diff --git a/doc/doc_ch/knowledge_distillation.md b/doc/doc_ch/knowledge_distillation.md index 76ab5e62e0136bb8707a51537bf6693fc5687047..79c4418d535cc7989360bc581974dc2d55cf1890 100644 --- a/doc/doc_ch/knowledge_distillation.md +++ b/doc/doc_ch/knowledge_distillation.md @@ -424,9 +424,9 @@ Architecture: ``` -如果是采用DML，即两个小模型互相学习的方法，上述配置文件里的Teacher网络结构需要设置为Student模型一样的配置，具体参考配置文件[ch_PP-OCRv3_det_dml.yml](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_dml.yml)。 - -下面介绍[ch_PP-OCRv3_det_cml.yml](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)的配置文件参数： +如果是采用DML，即两个小模型互相学习的方法，上述配置文件里的Teacher网络结构需要设置为Student模型一样的配置，具体参考配置文件[ch_PP-OCRv3_det_dml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_dml.yml)。 + +下面介绍[ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)的配置文件参数： ``` Architecture: diff --git a/doc/doc_ch/multi_languages.md b/doc/doc_ch/multi_languages.md index 499fdd9881563b3a784b5f4ba4feace54f1a3a6a..1f337bdf49f4c6f90b8b35af85bc1316dae308a4 100644 --- a/doc/doc_ch/multi_languages.md +++ b/doc/doc_ch/multi_languages.md @@ -238,10 +238,10 @@ python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs ## 4 预测部署 除了安装whl包进行快速预测，ppocr 也提供了多种预测部署方式，如有需求可阅读相关文档： -- [基于Python脚本预测引擎推理](./inference.md) -- [基于C++预测引擎推理](../../deploy/cpp_infer/readme.md) +- [基于Python脚本预测引擎推理](./inference_ppocr.md) +- [基于C++预测引擎推理](../../deploy/cpp_infer/readme_ch.md) - [服务化部署](../../deploy/hubserving/readme.md) -- [端侧部署](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/deploy/lite/readme.md) +- [端侧部署](../../deploy/lite/readme_ch.md) - [Benchmark](./benchmark.md) diff --git a/doc/doc_ch/serving_inference.md b/doc/doc_ch/serving_inference.md deleted file mode 100644 index 30ea7ee7c11692ba02e8314036d74a21c2f090e5..0000000000000000000000000000000000000000 --- a/doc/doc_ch/serving_inference.md +++ /dev/null @@ -1,238 +0,0 @@ -# 使用Paddle Serving预测推理 - -阅读本文档之前，请先阅读文档 [基于Python预测引擎推理](./inference.md) - -同本地执行预测一样，我们需要保存一份可以用于Paddle Serving的模型。 - -接下来首先介绍如何将训练的模型转换成Paddle Serving模型，然后将依次介绍文本检测、文本识别以及两者串联基于预测引擎推理。 - -### 一、 准备环境 -我们先安装Paddle Serving相关组件 -我们推荐用户使用GPU来做Paddle Serving的OCR服务部署 - -**CUDA版本：9.X/10.X** - -**CUDNN版本：7.X** - -**操作系统版本：Linux/Windows** - -**Python版本： 2.7/3.5/3.6/3.7** - -**Python操作指南：** - -目前Serving用于OCR的部分功能还在测试当中，因此在这里我们给出[Servnig latest package](https://github.com/PaddlePaddle/Serving/blob/develop/doc/Latest_Packages_CN.md) -大家根据自己的环境选择需要安装的whl包即可，例如以Python 3.5为例，执行下列命令 -``` -#CPU/GPU版本选择一个 -#GPU版本服务端 -#CUDA 9 -python -m pip install -U https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post9-py3-none-any.whl -#CUDA 10 -python -m pip install -U https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server_gpu-0.0.0.post10-py3-none-any.whl -#CPU版本服务端 -python -m pip install -U https://paddle-serving.bj.bcebos.com/whl/paddle_serving_server-0.0.0-py3-none-any.whl -#客户端和App包使用以下链接（CPU，GPU通用） -python -m pip install -U https://paddle-serving.bj.bcebos.com/whl/paddle_serving_client-0.0.0-cp36-none-any.whl https://paddle-serving.bj.bcebos.com/whl/paddle_serving_app-0.0.0-py3-none-any.whl -``` - -## 二、训练模型转Serving模型 - -在前序文档 [基于Python预测引擎推理](./inference.md) 中，我们提供了如何把训练的checkpoint转换成Paddle模型。Paddle模型通常由一个文件夹构成，内含模型结构描述文件`model`和模型参数文件`params`。Serving模型由两个文件夹构成，用于存放客户端和服务端的配置。 - -我们以`ch_rec_r34_vd_crnn`模型作为例子，下载链接在： - -``` -wget --no-check-certificate https://paddleocr.bj.bcebos.com/ch_models/ch_rec_r34_vd_crnn_infer.tar -tar xf ch_rec_r34_vd_crnn_infer.tar -``` -因此我们按照Serving模型转换教程，运行下列python文件。 -``` -python tools/inference_to_serving.py --model_dir ch_rec_r34_vd_crnn -``` -最终会在`serving_client_dir`和`serving_server_dir`生成客户端和服务端的模型配置。其中`serving_server_dir`和`serving_client_dir`的名字可以自定义。最终文件结构如下 - -``` -/ch_rec_r34_vd_crnn/ -├── serving_client_dir # 客户端配置文件夹 -└── serving_server_dir # 服务端配置文件夹 -``` - -## 三、文本检测模型Serving推理 - -启动服务可以根据实际需求选择启动`标准版`或者`快速版`，两种方式的对比如下表： - -|版本|特点|适用场景| -|-|-|-| -|标准版|稳定性高，分布式部署|适用于吞吐量大，需要跨机房部署的情况| -|快速版|部署方便，预测速度快|适用于对预测速度要求高，迭代速度快的场景，Windows用户只能选择快速版| - -接下来的命令中，我们会指定快速版和标准版的命令。需要说明的是，标准版只能用Linux平台，快速版可以支持Linux/Windows。 -文本检测模型推理，默认使用DB模型的配置参数，识别默认为CRNN。 - -配置文件在`params.py`中，我们贴出配置部分，如果需要做改动，也在这个文件内部进行修改。 - -``` -def read_params(): - cfg = Config() - #use gpu - cfg.use_gpu = False # 是否使用GPU - cfg.use_pdserving = True # 是否使用paddleserving，必须为True - - #params for text detector - cfg.det_algorithm = "DB" # 检测算法， DB/EAST等 - cfg.det_model_dir = "./det_mv_server/" # 检测算法模型路径 - cfg.det_max_side_len = 960 - - #DB params - cfg.det_db_thresh =0.3 - cfg.det_db_box_thresh =0.5 - cfg.det_db_unclip_ratio =2.0 - - #EAST params - cfg.det_east_score_thresh = 0.8 - cfg.det_east_cover_thresh = 0.1 - cfg.det_east_nms_thresh = 0.2 - - #params for text recognizer - cfg.rec_algorithm = "CRNN" # 识别算法， CRNN/RARE等 - cfg.rec_model_dir = "./ocr_rec_server/" # 识别算法模型路径 - - cfg.rec_image_shape = "3, 32, 320" - cfg.rec_batch_num = 30 - cfg.max_text_length = 25 - - cfg.rec_char_dict_path = "./ppocr_keys_v1.txt" # 识别算法字典文件 - cfg.use_space_char = True - - #params for text classifier - cfg.use_angle_cls = True # 是否启用分类算法 - cfg.cls_model_dir = "./ocr_clas_server/" # 分类算法模型路径 - cfg.cls_image_shape = "3, 48, 192" - cfg.label_list = ['0', '180'] - cfg.cls_batch_num = 30 - cfg.cls_thresh = 0.9 - - return cfg -``` -与本地预测不同的是，Serving预测需要一个客户端和一个服务端，因此接下来的教程都是两行代码。 - -在正式执行服务端启动命令之前，先export PYTHONPATH到工程主目录下。 -``` -export PYTHONPATH=$PWD:$PYTHONPATH -cd deploy/pdserving -``` -为了方便用户复现Demo程序，我们提供了Chinese and English ultra-lightweight OCR model (8.1M)版本的Serving模型 -``` -wget --no-check-certificate https://paddleocr.bj.bcebos.com/deploy/pdserving/ocr_pdserving_suite.tar.gz -tar xf ocr_pdserving_suite.tar.gz -``` - -### 1. 超轻量中文检测模型推理 - -超轻量中文检测模型推理，可以执行如下命令启动服务端： - -``` -#根据环境只需要启动其中一个就可以 -python det_rpc_server.py #标准版，Linux用户 -python det_local_server.py #快速版，Windows/Linux用户 -``` - -客户端 - -``` -python det_web_client.py -``` - - -Serving的推测和本地预测不同点在于，客户端发送请求到服务端，服务端需要检测到文字框之后返回框的坐标，此处没有后处理的图片，只能看到坐标值。 - -## 四、文本识别模型Serving推理 - -下面将介绍超轻量中文识别模型推理、基于CTC损失的识别模型推理和基于Attention损失的识别模型推理。对于中文文本识别，建议优先选择基于CTC损失的识别模型，实践中也发现基于Attention损失的效果不如基于CTC损失的识别模型。此外，如果训练时修改了文本的字典，请参考下面的自定义文本识别字典的推理。 - -### 1. 超轻量中文识别模型推理 - -超轻量中文识别模型推理，可以执行如下命令启动服务端： -需要注意params.py中的`--use_gpu`的值 -``` -#根据环境只需要启动其中一个就可以 -python rec_rpc_server.py #标准版，Linux用户 -python rec_local_server.py #快速版，Windows/Linux用户 -``` -如果需要使用CPU版本，还需增加 `--use_gpu False`。 - -客户端 - -``` -python rec_web_client.py -``` - -![](../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： - -``` -{u'result': {u'score': [u'0.89547354'], u'pred_text': ['实力活力']}} -``` - - - -## 五、方向分类模型推理 - -下面将介绍方向分类模型推理。 - - - -### 1. 方向分类模型推理 - -方向分类模型推理， 可以执行如下命令启动服务端： -需要注意params.py中的`--use_gpu`的值 -``` -#根据环境只需要启动其中一个就可以 -python clas_rpc_server.py #标准版，Linux用户 -python clas_local_server.py #快速版，Windows/Linux用户 -``` - -客户端 - -``` -python rec_web_client.py -``` - -![](../imgs_words/ch/word_4.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： - -``` -{u'result': {u'direction': [u'0'], u'score': [u'0.9999963']}} -``` - - -## 六、文本检测、方向分类和文字识别串联Serving推理 - -### 1. 超轻量中文OCR模型推理 - -在执行预测时，需要通过参数`image_dir`指定单张图像或者图像集合的路径、参数`det_model_dir`,`cls_model_dir`和`rec_model_dir`分别指定检测，方向分类和识别的inference模型路径。参数`use_angle_cls`用于控制是否启用方向分类模型。与本地预测不同的是，为了减少网络传输耗时，可视化识别结果目前不做处理，用户收到的是推理得到的文字字段。 - -执行如下命令启动服务端： -需要注意params.py中的`--use_gpu`的值 -``` -#标准版，Linux用户 -#GPU用户 -python -m paddle_serving_server_gpu.serve --model det_infer_server --port 9293 --gpu_id 0 -python -m paddle_serving_server_gpu.serve --model cls_infer_server --port 9294 --gpu_id 0 -python ocr_rpc_server.py -#CPU用户 -python -m paddle_serving_server.serve --model det_infer_server --port 9293 -python -m paddle_serving_server.serve --model cls_infer_server --port 9294 -python ocr_rpc_server.py - -#快速版，Windows/Linux用户 -python ocr_local_server.py -``` - -客户端 - -``` -python rec_web_client.py -``` diff --git a/doc/doc_ch/update.md b/doc/doc_ch/update.md index 9927a228d270c0e4c5ddbd5ab2a0d35911c6a75a..07591ea126f5b168389657141673142c084e67ad 100644 --- a/doc/doc_ch/update.md +++ b/doc/doc_ch/update.md @@ -1,9 +1,9 @@ # 更新 - 2022.5.9 发布PaddleOCR v2.5。发布内容包括： - - [PP-OCRv3](./doc/doc_ch/ppocr_introduction.md#pp-ocrv3)，速度可比情况下，中文场景效果相比于PP-OCRv2再提升5%，英文场景提升11%，80语种多语言模型平均识别准确率提升5%以上； - - 半自动标注工具[PPOCRLabelv2](./PPOCRLabel)：新增表格文字图像、图像关键信息抽取任务和不规则文字图像的标注功能； + - [PP-OCRv3](./ppocr_introduction.md#pp-ocrv3)，速度可比情况下，中文场景效果相比于PP-OCRv2再提升5%，英文场景提升11%，80语种多语言模型平均识别准确率提升5%以上； + - 半自动标注工具[PPOCRLabelv2](../../PPOCRLabel)：新增表格文字图像、图像关键信息抽取任务和不规则文字图像的标注功能； - OCR产业落地工具集：打通22种训练部署软硬件环境与方式，覆盖企业90%的训练部署环境需求 - - 交互式OCR开源电子书[《动手学OCR》](./doc/doc_ch/ocr_book.md)，覆盖OCR全栈技术的前沿理论与代码实践，并配套教学视频。 + - 交互式OCR开源电子书[《动手学OCR》](./ocr_book.md)，覆盖OCR全栈技术的前沿理论与代码实践，并配套教学视频。 - 2022.5.7 添加对[Weights & Biases](https://docs.wandb.ai/)训练日志记录工具的支持。 - 2021.12.21 《OCR十讲》课程开讲，12月21日起每晚八点半线上授课！ 【免费】报名地址：https://aistudio.baidu.com/aistudio/course/introduce/25207 - 2021.12.21 发布PaddleOCR v2.4。OCR算法新增1种文本检测算法（PSENet），3种文本识别算法（NRTR、SEED、SAR）；文档结构化算法新增1种关键信息提取算法（SDMGR），3种DocVQA算法（LayoutLM、LayoutLMv2，LayoutXLM）。 diff --git a/doc/doc_en/algorithm_det_east_en.md b/doc/doc_en/algorithm_det_east_en.md index 3955809a49a595aa59717bafcfbb23146ae96bd2..07c434a9b162d9d373f5f357522cbd752be1afc1 100644 --- a/doc/doc_en/algorithm_det_east_en.md +++ b/doc/doc_en/algorithm_det_east_en.md @@ -40,7 +40,7 @@ Please prepare your environment referring to [prepare the environment](./environ The above EAST model is trained using the ICDAR2015 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](./dataset/ocr_datasets_en.md). -After the data download is complete, please refer to [Text Detection Training Tutorial](./detection.