Merge branch 'PaddlePaddle:main' into main

Author: self4m

README_en.md

@@ -45,7 +45,7 @@ In addition to providing an outstanding model library, PaddleOCR 3.0 also offers
 ## 📣 Recent updates
 🔥🔥2025.05.20: Official Release of **PaddleOCR v3.0**, including:
 - **PP-OCRv5**: High-Accuracy Text Recognition Model for All Scenarios - Instant Text from Images/PDFs.
-   1. 🌐 Single-model support for **five** text types - Seamlessly process **Simplified Chinese, Traditional Chinese, Simplified Chinese Pinyin, English** and **Japanse** within a single model.
+   1. 🌐 Single-model support for **five** text types - Seamlessly process **Simplified Chinese, Traditional Chinese, Simplified Chinese Pinyin, English** and **Japanese** within a single model.
    2. ✍️ Improved **handwriting recognition**: Significantly better at complex cursive scripts and non-standard handwriting.
    3. 🎯 **13-point accuracy gain** over PP-OCRv4, achieving state-of-the-art performance across a variety of real-world scenarios.
 

docs/version3.x/deployment/python_and_cpp_infer.md

@@ -0,0 +1,7 @@
+# 基于Python或C++预测引擎推理
+
+自 2.x 分支以来，基于 Python 或 C++ 的预测引擎推理一直是一项重要功能。该功能允许用户在无需安装 wheel 包的情况下加载OCR相关模型并进行推理。有关具体使用方法，请参考以下文档：
+
+* [基于Python预测引擎推理](../../version2.x/legacy/python_infer.md)
+* [基于C++预测引擎推理](../../version2.x/legacy/cpp_infer.md)
+* [支持的模型列表](../../version2.x/legacy/model_list_2.x.md)

docs/version3.x/deployment/serving.en.md

@@ -60,7 +60,7 @@ The command-line options related to serving are as follows:
 </tr>
 <tr>
 <td><code>--device</code></td>
-<td>Deployment device for the pipeline. Defaults to <code>cpu</code> (if GPU is unavailable) or <code>gpu</code> (if GPU is available).</td>
+<td>Deployment device for the pipeline. By default, a GPU will be used if available; otherwise, a CPU will be used."</td>
 </tr>
 <tr>
 <td><code>--host</code></td>

docs/version3.x/deployment/serving.md

@@ -60,7 +60,7 @@ INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
 </tr>
 <tr>
 <td><code>--device</code></td>
-<td>产线部署设备。默认为 <code>cpu</code>（如 GPU 不可用）或 <code>gpu</code>（如 GPU 可用）。</td>
+<td>产线部署设备。默认情况下，当 GPU 可用时，将使用 GPU；否则使用 CPU。</td>
 </tr>
 <tr>
 <td><code>--host</code></td>

docs/version3.x/model_list.md

@@ -127,21 +127,21 @@ PaddleOCR 内置了多条产线，每条产线都包含了若干模块，每个
 </tr>
 <tr>
 <td>PP-OCRv5_server_rec</td>
-<td>-</td>
-<td>- / -</td>
-<td>- / -</td>
-<td>206 M</td>
+<td>86.38</td>
+<td>8.45/2.36</td>
+<td>122.69/122.69</td>
+<td>81 M</td>
 <td><a href="https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/modules/text_recognition/PP-OCRv5_server_rec.yaml">PP-OCRv5_server_rec.yaml</a></td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_rec_infer.tar">推理模型</a>/<a href="">训练模型</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_server_rec_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_server_rec_pretrained.pdparams">训练模型</a></td>
 </tr>
 <tr>
 <td>PP-OCRv5_mobile_rec</td>
-<td>-</td>
-<td>- / -</td>
-<td>- / -</td>
-<td>137 M</td>
+<td>81.29</td>
+<td>1.46/5.43</td>
+<td>5.32/91.79</td>
+<td>16 M</td>
 <td><a href="https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/modules/text_recognition/PP-OCRv5_mobile_rec.yaml">PP-OCRv5_mobile_rec.yaml</a></td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_rec_infer.tar">推理模型</a>/<a href="">训练模型</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv5_mobile_rec_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv5_mobile_rec_pretrained.pdparams">训练模型</a></td>
 </tr>
 <tr>
 <td>PP-OCRv4_server_rec_doc</td>

docs/version3.x/module_usage/module_overview.en.md

@@ -0,0 +1,3 @@
+# Module Overview
+
+A module is the smallest unit that implements basic functionality. Modules typically use a single model to accomplish specific tasks, such as text detection, image classification, and other basic functions. As fundamental building blocks, modules provide the necessary functional support for more complex application scenarios. This design approach allows users to flexibly select and combine different modules according to their needs, thereby simplifying the development process and enhancing development flexibility and efficiency.

