果默认保存到`./inference_results`文件夹里面，结果文件的名称前缀为'det_res'。结果示例如下： -![](/Users/zhulingfeng01/OCR/PaddleOCR/doc/imgs_results/det_res_00018069.jpg) +![](../imgs_results/det_res_00018069.jpg) 通过参数`limit_type`和`det_limit_side_len`来对图片的尺寸进行限制， `limit_type`可选参数为[`max`, `min`]， @@ -39,13 +39,13 @@ wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_i 如果输入图片的分辨率比较大，而且想使用更大的分辨率预测，可以设置det_limit_side_len 为想要的值，比如1216： ``` -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --det_limit_type=max --det_limit_side_len=1216 +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --det_limit_type=max --det_limit_side_len=1216 ``` 如果想使用CPU进行预测，执行命令如下 ``` -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --use_gpu=False +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --use_gpu=False ``` @@ -62,12 +62,12 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_di ``` # 下载超轻量中文识别模型： -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar -tar xf ch_ppocr_mobile_v2.0_rec_infer.tar -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer" +wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar +tar xf ch_PP-OCRv2_rec_infer.tar +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./ch_PP-OCRv2_rec_infer/" ``` -![](/Users/zhulingfeng01/OCR/PaddleOCR/doc/imgs_words/ch/word_4.jpg) +![](../imgs_words/ch/word_4.jpg) 执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下： @@ -79,14 +79,13 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153) ### 2.2 多语言模型的推理 -如果您需要预测的是其他语言模型，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径, 同时为了得到正确的可视化结果， -需要通过 `--vis_font_path` 指定可视化的字体路径，`doc/fonts/` 路径下有默认提供的小语种字体，例如韩文识别： - +如果您需要预测的是其他语言模型，可以在[此链接](./models_list.md#%E5%A4%9A%E8%AF%AD%E8%A8%80%E8%AF%86%E5%88%AB%E6%A8%A1%E5%9E%8B)中找到对应语言的inference模型，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径, 同时为了得到正确的可视化结果，需要通过 `--vis_font_path` 指定可视化的字体路径，`doc/fonts/` 路径下有默认提供的小语种字体，例如韩文识别： ``` +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf" ``` -![](/Users/zhulingfeng01/OCR/PaddleOCR/doc/imgs_words/korean/1.jpg) +![](../imgs_words/korean/1.jpg) 执行命令后，上图的预测结果为： @@ -107,7 +106,7 @@ tar xf ch_ppocr_mobile_v2.0_cls_infer.tar python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer" ``` -![](/Users/zhulingfeng01/OCR/PaddleOCR/doc/imgs_words/ch/word_1.jpg) +![](../imgs_words/ch/word_1.jpg) 执行命令后，上面图像的预测结果（分类的方向和得分）会打印到屏幕上，示例如下： @@ -123,14 +122,13 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:['0', 0.9999982] ```shell # 使用方向分类器 -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --cls_model_dir="./inference/cls/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=true +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --cls_model_dir="./inference/cls/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=true # 不使用方向分类器 -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=false +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=false # 使用多进程 -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=false --use_mp=True --total_process_num=6 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 ``` 执行命令后，识别结果图像如下： -![](/Users/zhulingfeng01/OCR/PaddleOCR/doc/imgs_results/system_res_00018069.jpg) - +![](../imgs_results/system_res_00018069.jpg) diff --git a/doc/doc_ch/models.md b/doc/doc_ch/models.md new file mode 100644 index 0000000000000000000000000000000000000000..bd798e05b358e06d030dca8151eed36bc0714668 --- /dev/null +++ b/doc/doc_ch/models.md @@ -0,0 +1,47 @@ + +# PP-OCR模型库 +PP-OCR模型一节主要补充一些OCR模型的基本概念以及如何快速运用PP-OCR模型库中的模型。 + +本节包含两个部分，首先在[PP-OCR模型下载](./models_list.md)中解释PP-OCR模型的类型概念，并提供所有模型的下载链接。然后在[基于Python引擎的PP-OCR模型库推理](./inference_ppocr.md)中介绍PP-OCR模型库的使用方法，可以通过Python推理引擎快速利用丰富的模型库模型获得测试结果。 + +------ + +下面我们首先了解一些OCR相关的基本概念： + +- [1. OCR 简要介绍](#1-ocr-----) + * [1.1 OCR 检测模型基本概念](#11-ocr---------) + * [1.2 OCR 识别模型基本概念](#12-ocr---------) + * [1.3 PP-OCR模型](#13-pp-ocr--) + + +## 1. OCR 简要介绍 +本节简要介绍OCR检测模型、识别模型的基本概念，并介绍PaddleOCR的PP-OCR模型。 + +OCR（Optical Character Recognition，光学字符识别）目前是文字识别的统称，已不限于文档或书本文字识别，更包括识别自然场景下的文字，又可以称为STR（Scene Text Recognition）。 + +OCR文字识别一般包括两个部分，文本检测和文本识别；文本检测首先利用检测算法检测到图像中的文本行；然后检测到的文本行用识别算法去识别到具体文字。 + + +### 1.1 OCR 检测模型基本概念 + +文本检测就是要定位图像中的文字区域，然后通常以边界框的形式将单词或文本行标记出来。传统的文字检测算法多是通过手工提取特征的方式，特点是速度快，简单场景效果好，但是面对自然场景，效果会大打折扣。当前多是采用深度学习方法来做。 + +基于深度学习的文本检测算法可以大致分为以下几类： +1. 基于目标检测的方法；一般是预测得到文本框后，通过NMS筛选得到最终文本框，多是四点文本框，对弯曲文本场景效果不理想。典型算法为EAST、Text Box等方法。 +2. 基于分割的方法；将文本行当成分割目标，然后通过分割结果构建外接文本框，可以处理弯曲文本，对于文本交叉场景问题效果不理想。典型算法为DB、PSENet等方法。 +3. 混合目标检测和分割的方法； + + +### 1.2 OCR 识别模型基本概念 + +OCR识别算法的输入数据一般是文本行，背景信息不多，文字占据主要部分，识别算法目前可以分为两类算法： +1. 基于CTC的方法；即识别算法的文字预测模块是基于CTC的，常用的算法组合为CNN+RNN+CTC。目前也有一些算法尝试在网络中加入transformer模块等等。 +2. 基于Attention的方法；即识别算法的文字预测模块是基于Attention的，常用算法组合是CNN+RNN+Attention。 + + +### 1.3 PP-OCR模型 + +PaddleOCR 中集成了很多OCR算法，文本检测算法有DB、EAST、SAST等等，文本识别算法有CRNN、RARE、StarNet、Rosetta、SRN等算法。 + +其中PaddleOCR针对中英文自然场景通用OCR，推出了PP-OCR系列模型，PP-OCR模型由DB+CRNN算法组成，利用海量中文数据训练加上模型调优方法，在中文场景上具备较高的文本检测识别能力。并且PaddleOCR推出了高精度超轻量PP-OCRv2模型，检测模型仅3M，识别模型仅8.5M，利用[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)的模型量化方法，可以在保持精度不降低的情况下，将检测模型压缩到0.8M，识别压缩到3M，更加适用于移动端部署场景。 + diff --git a/doc/doc_ch/models_list.md b/doc/doc_ch/models_list.md index 5e78795bcda96cf005f24b97cfcc0a8580b2ae1e..31ab6a2c1c2df6528c3b08c32a39a94115b946b8 100644 --- a/doc/doc_ch/models_list.md +++ b/doc/doc_ch/models_list.md @@ -1,4 +1,4 @@ -## OCR模型列表（V2.1，2021年9月6日更新） +# OCR模型列表（V2.1，2021年9月6日更新） > **说明** > 1. 2.1版模型相比2.0版模型，2.1的模型在模型精度上做了提升 @@ -6,13 +6,13 @@ > 3. 本文档提供的是PPOCR自研模型列表，更多基于公开数据集的算法介绍与预训练模型可以参考：[算法概览文档](./algorithm_overview.md)。 -- [一、文本检测模型](#文本检测模型) -- [二、文本识别模型](#文本识别模型) - - [1. 中文识别模型](#中文识别模型) - - [2. 英文识别模型](#英文识别模型) - - [3. 多语言识别模型](#多语言识别模型) -- [三、文本方向分类模型](#文本方向分类模型) -- [四、Paddle-Lite 模型](#Paddle-Lite模型) +- [1. 