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models. +After the data download is complete, please refer to [Text Detection Training Tutorial](./detection_en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models. diff --git a/doc/doc_en/algorithm_det_fcenet_en.md b/doc/doc_en/algorithm_det_fcenet_en.md index e15fb9a07ede3296d3de83c134457194d4639a1c..f3c51a91a486342b86828167de5c1b386b42cc66 100644 --- a/doc/doc_en/algorithm_det_fcenet_en.md +++ b/doc/doc_en/algorithm_det_fcenet_en.md @@ -37,7 +37,7 @@ Please prepare your environment referring to [prepare the environment](./environ The above FCE model is trained using the CTW1500 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](./dataset/ocr_datasets_en.md). -After the data download is complete, please refer to [Text Detection Training Tutorial](./detection.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models. +After the data download is complete, please refer to [Text Detection Training Tutorial](./detection_en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models. ## 4. Inference and Deployment diff --git a/doc/doc_en/algorithm_det_psenet_en.md b/doc/doc_en/algorithm_det_psenet_en.md index d4cb3ea7d1e82a3f9c261c6e44cd6df6b0f6bf1e..3977a156ace3beb899e105bc381e27af6e825d6a 100644 --- a/doc/doc_en/algorithm_det_psenet_en.md +++ b/doc/doc_en/algorithm_det_psenet_en.md @@ -39,7 +39,7 @@ Please prepare your environment referring to [prepare the environment](./environ The above PSE model is trained using the ICDAR2015 text detection public dataset. For the download of the dataset, please refer to [ocr_datasets](./dataset/ocr_datasets_en.md). -After the data download is complete, please refer to [Text Detection Training Tutorial](./detection.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models. +After the data download is complete, please refer to [Text Detection Training Tutorial](./detection_en.md) for training. PaddleOCR has modularized the code structure, so that you only need to **replace the configuration file** to train different detection models. ## 4. Inference and Deployment diff --git a/doc/doc_en/algorithm_e2e_pgnet_en.md b/doc/doc_en/algorithm_e2e_pgnet_en.md index c7cb3221ccfd897e2fd9062a828c2fe0ceb42024..ab74c57bc3d4d97852641cd708a2dceea5732ba7 100644 --- a/doc/doc_en/algorithm_e2e_pgnet_en.md +++ b/doc/doc_en/algorithm_e2e_pgnet_en.md @@ -36,7 +36,7 @@ The results of detection and recognition are as follows: ## 2. Environment Configuration -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 +Please refer to [Operation Environment Preparation](./environment_en.md) to configure PaddleOCR operating environment first, refer to [Project Clone](./clone_en.md) to clone the project ## 3. Quick Use diff --git a/doc/doc_en/algorithm_rec_aster_en.md b/doc/doc_en/algorithm_rec_aster_en.md index 1540681a19f94160e221c37173510395d0fd407f..b949cb5b37c985cc55a2aa01ea5ae4096946bb05 100644 --- a/doc/doc_en/algorithm_rec_aster_en.md +++ b/doc/doc_en/algorithm_rec_aster_en.md @@ -33,13 +33,13 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/algorithm_rec_crnn_en.md b/doc/doc_en/algorithm_rec_crnn_en.md index 571569ee445d756ca7bdfeea6d5f960187a5a666..8548c2fa625b713d7e7e278506ff5c46713303ed 100644 --- a/doc/doc_en/algorithm_rec_crnn_en.md +++ b/doc/doc_en/algorithm_rec_crnn_en.md @@ -33,13 +33,13 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/algorithm_rec_nrtr_en.md b/doc/doc_en/algorithm_rec_nrtr_en.md index 3f8fd0adee900cf889d70e8b78fb1122d54c7d08..40c9b91629964dfaed74bf96aaa947f3fce99446 