adapt to aistudio docs (#3328)

Co-authored-by: cuicheng01 <45199522+cuicheng01@users.noreply.github.com>

README.md

@@ -177,23 +177,23 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI
     </tr>
         <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/cv_pipelines/small_object_detection.html">小目标检测</a></td>
-        <td>🚧</td>
+        <td><a href = "https://aistudio.baidu.com/community/app/387975/webUI?source=appCenter">链接</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
         <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.html">图像多标签分类</a></td>
-        <td>🚧</td>
+        <td><a href = "https://aistudio.baidu.com/community/app/387974/webUI?source=appCenter">链接</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.html">图像异常检测</a></td>
@@ -287,23 +287,23 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.html">公式识别</a></td>
-        <td>🚧</td>
+        <td><a href = "https://aistudio.baidu.com/community/app/387976/webUI?source=appCenter">链接</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.html">印章文本识别</a></td>
-        <td>🚧</td>
+        <td><a href = "https://aistudio.baidu.com/community/app/387977/webUI?source=appCenter">链接</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.html">文档图像预处理</a></td>
@@ -327,23 +327,23 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.html">行人属性识别</a></td>
-        <td>🚧</td>
+        <td><a href = "https://aistudio.baidu.com/community/app/387978/webUI?source=appCenter">链接</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.html">车辆属性识别</a></td>
-        <td>🚧</td>
+        <td><a href = "https://aistudio.baidu.com/community/app/387979/webUI?source=appCenter">链接</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/tutorials/cv_pipelines/face_recognition.html">人脸识别</a></td>

README_en.md

@@ -179,23 +179,23 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
         <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/small_object_detection.html">Small Object Detection</a></td>
-        <td>🚧</td>
+        <td><a href="https://aistudio.baidu.com/community/app/387975/webUI?source=appCenter">Link</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
         <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.html">Multi-label Image Classification</a></td>
-        <td>🚧</td>
+        <td><a href="https://aistudio.baidu.com/community/app/387974/webUI?source=appCenter">Link</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.html">Image Anomaly Detection</a></td>
@@ -289,23 +289,23 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.html">Formula Recognition</a></td>
-        <td>🚧</td>
+        <td><a href="https://aistudio.baidu.com/community/app/387976/webUI?source=appCenter">Link</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.html">Seal Recognition</a></td>
-        <td>🚧</td>
+        <td><a href="https://aistudio.baidu.com/community/app/387977/webUI?source=appCenter">Link</a></td>
         <td>✅</td>
         <td>✅</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.html">Document Image Preprocessing</a></td>
@@ -318,7 +318,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
         <td>🚧</td>
     </tr>
     <tr>
-        <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.html>Image Recognition</a></td>
+        <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.html">Image Recognition</a></td>
         <td>🚧</td>
         <td>✅</td>
         <td>🚧</td>
@@ -329,23 +329,23 @@ In addition, PaddleX provides developers with a full-process efficient model tra
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute.html">Pedestrian Attribute Recognition</a></td>
-        <td>🚧</td>
+        <td><a href="https://aistudio.baidu.com/community/app/387978/webUI?source=appCenter">Link</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute.html">Vehicle Attribute Recognition</a></td>
-        <td>🚧</td>
+        <td><a href="https://aistudio.baidu.com/community/app/387979/webUI?source=appCenter">Link</a></td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
         <td>🚧</td>
         <td>✅</td>
-        <td>🚧</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td><a href="https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/tutorials/cv_pipelines/face_recognition.html">Face Recognition</a></td>
@@ -822,7 +822,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 
 * <details open>
   <summary> <b> 🌐 3D </b></summary>
-  
+
   * [🚗 3D Multimodal Fusion Detection Module Usage Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/module_usage/tutorials/cv_modules/3d_bev_detection.html)
 