文本检测模型](#文本检测模型) +- [2. 文本识别模型](#文本识别模型) + - [2.1 中文识别模型](#中文识别模型) + - [2.2 英文识别模型](#英文识别模型) + - [2.3 多语言识别模型](#多语言识别模型) +- [3. 文本方向分类模型](#文本方向分类模型) +- [4. Paddle-Lite 模型](#Paddle-Lite模型) PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训练模型`、`slim模型`，模型区别说明如下： @@ -29,27 +29,28 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 -### 一、文本检测模型 +## 1. 文本检测模型 |模型名称|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- | --- | -|ch_PP-OCRv2_det_slim|slim量化+蒸馏版超轻量模型，支持中英文、多语种文本检测|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)| 3M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar)| -|ch_PP-OCRv2_det|原始超轻量模型，支持中英文、多语种文本检测|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)|3M|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| +|ch_PP-OCRv2_det_slim|【最新】slim量化+蒸馏版超轻量模型，支持中英文、多语种文本检测|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)| 3M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar)| +|ch_PP-OCRv2_det|【最新】原始超轻量模型，支持中英文、多语种文本检测|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)|3M|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| |ch_ppocr_mobile_slim_v2.0_det|slim裁剪版超轻量模型，支持中英文、多语种文本检测|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| 2.6M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar)| |ch_ppocr_mobile_v2.0_det|原始超轻量模型，支持中英文、多语种文本检测|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)| |ch_ppocr_server_v2.0_det|通用模型，支持中英文、多语种文本检测，比超轻量模型更大，但效果更好|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)| -### 二、文本识别模型 +## 2. 文本识别模型 -#### 1. 中文识别模型 + +### 2.1 中文识别模型 |模型名称|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- | --- | -|ch_PP-OCRv2_rec_slim|slim量化版超轻量模型，支持中英文、数字识别|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) | -|ch_PP-OCRv2_rec|原始超轻量模型，支持中英文、数字识别|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)|8.5M|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) | +|ch_PP-OCRv2_rec_slim|【最新】slim量化版超轻量模型，支持中英文、数字识别|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) | +|ch_PP-OCRv2_rec|【最新】原始超轻量模型，支持中英文、数字识别|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)|8.5M|[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) | |ch_ppocr_mobile_slim_v2.0_rec|slim裁剪量化版超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| 6M |[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_train.tar) | |ch_ppocr_mobile_v2.0_rec|原始超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|5.2M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) | |ch_ppocr_server_v2.0_rec|通用模型，支持中英文、数字识别|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) | @@ -57,7 +58,7 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 **说明：** `训练模型`是基于预训练模型在真实数据与竖排合成文本数据上finetune得到的模型，在真实应用场景中有着更好的表现，`预训练模型`则是直接基于全量真实数据与合成数据训练得到，更适合用于在自己的数据集上finetune。 -#### 2. 英文识别模型 +### 2.2 英文识别模型 |模型名称|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- | --- | @@ -65,7 +66,7 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 |en_number_mobile_v2.0_rec|原始超轻量模型，支持英文、数字识别|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.6M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) | -#### 3. 多语言识别模型（更多语言持续更新中...） +### 2.3 多语言识别模型（更多语言持续更新中...） |模型名称|字典文件|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- |--- | --- | @@ -86,7 +87,7 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 -### 三、文本方向分类模型 +## 3. 文本方向分类模型 |模型名称|模型简介|配置文件|推理模型大小|下载地址| | --- | --- | --- | --- | --- | @@ -95,7 +96,7 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 -### 四、Paddle-Lite 模型 +## 4. Paddle-Lite 模型 |模型版本|模型简介|模型大小|检测模型|文本方向分类模型|识别模型|Paddle-Lite版本| |---|---|---|---|---|---|---| diff --git a/doc/doc_ch/pgnet.md b/doc/doc_ch/pgnet.md index e79c2388ea0047a75ceec3dcb3c1d762c3702b2b..9aa7f255e54ce8dec3a20d475cccb71847d95cc7 100644 --- a/doc/doc_ch/pgnet.md +++ b/doc/doc_ch/pgnet.md @@ -28,9 +28,9 @@ PGNet算法细节详见[论文](https://www.aaai.org/AAAI21Papers/AAAI-2885.Wang ### 性能指标 -测试集: Total Text +#### 测试集: Total Text -测试环境: NVIDIA Tesla V100-SXM2-16GB +#### 测试环境: NVIDIA Tesla V100-SXM2-16GB |PGNetA|det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|下载| | --- | --- | --- | --- | --- | --- | --- | --- | --- | @@ -43,7 +43,7 @@ PGNet算法细节详见[论文](https://www.aaai.org/AAAI21Papers/AAAI-2885.Wang ## 二、环境配置 -请先参考[快速安装](./installation.md)配置PaddleOCR运行环境。 +请先参考[《运行环境准备》](./environment.md)配置PaddleOCR运行环境，参考[《PaddleOCR全景图与项目克隆》](./paddleOCR_overview.md)克隆项目 ## 三、快速使用 @@ -92,7 +92,7 @@ python3 tools/infer/predict_e2e.py --e2e_algorithm="PGNet" --image_dir="./doc/im |- train.txt # total_text数据集的训练标注 ``` -total_text.txt标注文件格式如下，文件名和标注信息中间用"\t"分隔： +train.txt标注文件格式如下，文件名和标注信息中间用"\t"分隔： ``` " 图像文件名 json.dumps编码的图像标注信息" rgb/img11.jpg [{"transcription": "ASRAMA", "points": [[214.0, 325.0], [235.0, 308.0], [259.0, 296.0], [286.0, 291.0], [313.0, 295.0], [338.0, 305.0], [362.0, 320.0], [349.0, 347.0], [330.0, 337.0], [310.0, 329.0], [290.0, 324.0], [269.0, 328.0], [249.0, 336.0], [231.0, 346.0]]}, {...}] diff --git a/doc/doc_ch/quickstart.md b/doc/doc_ch/quickstart.md index 1896d7a137f0768c6b2a8e0c02b18ff61fbfd03c..d9ff5a628fbd8d8effd50fb2b276d89d5e13225a 100644 --- a/doc/doc_ch/quickstart.md +++ b/doc/doc_ch/quickstart.md @@ -47,10 +47,10 @@ cd /path/to/ppocr_img #### 2.1.1 中英文模型 -* 检测+方向分类器+识别全流程：设置方向分类器参数`--use_angle_cls true`后可对竖排文本进行识别。 +* 检测+方向分类器+识别全流程：`--use_angle_cls true`设置使用方向分类器识别180度旋转文字，`--use_gpu false`设置不使用GPU ```bash - paddleocr --image_dir ./imgs/11.jpg --use_angle_cls true + paddleocr --image_dir ./imgs/11.jpg --use_angle_cls true --use_gpu false ``` 结果是一个list，每个item包含了文本框，文字和识别置信度 diff --git a/doc/doc_ch/reference.md b/doc/doc_ch/reference.md index f1337dedc96c685173cbcc8450a57c259d2c0029..3347447741a7852b30e793bd0d30696c190598a0 100644 --- a/doc/doc_ch/reference.md +++ b/doc/doc_ch/reference.md @@ -112,4 +112,14 @@ year={2016} } +13.NRTR +@misc{sheng2019nrtr, + title={NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition}, + author={Fenfen Sheng and Zhineng Chen and Bo Xu}, + year={2019}, + eprint={1806.00926}, + archivePrefix={arXiv}, + primaryClass={cs.CV} +} + ``` diff --git a/doc/doc_ch/thirdparty.md b/doc/doc_ch/thirdparty.md new file mode 100644 index 0000000000000000000000000000000000000000..45e82264045867bdb7b58bdb1bdd2776c0459107 --- /dev/null +++ b/doc/doc_ch/thirdparty.md @@ -0,0 +1,89 @@ +# 社区贡献说明 + +感谢大家长久以来对PaddleOCR的支持和关注，与广大开发者共同构建一个专业、和谐、相互帮助的开源社区是PaddleOCR的目标。本文档展示了已有的社区贡献、对于各类贡献说明、新的机会与流程，希望贡献流程更加高效、路径更加清晰。 + +PaddleOCR希望可以通过AI的力量助力任何一位有梦想的开发者实现自己的想法，享受创造价值带来的愉悦。 + + + + + +> 上图为PaddleOCR目前的Contributor，定期更新 + +## 1. 社区贡献 + +### 1.1 为PaddleOCR新增功能 + +- 非常感谢 [authorfu](https://github.com/authorfu) 贡献Android([#340](https://github.com/PaddlePaddle/PaddleOCR/pull/340))和[xiadeye](https://github.com/xiadeye) 贡献IOS的demo代码([#325](https://github.com/PaddlePaddle/PaddleOCR/pull/325)) +- 非常感谢 [tangmq](https://gitee.com/tangmq) 给PaddleOCR增加Docker化部署服务，支持快速发布可调用的Restful API服务([#507](https://github.com/PaddlePaddle/PaddleOCR/pull/507))。 +- 非常感谢 [lijinhan](https://github.com/lijinhan) 给PaddleOCR增加java SpringBoot 调用OCR Hubserving接口完成对OCR服务化部署的使用([#1027](https://github.com/PaddlePaddle/PaddleOCR/pull/1027))。 +- 非常感谢 [Evezerest](https://github.com/Evezerest)， [ninetailskim](https://github.com/ninetailskim)， [edencfc](https://github.com/edencfc)， [BeyondYourself](https://github.com/BeyondYourself)， [1084667371](https://github.com/1084667371) 贡献了[PPOCRLabel](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/PPOCRLabel/README_ch.md) 的完整代码。 + +### 1.2 基于PaddleOCR开发的工具 + +- 【最新】[包建强](https://gitee.com/BaoJianQiang) 使用PaddleOCR构建了完整的C#版本标注工具 [FastOCRLabel](https://gitee.com/BaoJianQiang/FastOCRLabel) + +### 1.3 代码与文档优化 + + +- 非常感谢 [zhangxin](https://github.com/ZhangXinNan)([Blog](https://blog.csdn.net/sdlypyzq)) 贡献新的可视化方式、添加.gitgnore、处理手动设置PYTHONPATH环境变量的问题([#210](https://github.com/PaddlePaddle/PaddleOCR/pull/210))。 +- 非常感谢 [lyl120117](https://github.com/lyl120117) 贡献打印网络结构的代码([#304](https://github.com/PaddlePaddle/PaddleOCR/pull/304))。 +- 非常感谢 [BeyondYourself](https://github.com/BeyondYourself) 给PaddleOCR提了很多非常棒的建议，并简化了PaddleOCR的部分代码风格([so many commits)](https://github.com/PaddlePaddle/PaddleOCR/commits?author=BeyondYourself)。 + +- 非常感谢 [Khanh Tran](https://github.com/xxxpsyduck) 和 [Karl Horky](https://github.com/karlhorky) 贡献修改英文文档。 + +### 1.4 多语言语料 + +- 非常感谢 [xiangyubo](https://github.com/xiangyubo) 贡献手写中文OCR数据集([#321](https://github.com/PaddlePaddle/PaddleOCR/pull/321))。 +- 非常感谢 [Mejans](https://github.com/Mejans) 给PaddleOCR增加新语言奥克西坦语Occitan的字典和语料([#954](https://github.com/PaddlePaddle/PaddleOCR/pull/954))。 + + + +## 2. 贡献说明 +### 2.1 新增功能类 + +PaddleOCR非常欢迎社区贡献以PaddleOCR为核心的各种服务、部署实例与软件应用，经过认证的社区贡献会被添加在上述社区贡献表中，为广大开发者增加曝光，也是PaddleOCR的荣耀，其中： + +- 项目形式：官方社区认证的项目代码应有良好的规范和结构，同时，还应配备一个详细的README.md，说明项目的使用方法。通过在requirements.txt文件中增加一行 `paddleocr` 可以自动收录到usedby中。 + +- 合入方式：如果是对PaddleOCR现有工具的更新升级，则会合入主repo。如果为PaddleOCR拓展了新功能，请先与官方人员联系，确认项目是否合入主repo，*即使新功能未合入主repo，我们同样也会以社区贡献的方式为您的个人项目增加曝光。* + + +### 2.2 代码优化 + +如果您在使用PaddleOCR时遇到了代码bug、功能不符合预期等问题，可以为PaddleOCR贡献您的修改，其中： + +- Python代码规范可参考[附录1：Python代码规范](./code_and_doc.md/#附录1)。 + +- 提交代码前请再三确认不会引入新的bug，并在PR中描述优化点。如果该PR解决了某个issue，请在PR中连接到该issue。所有的PR都应该遵守附录3中的[3.2.10 提交代码的一些约定。](./code_and_doc.md/#提交代码的一些约定) + +- 请在提交之前参考下方的[附录3：Pull Request说明](./code_and_doc.md/#附录3)。如果您对git的提交流程不熟悉，同样可以参考附录3的3.2节。 + +**最后请在PR的题目中加上标签`【improvement】` , 在说明中@Evezerest，拥有此标签的PR将会被高优处理**。 + +### 2.3 文档优化 + +如果您在使用PaddleOCR时遇到了文档表述不清楚、描述缺失、链接失效等问题，可以为PaddleOCR贡献您的修改。文档书写规范请参考[附录2：文档规范](./code_and_doc.md/#附录2)。**最后请在PR的题目中加上标签`【improvement】` , 在说明中@Evezerest，拥有此标签的PR将会被高优处理。** + +## 3. 更多贡献机会 + +我们非常鼓励开发者使用PaddleOCR实现自己的想法，同时我们也列出一些经过分析后认为有价值的拓展方向，供大家参考 + +- 功能类：IOS端侧demo、前后处理工具、针对各种垂类场景的检测识别模型（如手写体、公式、表格）。 +- 文档类：PaddleOCR在各种垂类行业的应用案例。 + +## 4. 联系我们 + +PaddleOCR非常欢迎广大开发者在有意向贡献前与我们联系，这样可以大大降低PR过程中的沟通成本。同时，如果您觉得某些想法个人难以实现，我们也可以通过SIG的形式定向为项目招募志同道合的开发者一起共建。通过SIG渠道贡献的项目将会获得深层次的研发支持与运营资源。 + +我们推荐的贡献流程是： + +- 通过 `【improvement】` 标记的github issue说明遇到的问题（以及解决的思路）或想拓展的功能，等待值班人员回复。 +- 与我们沟通确认技术方案或bug、优化点准确无误后进行功能新增或相应的修改，代码与文档遵循相关规范。 +- PR链接到上述issue，等待review。 + +## 5. 致谢与后续 + + - 合入代码之后，首页README末尾新增感谢贡献，默认链接为github名字及主页，如果有需要更换主页，也可以联系我们。 + - 新增重要功能类，会在用户群广而告之，享受开源社区荣誉时刻。 + - 如果您有基于PaddleOCR的贡献，但未出现在上述列表中，请按照同样的方式联系我们。 diff --git a/doc/doc_ch/training.md b/doc/doc_ch/training.md index d2deea6f205e0402e8c9c0010d5d8dd3e325fa3b..7fca061b82ad0c3b9ee83b67f6238a3c75965ce8 100644 --- a/doc/doc_ch/training.md +++ b/doc/doc_ch/training.md @@ -1,4 +1,4 @@ -# 模型训练 +# PP-OCR模型训练 本文将介绍模型训练时需掌握的基本概念，和训练时的调优方法。 @@ -15,13 +15,19 @@ * [3.3 自己构建数据集](#自己构建数据集) * [4. 常见问题](#常见问题) + + +## 1. 配置文件说明 + +PaddleOCR模型使用配置文件管理网络训练、评估的参数。在配置文件中，可以设置组建模型、优化器、损失函数、模型前后处理的参数，PaddleOCR从配置文件中读取到这些参数，进而组建出完整的训练流程，完成模型训练，在需要对模型进行优化的时，可以通过修改配置文件中的参数完成配置，使用简单且方便修改。 + +完整的配置文件说明可以参考[配置文件](./config.md) + -## 1. 基本概念 -OCR(Optical Character Recognition,光学字符识别)是指对图像进行分析识别处理，获取文字和版面信息的过程，是典型的计算机视觉任务， -通常由文本检测和文本识别两个子任务构成。 +## 2. 基本概念 -模型调优时需要关注以下参数： +模型训练过程中需要手动调整一些超参数，帮助模型以最小的代价获得最优指标。不同的数据量可能需要不同的超参，当您希望在自己的数据上finetune或对模型效果调优时，有以下几个参数调整策略可供参考： ### 2.1 学习率 @@ -132,8 +138,13 @@ PaddleOCR主要聚焦通用OCR，如果有垂类需求，您可以用PaddleOCR+ A：识别模型训练初期acc为0是正常的，多训一段时间指标就上来了。 + *** -具体的训练教程可点击下方链接跳转： -- [文本检测模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/detection.md) -- [文本识别模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/recognition.md) -- [文本方向分类器训练](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/angle_class.md) \ No newline at end of file + +具体的训练教程可点击下方链接跳转： + +\- [文本检测模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/detection.md) + +\- [文本识别模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/recognition.md) + +\- [文本方向分类器训练](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/angle_class.md) diff --git a/doc/doc_en/add_new_algorithm_en.md b/doc/doc_en/add_new_algorithm_en.md index dc81f1820f5d72a54f66fcddd716f18e5f6607e4..db72fe7d4b4b5b5d12e06ff34140c9da1186319b 100644 --- a/doc/doc_en/add_new_algorithm_en.md +++ b/doc/doc_en/add_new_algorithm_en.md @@ -1,4 +1,4 @@ -# Add new algorithm +# Add New Algorithm PaddleOCR decomposes an algorithm into the following parts, and modularizes each part to make it more convenient to develop new algorithms. @@ -263,7 +263,7 @@ Metric: main_indicator: acc ``` -## 优化器 +## Optimizer The optimizer is used to train the network. The optimizer also contains network regularization and learning rate decay modules. This part is under [ppocr/optimizer](../../ppocr/optimizer). PaddleOCR has built-in Commonly used optimizer modules such as `Momentum`, `Adam` and `RMSProp`, common regularization modules such as `Linear`, `Cosine`, `Step` and `Piecewise`, and common learning rate decay modules such as `L1Decay` and `L2Decay`. diff --git a/doc/doc_en/algorithm_overview_en.md b/doc/doc_en/algorithm_overview_en.md index df8a4ce3ef5fbcadb7ebdfd8ddf2bdf59637783e..4d521c9cd35d4dbde9b8c83d8a7e5ebbd84e59c9 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). @@ -8,31 +17,32 @@ 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)) -- [x] DB([paper](https://arxiv.org/abs/1911.08947)) -- [x] SAST([paper](https://arxiv.org/abs/1908.05498)) -- [x] PSE([paper](https://arxiv.org/abs/1903.12473v2)) +- [x] EAST([paper](https://arxiv.org/abs/1704.03155))[2] +- [x] DB([paper](https://arxiv.org/abs/1911.08947))[1] +- [x] SAST([paper](https://arxiv.org/abs/1908.05498))[4] +- [x] PSENet([paper](https://arxiv.org/abs/1903.12473v2)） On the ICDAR2015 dataset, the text detection result is as follows: -|Model|Backbone|precision|recall|Hmean|Download link| +|Model|Backbone|Precision|Recall|Hmean|Download link| | --- | --- | --- | --- | --- | --- | -|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[Download link](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%|[Download link](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%|[Download link](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%|[Download link](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%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)| -|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)| -|PSE|MobileNetV3|82.20%|70.48%|75.89%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)| +|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[trained model](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%|[trained model](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%|[trained model](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%|[trained model](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%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)| +|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[trianed model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)| +|PSE|MobileNetV3|82.20%|70.48%|75.89%|[trianed model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)| On Total-Text dataset, the text detection result is as follows: -|Model|Backbone|precision|recall|Hmean|Download link| +|Model|Backbone|Precision|Recall|Hmean|Download link| | --- | --- | --- | --- | --- | --- | -|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[Download link](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%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)| **Note：** Additional data, like icdar2013, icdar2017, COCO-Text, ArT, was added to the model training of SAST. Download English public dataset in organized format used by PaddleOCR from: * [Baidu Drive](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (download code: 2bpi). @@ -41,31 +51,41 @@ 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)) -- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085)) -- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html)) -- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1)) -- [x] SRN([paper](https://arxiv.org/abs/2003.12294)) -- [x] NRTR([paper](https://arxiv.org/abs/1806.00926v2)) +- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7] +- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))[10] +- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11] +- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))[12] +- [x] SRN([paper](https://arxiv.org/abs/2003.12294))[5] +- [x] NRTR([paper](https://arxiv.org/abs/1806.00926v2))[13] - [x] SAR([paper](https://arxiv.org/abs/1811.00751v2)) +- [x] SEED([paper](https://arxiv.org/pdf/2005.10977.pdf)) Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow: |Model|Backbone|Avg Accuracy|Module combination|Download link| |---|---|---|---|---| -|Rosetta|Resnet34_vd|80.9%|rec_r34_vd_none_none_ctc|[Download link](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|[Download link](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|[Download link](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|[Download link](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|[Download link](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|[Download link](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 |[Download link](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 |[Download link](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 |[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) | -|SAR|Resnet31| 