100644 --- a/doc/doc_en/algorithm_rec_nrtr_en.md +++ b/doc/doc_en/algorithm_rec_nrtr_en.md @@ -29,13 +29,13 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/algorithm_rec_sar_en.md b/doc/doc_en/algorithm_rec_sar_en.md index 8c1e6dbbfa5cc05da4d7423a535c6db74cf8f4c3..24b87c10c3b2839909392bf3de0e0c850112fcdc 100644 --- a/doc/doc_en/algorithm_rec_sar_en.md +++ b/doc/doc_en/algorithm_rec_sar_en.md @@ -31,13 +31,13 @@ Note:In addition to using the two text recognition datasets MJSynth and SynthTex ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/algorithm_rec_seed_en.md b/doc/doc_en/algorithm_rec_seed_en.md index 21679f42fd6302228804db49d731f9b69ec692b2..f8d7ae6d3f34ab8a4f510c88002b22dbce7a10e8 100644 --- a/doc/doc_en/algorithm_rec_seed_en.md +++ b/doc/doc_en/algorithm_rec_seed_en.md @@ -31,13 +31,13 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/algorithm_rec_srn_en.md b/doc/doc_en/algorithm_rec_srn_en.md index c022a81f9e5797c531c79de7e793d44d9a22552c..1d7fc07dc29e0de021165fc5656cbca704b45284 100644 --- a/doc/doc_en/algorithm_rec_srn_en.md +++ b/doc/doc_en/algorithm_rec_srn_en.md @@ -30,13 +30,13 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/algorithm_rec_svtr_en.md b/doc/doc_en/algorithm_rec_svtr_en.md index 2e7deb4c077ce508773c4789e2e76bdda7dfe8c8..d402a6b49194009a061c6a200322047be5b50a30 100644 --- a/doc/doc_en/algorithm_rec_svtr_en.md +++ b/doc/doc_en/algorithm_rec_svtr_en.md @@ -34,7 +34,7 @@ The accuracy (%) and model files of SVTR on the public dataset of scene text rec ## 2. Environment -Please refer to ["Environment Preparation"](./environment.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone.md) to clone the project code. +Please refer to ["Environment Preparation"](./environment_en.md) to configure the PaddleOCR environment, and refer to ["Project Clone"](./clone_en.md) to clone the project code. #### Dataset Preparation @@ -44,7 +44,7 @@ Please refer to ["Environment Preparation"](./environment.md) to configure the P ## 3. Model Training / Evaluation / Prediction -Please refer to [Text Recognition Tutorial](./recognition.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. +Please refer to [Text Recognition Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Training: diff --git a/doc/doc_en/knowledge_distillation_en.md b/doc/doc_en/knowledge_distillation_en.md index bd36907c98c6d556fe1dea85712ece0e717fe426..52725e5c0586b7f7b3e8fdc86d0c24ea38030d53 100755 --- a/doc/doc_en/knowledge_distillation_en.md +++ b/doc/doc_en/knowledge_distillation_en.md @@ -438,10 +438,10 @@ Architecture: ``` If DML is used, that is, the method of two small models learning from each other, the Teacher network structure in the above configuration file needs to be set to the same configuration as the Student model. -Refer to the configuration file for details. [ch_PP-OCRv3_det_dml.yml](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_dml.yml) +Refer to the configuration file for details. [ch_PP-OCRv3_det_dml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_dml.yml) -The following describes the configuration file parameters [ch_PP-OCRv3_det_cml.yml](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml): +The following describes the configuration file parameters [ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml): ``` Architecture: diff --git a/doc/doc_en/multi_languages_en.md b/doc/doc_en/multi_languages_en.md index 4696a3e842242517d19bcac7d7bdef3b4c233b12..d9cb180f706eebdba4727f7909499487794545b9 100644 --- a/doc/doc_en/multi_languages_en.md +++ b/doc/doc_en/multi_languages_en.md @@ -187,10 +187,10 @@ In addition to installing the whl package for quick forecasting, PPOCR also provides a variety of forecasting deployment methods. If necessary, you can read related documents: -- [Python Inference](./inference_en.md) -- [C++ Inference](../../deploy/cpp_infer/readme_en.md) +- [Python Inference](./inference_ppocr_en.md) +- [C++ Inference](../../deploy/cpp_infer/readme.md) - [Serving](../../deploy/hubserving/readme_en.md) -- [Mobile](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/deploy/lite/readme_en.md) +- [Mobile](../../deploy/lite/readme.md) - [Benchmark](./benchmark_en.md) diff --git a/doc/doc_en/update_en.md b/doc/doc_en/update_en.md index a900219b2462524425fc4303ea3bd571efcbab8f..a44dd0d70c611e1b5fb59d1e58b382704d0bbae8 100644 --- a/doc/doc_en/update_en.md +++ b/doc/doc_en/update_en.md @@ -1,8 +1,8 @@ # RECENT UPDATES - 2022.5.9 release PaddleOCR v2.5, including: - - [PP-OCRv3](./doc/doc_en/ppocr_introduction_en.md#pp-ocrv3): With comparable speed, the effect of Chinese scene is further improved by 5% compared with PP-OCRv2, the effect of English scene is improved by 11%, and the average recognition accuracy of 80 language multilingual models is improved by more than 5%. - - [PPOCRLabelv2](./PPOCRLabel): Add the annotation function for table recognition task, key information extraction task and irregular text image. - - Interactive e-book [*"Dive into OCR"*](./doc/doc_en/ocr_book_en.md), covers the cutting-edge theory and code practice of OCR full stack technology. + - [PP-OCRv3](./ppocr_introduction_en.md#pp-ocrv3): With comparable speed, the effect of Chinese scene is further improved by 5% compared with PP-OCRv2, the effect of English scene is improved by 11%, and the average recognition accuracy of 80 language multilingual models is improved by more than 5%. + - [PPOCRLabelv2](../../PPOCRLabel): Add the annotation function for table recognition task, key information extraction task and irregular text image. + - Interactive e-book [*"Dive into OCR"*](./ocr_book_en.md), covers the cutting-edge theory and code practice of OCR full stack technology. - 2022.5.7 Add support for metric and model logging during training to [Weights & Biases](https://docs.wandb.ai/). - 2021.12.21 OCR open source online course starts. The lesson starts at 8:30 every night and lasts for ten days. Free registration: https://aistudio.baidu.com/aistudio/course/introduce/25207 - 2021.12.21 release PaddleOCR v2.4, release 1 text detection algorithm (PSENet), 3 text recognition algorithms (NRTR、SEED、SAR), 1 key information extraction algorithm (SDMGR) and 3 DocVQA algorithms (LayoutLM、LayoutLMv2，LayoutXLM). diff --git a/ppstructure/vqa/README_ch.md b/ppstructure/vqa/README_ch.md index ff513f8f7d603d66a372ce383883f3bcf97a7880..b677dc07bce6c1a752d753b6a1c538b4d3f99271 100644 --- a/ppstructure/vqa/README_ch.md +++ b/ppstructure/vqa/README_ch.md @@ -52,7 +52,7 @@ PP-Structure 里的 