 * <details open>

docs/module_usage/tutorials/cv_modules/image_classification.md

@@ -932,15 +932,9 @@ python main.py -c paddlex/configs/modules/image_classification/PP-LCNet_x1_0.yam
   "analysis": {
     "histogram": "check_dataset/histogram.png"
   },
-<<<<<<< HEAD
-  "dataset_path": "./dataset/cls_flowers_examples",
+  "dataset_path": "cls_flowers_examples",
   "show_type": "image",
   "dataset_type": "ClsDataset"
-=======
-  &quot;dataset_path&quot;: &quot;cls_flowers_examples&quot;,
-  &quot;show_type&quot;: &quot;image&quot;,
-  &quot;dataset_type&quot;: &quot;ClsDataset&quot;
->>>>>>> modify_pipeline_and_module_docs
 }
 </code></pre>
 <p>上述校验结果中，check_pass 为 True 表示数据集格式符合要求，其他部分指标的说明如下：</p>

docs/module_usage/tutorials/ocr_modules/layout_detection.en.md

@@ -332,12 +332,12 @@ Relevant methods, parameters, and explanations are as follows:
 <tr>
 <td><code>input</code></td>
 <td>Data for prediction, supporting multiple input types</td>
-<td><code>Python Var</code>/<code>str</code>/<code>dict</code>/<code>list</code></td>
+<td><code>Python Var</code>/<code>str</code>/<code>list</code></td>
 <td>
 <ul>
 <li><b>Python Variable</b>, such as image data represented by <code>numpy.ndarray</code></li>
 <li><b>File Path</b>, such as the local path of an image file: <code>/root/data/img.jpg</code></li>
-<li><b>URL链接</b>，如图像文件的网络URL：<a href = "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg">示例</a></li>
+<li><b>URL link</b>, such as the network URL of an image file: <a href = "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg">示例</a></li>
 <li><b>Local Directory</b>, the directory should contain the data files to be predicted, such as the local path: <code>/root/data/</code></li>
 <li><b>List</b>, the elements of the list should be of the above-mentioned data types, such as <code>[numpy.ndarray, numpy.ndarray]</code>, <code>[\"/root/data/img1.jpg\", \"/root/data/img2.jpg\"]</code>, <code>[\"/root/data1\", \"/root/data2\"]</code></li>
 </ul>
@@ -472,7 +472,7 @@ After executing the above command, PaddleX will validate the dataset and collect
   "analysis": {
     "histogram": "check_dataset/histogram.png"
   },
-  "dataset_path": "./dataset/example_data/det_layout_examples",
+  "dataset_path": "det_layout_examples",
   "show_type": "image",
   "dataset_type": "COCODetDataset"
 }

docs/module_usage/tutorials/ocr_modules/layout_detection.md

@@ -341,7 +341,7 @@ for res in output:
 <tr>
 <td><code>input</code></td>
 <td>待预测数据，支持多种输入类型</td>
-<td><code>Python Var</code>/<code>str</code>/<code>dict</code>/<code>list</code></td>
+<td><code>Python Var</code>/<code>str</code>/<code>list</code></td>
 <td>
 <ul>
   <li><b>Python变量</b>，如<code>numpy.ndarray</code>表示的图像数据</li>
@@ -543,7 +543,7 @@ python main.py -c paddlex/configs/modules/layout_detection/PP-DocLayout-L.yaml \
   "analysis": {
     "histogram": "check_dataset/histogram.png"
   },
-  "dataset_path": "./dataset/example_data/det_layout_examples",
+  "dataset_path": "det_layout_examples",
   "show_type": "image",
   "dataset_type": "COCODetDataset"
 }

docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.md

@@ -58,6 +58,7 @@ for res in output:
 
 运行结果参数含义如下：
 - `input_path`：表示输入图片的路径。
+- `page_index`：如果输入是PDF文件，则表示当前是PDF的第几页，否则为 `None`
 - `class_ids`：表示预测结果的类别 id，含有两个类别，即0度和180度。
 - `scores`：表示预测结果的置信度。
 - `label_names`：表示预测结果的类别名。
@@ -413,7 +414,7 @@ python main.py -c paddlex/configs/modules/textline_orientation/PP-LCNet_x0_25_te
 
 1.<b>产线集成</b>
 
-文本行方向分类模块可以集成的PaddleX产线有[通用OCR产线](../../../pipeline_usage/tutorials/ocr_pipelines/OCR.md)和[文档场景信息抽取v3产线（PP-ChatOCRv3-doc）](../../../pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.md)，只需要替换模型路径即可完成文本行方向分类模块的模型更新。
+文本行方向分类模块可以集成的PaddleX产线有[通用OCR产线](../../../pipeline_usage/tutorials/ocr_pipelines/OCR.md)、[通用版面解析产线](../../../pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md)、[通用版面解析v2产线](../../../pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.md)和[文档场景信息抽取v3产线（PP-ChatOCRv3-doc）](../../../pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.md)，只需要替换模型路径即可完成文本行方向分类模块的模型更新。
 