87.2% | rec_r31_sar | [Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_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) +|Rosetta|Resnet34_vd|80.9%|rec_r34_vd_none_none_ctc|[trained model](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|[trained model](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|[trained model](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|[trained model](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|[trained model](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|[trained model](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 |[trained model](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 |[trained model](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 |[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar)| +|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) | +|SAR|Resnet31| 87.2% | rec_r31_sar | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_r31_sar_train.tar) | +|SEED|Aster_Resnet| 85.2% | rec_resnet_stn_bilstm_att | [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/rec/rec_resnet_stn_bilstm_att.tar) | + +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) diff --git a/doc/doc_en/angle_class_en.md b/doc/doc_en/angle_class_en.md index 46d91bee43de3af99659651b7f31cf1148e7b294..b7fcd63e070318d3aab37714a1213ad9f56cb6fc 100644 --- a/doc/doc_en/angle_class_en.md +++ b/doc/doc_en/angle_class_en.md @@ -15,7 +15,6 @@ The text line image obtained after text detection is sent to the recognition mod Example of 0 and 180 degree data samples： ![](../imgs_results/angle_class_example.jpg) -### DATA PREPARATION ## 2. Data Preparation @@ -131,8 +130,6 @@ python3 tools/eval.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/ ## 5. Prediction -### PREDICTION - * Training engine prediction Using the model trained by paddleocr, you can quickly get prediction through the following script. diff --git a/doc/doc_en/config_en.md b/doc/doc_en/config_en.md index ce76da9b2f39532b387e3e45ca2ff497b0408635..9742c3d18ae52191106c5e08371cef1c09238bf6 100644 --- a/doc/doc_en/config_en.md +++ b/doc/doc_en/config_en.md @@ -1,4 +1,4 @@ -# Configuration +# Configuration - [1. Optional Parameter List](#1-optional-parameter-list) - [2. Intorduction to Global Parameters of Configuration File](#2-intorduction-to-global-parameters-of-configuration-file) @@ -36,10 +36,10 @@ Take rec_chinese_lite_train_v2.0.yml as an example | pretrained_model | Set the path of the pre-trained model | ./pretrain_models/CRNN/best_accuracy | \ | | checkpoints | set model parameter path | None | Used to load parameters after interruption to continue training| | use_visualdl | Set whether to enable visualdl for visual log display | False | [Tutorial](https://www.paddlepaddle.org.cn/paddle/visualdl) | -| infer_img | Set inference image path or folder path | ./infer_img | \| -| character_dict_path | Set dictionary path | ./ppocr/utils/ppocr_keys_v1.txt | If the character_dict_path is None, model can only recognize number and lower letters | +| infer_img | Set inference image path or folder path | ./infer_img | \|| +| character_dict_path | Set dictionary path | ./ppocr/utils/ppocr_keys_v1.txt | If the character_dict_path is None, model can only recognize number and lower letters | | max_text_length | Set the maximum length of text | 25 | \ | -| use_space_char | Set whether to recognize spaces | True | Only support in character_type=ch mode | +| use_space_char | Set whether to recognize spaces | True | \| | | label_list | Set the angle supported by the direction classifier | ['0','180'] | Only valid in angle classifier model | | save_res_path | Set the save address of the test model results | ./output/det_db/predicts_db.txt | Only valid in the text detection model | @@ -196,21 +196,21 @@ Italian is made up of Latin letters, so after executing the command, you will ge epoch_num: 500 ... character_dict_path: {path/of/dict} # path of dict - + Train: dataset: name: SimpleDataSet data_dir: train_data/ # root directory of training data label_file_list: ["./train_data/train_list.txt"] # train label path ... - + Eval: dataset: name: SimpleDataSet data_dir: train_data/ # root directory of val data label_file_list: ["./train_data/val_list.txt"] # val label path ... - + ``` @@ -220,12 +220,12 @@ Currently, the multi-language algorithms supported by PaddleOCR are: | :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | | rec_chinese_cht_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | chinese traditional | | rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | English(Case sensitive) | -| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | French | +| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | French | | rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | German | | rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Japanese | | rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Korean | | rec_latin_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Latin | -| rec_arabic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | arabic | +| rec_arabic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | arabic | | rec_cyrillic_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | cyrillic | | rec_devanagari_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | devanagari | diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md index 586ed30bb841122717e66966337b5c99b9cf3397..a634dd4903483a819caee88cf6dd1781253e6f85 100644 --- a/doc/doc_en/detection_en.md +++ b/doc/doc_en/detection_en.md @@ -235,6 +235,7 @@ python3 tools/infer/predict_det.py --det_algorithm="EAST" --det_model_dir="./out ## 