DOC-VQA算法基于PaddleNLP自然语言处理算法库进 ### 3.1 SER -![](../../doc/vqa/result_ser/zh_val_0_ser.jpg) | ![](../../doc/vqa/result_ser/zh_val_42_ser.jpg) +![](../docs/vqa/result_ser/zh_val_0_ser.jpg) | ![](../docs/vqa/result_ser/zh_val_42_ser.jpg) ---|--- 图中不同颜色的框表示不同的类别，对于XFUND数据集，有`QUESTION`, `ANSWER`, `HEADER` 3种类别 @@ -65,7 +65,7 @@ PP-Structure 里的 DOC-VQA算法基于PaddleNLP自然语言处理算法库进 ### 3.2 RE -![](../../doc/vqa/result_re/zh_val_21_re.jpg) | ![](../../doc/vqa/result_re/zh_val_40_re.jpg) +![](../docs/vqa/result_re/zh_val_21_re.jpg) | ![](../docs/vqa/result_re/zh_val_40_re.jpg) ---|--- diff --git a/test_tipc/docs/jeston_test_train_inference_python.md b/test_tipc/docs/jeston_test_train_inference_python.md index 9e9d15fb674ca04558b1f8cb616dc4e44934dbb9..b25175ed0071dd3728ae22c7588ca20535af0505 100644 --- a/test_tipc/docs/jeston_test_train_inference_python.md +++ b/test_tipc/docs/jeston_test_train_inference_python.md @@ -115,4 +115,4 @@ ValueError: The results of python_infer_gpu_usetrt_True_precision_fp32_batchsize ## 3. 更多教程 本文档为功能测试用，更丰富的训练预测使用教程请参考： [模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/training.md) -[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference.md) +[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference_ppocr.md) diff --git a/test_tipc/docs/mac_test_train_inference_python.md b/test_tipc/docs/mac_test_train_inference_python.md index ea6e0218b12b342347677ea512d3afd89053261a..c37291a8fc9b239564adce8f556565f51f2a9475 100644 --- a/test_tipc/docs/mac_test_train_inference_python.md +++ b/test_tipc/docs/mac_test_train_inference_python.md @@ -152,4 +152,4 @@ ValueError: The results of python_infer_cpu_usemkldnn_False_threads_1_batchsize_ ## 3. 更多教程 本文档为功能测试用，更丰富的训练预测使用教程请参考： [模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/training.md) -[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference.md) +[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference_ppocr.md) diff --git a/test_tipc/docs/test_train_inference_python.md b/test_tipc/docs/test_train_inference_python.md index fa969cbe1b9b6fd524efdaad5002afcfcf40e119..99de9400797493f429f8176a9b6b374a76df4872 100644 --- a/test_tipc/docs/test_train_inference_python.md +++ b/test_tipc/docs/test_train_inference_python.md @@ -153,4 +153,4 @@ python3.7 test_tipc/compare_results.py --gt_file=./test_tipc/results/python_*.tx ## 3. 更多教程 本文档为功能测试用，更丰富的训练预测使用教程请参考： [模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/training.md) -[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference.md) +[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference_ppocr.md) diff --git a/test_tipc/docs/win_test_train_inference_python.md b/test_tipc/docs/win_test_train_inference_python.md index 95585af0380be410c230a799b7d61e607de5f654..6e3ce93bb3123133075b9d65c64850a87de5f828 100644 --- a/test_tipc/docs/win_test_train_inference_python.md +++ b/test_tipc/docs/win_test_train_inference_python.md @@ -156,4 +156,4 @@ ValueError: The results of python_infer_cpu_usemkldnn_False_threads_1_batchsize_ ## 3. 更多教程 本文档为功能测试用，更丰富的训练预测使用教程请参考： [模型训练](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/training.md) -[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference.md) +[基于Python预测引擎推理](https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_ch/inference_ppocr.md)