docs/version3.x/module_usage/module_overview.md

@@ -0,0 +1,3 @@
+# 模块概述
+
+模块是实现基本功能的最小单位。模块通常使用单个模型去完成特定的任务，比如文本检测、图像分类等基本功能。模块作为基础构建单元，为更复杂的应用场景提供了必要的功能支持。这种设计方式使得用户可以根据需要灵活选择和组合不同的模块，从而简化了开发流程，并提高了开发的灵活性和效率。

docs/version3.x/module_usage/table_cells_detection.en.md

@@ -81,7 +81,7 @@ The Table Cell Detection Module is a key component of the table recognition task
 
 ## III. Quick Start
 
-> ❗ Before starting quickly, please first install the PaddleOCR wheel package. For details, please refer to the [installation tutorial](../installation.md).
+> ❗ Before starting quickly, please first install the PaddleOCR wheel package. For details, please refer to the [installation tutorial](../installation.en.md).
 
 You can quickly experience it with one command:
 
@@ -187,8 +187,8 @@ The relevant methods, parameters, etc., are described as follows:
 <td><code>float/dict</code></td>
 <td>
 <ul>
-  <li><b>float</b>, e.g., 0.2, indicates filtering out all bounding boxes with confidence lower than 0.2</li>
-  <li><b>dictionary</b>, where the key is of type <b>int</b> representing <code>cls_id</code>, and the value is of type <b>float</b> representing the threshold. For example, <code>{0: 0.45, 2: 0.48, 7: 0.4}</code> applies a threshold of 0.45 for category cls_id 0, 0.48 for category cls_id 1, and 0.4 for category cls_id 7</li>
+  <li><b>float</b>, e.g., 0.3, indicates filtering out all bounding boxes with confidence lower than 0.3</li>
+  <li><b>dictionary</b>, where the key is of type <b>int</b> representing <code>cls_id</code>, and the value is of type <b>float</b> representing the threshold. For example, <code>{0: 0.3}</code> applies a threshold of 0.3 for category cls_id 0</li>
 </ul>
 </td>
 <td>None</td>

docs/version3.x/module_usage/table_cells_detection.md

@@ -236,11 +236,11 @@ for res in output:
 <td><code>float/dict</code></td>
 <td>
 <ul>
-  <li><b>float</b>，如 0.2， 表示过滤掉所有阈值小于0.2的目标框</li>
-  <li><b>字典</b>，字典的key为<b>int</b>类型，代表<code>cls_id</code>，val为<b>float</b>类型阈值。如 <code>{0: 0.45, 2: 0.48, 7: 0.4}</code>，表示对cls_id为0的类别应用阈值0.45、cls_id为1的类别应用阈值0.48、cls_id为7的类别应用阈值0.4</li>
+  <li><b>float</b>，如 0.3， 表示过滤掉所有阈值小于0.3的目标框</li>
+  <li><b>字典</b>，字典的key为<b>int</b>类型，代表<code>cls_id</code>，val为<b>float</b>类型阈值。如 <code>{0: 0.3}</code>，表示对cls_id为0的类别应用阈值0.3</li>
 </ul>
 </td>
-<td>无</td>
+<td>None</td>
 </tr>
 </table>
 

docs/version3.x/module_usage/table_classification.en.md

@@ -74,7 +74,7 @@ The Table Classification Module is a key component in computer vision systems, r
 
 ## 3. Quick Start
 
-> ❗ Before starting quickly, please first install the PaddleOCR wheel package. For details, please refer to the [installation tutorial](../installation.md).
+> ❗ Before starting quickly, please first install the PaddleOCR wheel package. For details, please refer to the [installation tutorial](../installation.en.md).
 