5. FAQ Q1: The prediction results of trained model and inference model are inconsistent? + **A**: Most of the problems are caused by the inconsistency of the pre-processing and post-processing parameters during the prediction of the trained model and the pre-processing and post-processing parameters during the prediction of the inference model. Taking the model trained by the det_mv3_db.yml configuration file as an example, the solution to the problem of inconsistent prediction results between the training model and the inference model is as follows: - Check whether the [trained model preprocessing](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116) is consistent with the prediction [preprocessing function of the inference model](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42). When the algorithm is evaluated, the input image size will affect the accuracy. In order to be consistent with the paper, the image is resized to [736, 1280] in the training icdar15 configuration file, but there is only a set of default parameters when the inference model predicts, which will be considered To predict the speed problem, the longest side of the image is limited to 960 for resize by default. The preprocessing function of the training model preprocessing and the inference model is located in [ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147) - Check whether the [post-processing of the trained model](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51) is consistent with the [post-processing parameters of the inference](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50). diff --git a/doc/doc_en/environment_en.md b/doc/doc_en/environment_en.md index 9aad92cafb809a0eec519808b1c1755403b39318..854db648fc255d36ec5c01c710a1d3cab53aaeb5 100644 --- a/doc/doc_en/environment_en.md +++ b/doc/doc_en/environment_en.md @@ -1,5 +1,7 @@ # Environment Preparation +Windows and Mac users are recommended to use Anaconda to build a Python environment, and Linux users are recommended to use docker to build a Python environment. If you are familiar with the Python environment, you can skip to step 2 to install PaddlePaddle. + Recommended working environment: - PaddlePaddle >= 2.0.0 (2.1.2) - python3.7 diff --git a/doc/doc_en/inference_ppocr_en.md b/doc/doc_en/inference_ppocr_en.md index fa3b1c88713f01e8e411cf95d107b4b58dd7f4e1..62a672885c86119ae56dc93ef76c2bb746084a05 100755 --- a/doc/doc_en/inference_ppocr_en.md +++ b/doc/doc_en/inference_ppocr_en.md @@ -1,17 +1,14 @@ -# Python Inference for PP-OCR Model Library +# Python Inference for PP-OCR Model Zoo This article introduces the use of the Python inference engine for the PP-OCR model library. The content is in order of text detection, text recognition, direction classifier and the prediction method of the three in series on the CPU and GPU. - [Text Detection Model Inference](#DETECTION_MODEL_INFERENCE) - - [Text Recognition Model Inference](#RECOGNITION_MODEL_INFERENCE) - [1. Lightweight Chinese Recognition Model Inference](#LIGHTWEIGHT_RECOGNITION) - [2. Multilingaul Model Inference](#MULTILINGUAL_MODEL_INFERENCE) - - [Angle Classification Model Inference](#ANGLE_CLASS_MODEL_INFERENCE) - - [Text Detection Angle Classification and Recognition Inference Concatenation](#CONCATENATION) @@ -22,10 +19,10 @@ The default configuration is based on the inference setting of the DB text detec ``` # download DB text detection inference model -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar -tar xf ch_ppocr_mobile_v2.0_det_infer.tar -# predict -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" +wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar +tar xf ch_PP-OCRv2_det_infer.tar +# run inference +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv2_det_infer.tar/" ``` The visual text detection results are saved to the ./inference_results folder by default, and the name of the result file is prefixed with'det_res'. Examples of results are as follows: @@ -42,12 +39,12 @@ Set as `limit_type='min', det_limit_side_len=960`, it means that the shortest si If the resolution of the input picture is relatively large and you want to use a larger resolution prediction, you can set det_limit_side_len to the desired value, such as 1216: ``` -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --det_limit_type=max --det_limit_side_len=1216 +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --det_limit_type=max --det_limit_side_len=1216 ``` If you want to use the CPU for prediction, execute the command as follows ``` -python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --use_gpu=False +python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --use_gpu=False ``` @@ -62,9 +59,10 @@ For lightweight Chinese recognition model inference, you can execute the followi ``` # download CRNN text recognition inference model -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar -tar xf ch_ppocr_mobile_v2.0_rec_infer.tar -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_10.png" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer" +wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar +tar xf ch_PP-OCRv2_rec_infer.tar +# run inference +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./ch_PP-OCRv2_rec_infer/" ``` ![](../imgs_words_en/word_10.png) @@ -78,10 +76,12 @@ Predicts of ./doc/imgs_words_en/word_10.png:('PAIN', 0.9897658) ### 2. Multilingaul Model Inference -If you need to predict other language models, when using inference model prediction, you need to specify the dictionary path used by `--rec_char_dict_path`. At the same time, in order to get the correct visualization results, +If you need to predict [other language models](./models_list_en.md#Multilingual), when using inference model prediction, you need to specify the dictionary path used by `--rec_char_dict_path`. At the same time, in order to get the correct visualization results, You need to specify the visual font path through `--vis_font_path`. There are small language fonts provided by default under the `doc/fonts` path, such as Korean recognition: ``` +wget wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar + python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf" ``` ![](../imgs_words/korean/1.jpg) @@ -120,13 +120,13 @@ When performing prediction, you need to specify the path of a single image or a ```shell # use direction classifier -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --cls_model_dir="./inference/cls/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=true +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --cls_model_dir="./inference/cls/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=true # not use use direction classifier -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --rec_model_dir="./inference/rec_crnn/" +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=false # use multi-process -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/det_db/" --rec_model_dir="./inference/rec_crnn/" --use_angle_cls=false --use_mp=True --total_process_num=6 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv2_det_infer/" --rec_model_dir="./inference/ch_PP-OCRv2_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 ``` diff --git a/doc/doc_en/models_list_en.md b/doc/doc_en/models_list_en.md index 3b9b5518701f052079af1398a4fa3e3770eb12a1..dbb4860279cd25a888a6bfaf64dbe1952ef54470 100644 --- a/doc/doc_en/models_list_en.md +++ b/doc/doc_en/models_list_en.md @@ -1,4 +1,4 @@ -## OCR model list（V2.1, updated on 2021.9.6） +# OCR Model List（V2.1, updated on 2021.9.6） > **Note** > 1. Compared with the model v2.0, the 2.1 version of the detection model has a improvement in accuracy, and the 2.1 version of the recognition model is optimized in accuracy and CPU speed. > 2. Compared with [models 1.1](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md), which are trained with static graph programming paradigm, models 2.0 are the dynamic graph trained version and achieve close performance. @@ -6,9 +6,9 @@ - [1. Text Detection Model](#Detection) - [2. Text Recognition Model](#Recognition) - - [Chinese Recognition Model](#Chinese) - - [English Recognition Model](#English) - - [Multilingual Recognition Model](#Multilingual) + - [2.1 Chinese Recognition Model](#Chinese) + - [2.2 English Recognition Model](#English) + - [2.3 Multilingual Recognition Model](#Multilingual) - [3. Text Angle Classification Model](#Angle) - [4. Paddle-Lite Model](#Paddle-Lite) @@ -25,26 +25,26 @@ Relationship of the above models is as follows. ![](../imgs_en/model_prod_flow_en.png) -### 1. Text Detection Model +## 1. Text Detection Model |model name|description|config|model size|download| | --- | --- | --- | --- | --- | -|ch_PP-OCRv2_det_slim|slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)| 3M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar)| -|ch_PP-OCRv2_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| +|ch_PP-OCRv2_det_slim|[New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)| 3M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar)| +|ch_PP-OCRv2_det|[New] Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCR_det_cml.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)| |ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|2.6M |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_infer.tar)| |ch_ppocr_mobile_v2.0_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)| |ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)| -### 2. Text Recognition Model +## 2. Text Recognition Model -#### Chinese Recognition Model +### 2.1 Chinese Recognition Model |model name|description|config|model size|download| | --- | --- | --- | --- | --- | -|ch_PP-OCRv2_rec_slim|Slim qunatization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) | -|ch_PP-OCRv2_rec|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)|8.5M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) | +|ch_PP-OCRv2_rec_slim|[New] Slim qunatization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) | +|ch_PP-OCRv2_rec|[New] Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)|8.5M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) | |ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| 6M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_slim_train.tar) | |ch_ppocr_mobile_v2.0_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|5.2M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) | |ch_ppocr_server_v2.0_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) | @@ -53,7 +53,7 @@ Relationship of the above models is as follows. **Note:** The `trained model` is finetuned on the `pre-trained model` with real data and synthsized vertical text data, which achieved better performance in real scene. The `pre-trained model` is directly trained on the full amount of real data and synthsized data, which is more suitable for finetune on your own dataset. -#### English Recognition Model +### 2.2 English Recognition Model |model name|description|config|model size|download| | --- | --- | --- | --- | --- | @@ -61,7 +61,7 @@ Relationship of the above models is as follows. |en_number_mobile_v2.0_rec|Original lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) | -#### Multilingual Recognition Model（Updating...） +### 2.3 Multilingual Recognition Model（Updating...） |model name| dict file | description|config|model