 You can quickly experience it with one command:
 

docs/version3.x/module_usage/table_classification.md

@@ -272,6 +272,6 @@ for res in output:
 
 ## 四、二次开发
 
-由于 PaddleOCR 并不直接提供表格分类模块的训练，因此，如果需要训练表格分类模型，可以参考 [PaddleX 表格分类模块二次开发](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/ocr_modules/table_classification.html#_4)部分进行训练。训练后的模型可以无缝集成到 PaddleOCR 的 API 中进行推理。
+由于 PaddleOCR 并不直接提供表格分类模块的训练，因此，如果需要训练表格分类模型，可以参考 [PaddleX 表格分类模块二次开发](https://paddlepaddle.github.io/PaddleX/latest/module_usage/tutorials/ocr_modules/table_classification.html#_5)部分进行训练。训练后的模型可以无缝集成到 PaddleOCR 的 API 中进行推理。
 
 ## 五、FAQ

docs/version3.x/module_usage/table_structure_recognition.en.md

@@ -6,7 +6,7 @@ comments: true
 
 ## 1. Overview
 
-Table structure recognition is an important component of table recognition systems, capable of converting non-editable table images into editable table formats (such as HTML). The goal of table structure recognition is to identify the positions of rows, columns, and cells in tables. The performance of this module directly affects the accuracy and efficiency of the entire table recognition system. The table structure recognition module usually outputs HTML or Latex code for the table area, which is then passed as input to the table content recognition module for further processing.
+Table structure recognition is an important component of table recognition systems, capable of converting non-editable table images into editable table formats (such as HTML). The goal of table structure recognition is to identify the positions of rows, columns, and cells in tables. The performance of this module directly affects the accuracy and efficiency of the entire table recognition system. The table structure recognition module usually outputs HTML code for the table area, which is then passed as input to the tabl recognition pipeline for further processing.
 
 ## 2. Supported Model List
 
@@ -56,7 +56,7 @@ Table structure recognition is an important component of table recognition syste
   <ul>
       <li><b>Performance Test Environment</b>
           <ul>
-              <li><strong>Test Dataset:</strong> High-difficulty Chinese table recognition dataset built internally by PaddleX.</li>
+              <li><strong>Test Dataset:</strong> High-difficulty Chinese table recognition dataset.</li>
               <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
@@ -147,7 +147,7 @@ Descriptions of related methods and parameters are as follows:
 <td><code>model_name</code></td>
 <td>Model name</td>
 <td><code>str</code></td>
-<td>All model names supported by PaddleX</td>
+<td>All model names</td>
 <td>None</td>
 </tr>
 <tr>
@@ -180,7 +180,7 @@ Descriptions of related methods and parameters are as follows:
 </tr>
 </table>
 
-* Among them, `model_name` must be specified. After specifying `model_name`, the built-in model parameters of PaddleX are used by default. On this basis, if `model_dir` is specified, the user's custom model is used.
+* Among them, `model_name` must be specified. If `model_dir` is specified, the user's custom model is used.
 
 * Call the `predict()` method of the table structure recognition model for inference prediction, which returns a result list. In addition, this module also provides the `predict_iter()` method. The two are completely consistent in parameter acceptance and result return. The difference is that `predict_iter()` returns a `generator`, which can process and obtain prediction results step by step, suitable for handling large datasets or scenarios where you want to save memory. You can choose to use either method according to your actual needs. The `predict()` method has parameters `input` and `batch_size`, described as follows:
 
@@ -290,7 +290,7 @@ Descriptions of related methods and parameters are as follows:
 
 ## 4. Secondary Development
 
-If the above models are still not ideal for your scenario, you can try the following steps for secondary development. Here, training `SLANet` is used as an example, and for other models, just replace the corresponding configuration file. First, you need to prepare a dataset for table structure recognition, which can be prepared with reference to the format of the [table structure recognition demo data](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/table_rec_dataset_examples.tar). Once ready, you can train and export the model as follows. After exporting, you can quickly integrate the model into the above API. Here, the table structure recognition demo data is used as an example. Before training the model, please make sure you have installed the dependencies required by PaddleOCR according to the [installation documentation](../installation.en.md).
+If the above models are still not ideal for your scenario, you can try the following steps for secondary development. Here, training `SLANet_plus` is used as an example, and for other models, just replace the corresponding configuration file. First, you need to prepare a dataset for table structure recognition, which can be prepared with reference to the format of the [table structure recognition demo data](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/table_rec_dataset_examples.tar). Once ready, you can train and export the model as follows. After exporting, you can quickly integrate the model into the above API. Here, the table structure recognition demo data is used as an example. Before training the model, please make sure you have installed the dependencies required by PaddleOCR according to the [installation documentation](../installation.en.md).
 