size|download| | --- | --- | --- |--- | --- | --- | @@ -82,7 +82,7 @@ For more supported languages, please refer to : [Multi-language model](./multi_l -### 3. Text Angle Classification Model +## 3. Text Angle Classification Model |model name|description|config|model size|download| | --- | --- | --- | --- | --- | @@ -90,7 +90,7 @@ For more supported languages, please refer to : [Multi-language model](./multi_l |ch_ppocr_mobile_v2.0_cls|Original model for text angle classification|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | -### 4. Paddle-Lite Model +## 4. Paddle-Lite Model |Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle-Lite branch| |---|---|---|---|---|---|---| |PP-OCRv2|extra-lightweight chinese OCR optimized model|11M|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_ppocr_mobile_v2.0_cls_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer_opt.nb)|v2.9| diff --git a/doc/doc_en/pgnet_en.md b/doc/doc_en/pgnet_en.md index 9c46802b5b5273110a80cd5da8916f43e5f4883f..d2c6b30248ebad920c41ca53ee38cce828dddb8c 100644 --- a/doc/doc_en/pgnet_en.md +++ b/doc/doc_en/pgnet_en.md @@ -24,9 +24,9 @@ The results of detection and recognition are as follows: ![](../imgs_results/e2e_res_img293_pgnet.png) ![](../imgs_results/e2e_res_img295_pgnet.png) ### Performance -####Test set: Total Text +#### Test set: Total Text -####Test environment: NVIDIA Tesla V100-SXM2-16GB +#### Test environment: NVIDIA Tesla V100-SXM2-16GB |PGNetA|det_precision|det_recall|det_f_score|e2e_precision|e2e_recall|e2e_f_score|FPS|download| | --- | --- | --- | --- | --- | --- | --- | --- | --- | |Paper|85.30|86.80|86.1|-|-|61.7|38.20 (size=640)|-| @@ -36,7 +36,7 @@ The results of detection and recognition are as follows: ## 2. Environment Configuration -Please refer to [Quick Installation](./installation_en.md) Configure the PaddleOCR running environment. +Please refer to [Operation Environment Preparation](./environment_en.md) to configure PaddleOCR operating environment first, refer to [PaddleOCR Overview and Project Clone](./paddleOCR_overview_en.md) to clone the project ## 3. Quick Use diff --git a/doc/doc_en/quickstart_en.md b/doc/doc_en/quickstart_en.md index 0055d8f7a89d0d218d001ea94fd4c620de5d037f..9ed83aceb9f562ac3099f22eaf264b966c0d48c7 100644 --- a/doc/doc_en/quickstart_en.md +++ b/doc/doc_en/quickstart_en.md @@ -53,10 +53,10 @@ If you do not use the provided test image, you can replace the following `--imag #### 2.1.1 Chinese and English Model -* Detection, direction classification and recognition: set the direction classifier parameter`--use_angle_cls true` to recognize vertical text. +* Detection, direction classification and recognition: set the parameter`--use_gpu false` to disable the gpu device ```bash - paddleocr --image_dir ./imgs_en/img_12.jpg --use_angle_cls true --lang en + paddleocr --image_dir ./imgs_en/img_12.jpg --use_angle_cls true --lang en --use_gpu false ``` Output will be a list, each item contains bounding box, text and recognition confidence diff --git a/doc/doc_en/training_en.md b/doc/doc_en/training_en.md index aa5500ac88fef97829b4f19c5421e36f18ae1812..d013f5ac706a2a2b4a5b58ba0a6dff09ab0b4654 100644 --- a/doc/doc_en/training_en.md +++ b/doc/doc_en/training_en.md @@ -25,11 +25,10 @@ The PaddleOCR model uses configuration files to manage network training and eval For the complete configuration file description, please refer to [Configuration File](./config_en.md) -# 1. Basic concepts ## 2. Basic Concepts -The following parameters need to be paid attention to when tuning the model: +In the process of model training, some hyperparameters need to be manually adjusted to help the model obtain the optimal index at the least loss. Different data volumes may require different hyper-parameters. When you want to finetune your own data or tune the model effect, there are several parameter adjustment strategies for reference: ### 2.1 Learning Rate @@ -53,7 +52,7 @@ and the learning rate is the same in each stage. warmup_epoch means that in the first 5 epochs, the learning rate will gradually increase from 0 to base_lr. For all strategies, please refer to the code [learning_rate.py](../../ppocr/optimizer/learning_rate.py). -## 1.2 Regularization +### 2.2 Regularization Regularization can effectively avoid algorithm overfitting. PaddleOCR provides L1 and L2 regularization methods. L1 and L2 regularization are the most commonly used regularization methods. @@ -125,7 +124,7 @@ There are several experiences for reference when constructing the data set: -# 3. FAQ +## 4. FAQ **Q**: How to choose a suitable network input shape when training CRNN recognition? @@ -147,9 +146,10 @@ There are several experiences for reference when constructing the data set: A: It is normal for the acc to be 0 at the beginning of the recognition model training, and the indicator will come up after a longer training period. - *** + Click the following links for detailed training tutorial: + - [text detection model training](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/detection.md) - [text recognition model training](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/recognition.md) - [text direction classification model training](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.3/doc/doc_ch/angle_class.md) diff --git a/doc/joinus.PNG b/doc/joinus.PNG index 79bd3143d082636dc85a3a6d5f0601a05b4a784f..5f47e8da13894157c9c4b527c01463bdc395532b 100644 Binary files a/doc/joinus.PNG and b/doc/joinus.PNG differ diff --git a/doc/pr.png b/doc/pr.png new file mode 100644 index 0000000000000000000000000000000000000000..3d0d15f78d4cb5402a368f96ac79c1da74fabcb7 Binary files /dev/null and b/doc/pr.png differ