 
 ## 4.1 Dataset and Pretrained Model Preparation
@@ -306,24 +306,35 @@ tar -xf table_rec_dataset_examples.tar
 ### 4.1.2 Download Pretrained Model
 
 ```shell
-# Download SLANet pretrained model
-wget https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/SLANet_pretrained.pdparams
+# Download SLANet_plus pretrained model
+wget https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/SLANet_plus_pretrained.pdparams
 ```
 
 ### 4.2 Model Training
 
-PaddleOCR is modularized. When training the `SLANet` recognition model, you need to use the [configuration file](https://github.com/PaddlePaddle/PaddleOCR/blob/main/configs/table/SLANet.yml) of `SLANet`.
+PaddleOCR is modularized. When training the `SLANet_plus` recognition model, you need to use the [configuration file](https://github.com/PaddlePaddle/PaddleOCR/blob/main/configs/table/SLANet_plus.yml) of `SLANet_plus`.
 
 
 The training commands are as follows:
 
 ```bash
 # Single card training (default training method)
-python3 tools/train.py -c configs/table/SLANet.yml \
-   -o Global.pretrained_model=./SLANet_pretrained.pdparams
+python3 tools/train.py -c configs/table/SLANet_plus.yml \
+    -o Global.pretrained_model=./SLANet_plus_pretrained.pdparams
+    Train.dataset.data_dir=./table_rec_dataset_examples \
+    Train.dataset.label_file_list='[./table_rec_dataset_examples/train.txt]' \
+    Eval.dataset.data_dir=./table_rec_dataset_examples \
+    Eval.dataset.label_file_list='[./table_rec_dataset_examples/val.txt]'
+
 # Multi-card training, specify card numbers via --gpus parameter
-python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/table/SLANet.yml \
-        -o Global.pretrained_model=./SLANet_pretrained.pdparams
+python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py \
+    -c configs/table/SLANet_plus.yml \
+    -o Global.pretrained_model=./SLANet_plus_pretrained.pdparams
+    -o Global.pretrained_model=./PP-OCRv5_server_det_pretrained.pdparams \
+    Train.dataset.data_dir=./table_rec_dataset_examples \
+    Train.dataset.label_file_list='[./table_rec_dataset_examples/train.txt]' \
+    Eval.dataset.data_dir=./table_rec_dataset_examples \
+    Eval.dataset.label_file_list='[./table_rec_dataset_examples/val.txt]'
 ```
 
 
@@ -334,21 +345,23 @@ You can evaluate the trained weights, such as `output/xxx/xxx.pdparams`, using t
 ```bash
 # Note to set the path of pretrained_model to the local path. If you use the model saved by your own training, please modify the path and file name to {path/to/weights}/{model_name}.
  # Demo test set evaluation
- python3 tools/eval.py -c configs/table/SLANet.yml -o \
- Global.pretrained_model=output/xxx/xxx.pdparams
+ python3 tools/eval.py -c configs/table/SLANet_plus.yml -o \
+    Global.pretrained_model=output/xxx/xxx.pdparams
+    Eval.dataset.data_dir=./table_rec_dataset_examples \
+    Eval.dataset.label_file_list='[./table_rec_dataset_examples/val.txt]'
 ```
 
 ### 4.4 Model Export
 
 ```bash
- python3 tools/export_model.py -c configs/table/SLANet.yml -o \
- Global.pretrained_model=output/xxx/xxx.pdparams \
- save_inference_dir="./SLANet_infer/"
+ python3 tools/export_model.py -c configs/table/SLANet_plus.yml -o \
+    Global.pretrained_model=output/xxx/xxx.pdparams \
+    Global.save_inference_dir="./SLANet_plus_infer/"
 ```
 
- After exporting the model, the static graph model will be stored in `./SLANet_infer/` in the current directory. In this directory, you will see the following files:
+ After exporting the model, the static graph model will be stored in `./SLANet_plus_infer/` in the current directory. In this directory, you will see the following files:
  ```
- ./SLANet_infer/
+ ./SLANet_plus_infer/
  ├── inference.json
  ├── inference.pdiparams
  ├── inference.yml