 2.<b>模块集成</b>
 

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md

@@ -55,11 +55,19 @@ Image multi-label classification is a technique that assigns multiple relevant c
 <p><b>Note: The above accuracy metrics are mAP for the multi-label classification task on </b><a href="https://cocodataset.org/#home">COCO2017</a><b>. The GPU inference time for all models is based on an NVIDIA Tesla T4 machine with FP32 precision. The CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.</b></p>
 
 ## 2. Quick Start
-PaddleX supports experiencing the effects of the General Image Multi-Label Classification Pipeline locally using command line or Python.
+All model production lines provided by PaddleX can be quickly experienced. You can experience the effect of the image multi-label classification pipeline on the community platform, or you can use the command line or Python locally to experience the effect of the image multi-label classification pipeline.
 
-Before using the General Image Multi-Label Classification Pipeline locally, please ensure you have installed the PaddleX wheel package following the [PaddleX Local Installation Tutorial](../../../installation/installation.en.md).
+### 2.1 Online Experience
+You can [experience the image multi-label classification pipeline online](https://aistudio.baidu.com/community/app/387974/webUI?source=appCenter) by recognizing the demo images provided by the official platform, for example:
 
-### 2.1 Command Line Experience
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_multi_label_classification/multi_label_cls.png"/>
+
+If you are satisfied with the performance of the production line, you can directly integrate and deploy it. You can choose to download the deployment package from the cloud, or refer to the methods in [Section 2.2 Local Experience](#22-local-experience) for local deployment. If you are not satisfied with the effect, you can <b>fine-tune the models in the production line using your private data</b>. If you have local hardware resources for training, you can start training directly on your local machine; if not, the Star River Zero-Code platform provides a one-click training service. You don't need to write any code—just upload your data and start the training task with one click.
+
+### 2.2 Local Experience
+> ❗ Before using the image multi-label classification pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Installation Guide](../../../installation/installation.en.md).
+
+#### 2.2.1 Command Line Experience
 You can quickly experience the image multi-label classification pipeline effect with a single command. Use the [test file](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg), and replace `--input` with the local path for prediction.
 
 ```bash
@@ -80,7 +88,8 @@ The visualization results are saved under `save_path`, and the visualization res
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_multi_label_classification/02.png">
 
-### 2.2 Python Script Integration
+#### 2.2.2 Python Script Integration
+
 * The above command line is for quickly experiencing and viewing the effect. Generally, in a project, it is often necessary to integrate through code. You can complete the quick inference of the production line with just a few lines of code. The inference code is as follows:
 
 ```python

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -56,11 +56,19 @@ comments: true
 
 
 ## 2. 快速开始
-PaddleX 支持在本地使用命令行或 Python 体验通用图像多标签分类产线的效果。
+PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河社区线体验通用图像多标签分类产线的效果，也可以在本地使用命令行或 Python 体验通用图像多标签分类产线的效果。
 
-在本地使用通用图像多标签分类产线前，请确保您已经按照[PaddleX本地安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+### 2.1 在线体验
+您可以[在线体验](https://aistudio.baidu.com/community/app/387974/webUI?source=appCenter)通用图像多标签分类产线的效果，用官方提供的 Demo 图片进行识别，例如：
 
-### 2.1 命令行方式体验
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_multi_label_classification/multi_label_cls.png"/>
+
+如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
+
+### 2.2 本地体验
+❗ 在本地使用通用图像多标签分类产线前，请确保您已经按照[PaddleX安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+
+#### 2.2.1 命令行方式体验
 一行命令即可快速体验图像多标签分类产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg)，并将 `--input` 替换为本地路径，进行预测
 
 ```bash
@@ -80,7 +88,7 @@ paddlex --pipeline image_multilabel_classification --input general_image_classif
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_multi_label_classification/02.png">
 
-### 2.2 Python脚本方式集成
+#### 2.2.1 命令行方式体验
 * 上述命令行是为了快速体验查看效果，一般来说，在项目中，往往需要通过代码集成，您可以通过几行代码即可完成产线的快速推理，推理代码如下：
 
 ```python

docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.en.md

@@ -67,10 +67,16 @@ Pedestrian attribute recognition is a key function in computer vision systems, u
 <p><b>Note: The above accuracy metrics are mA on PaddleX's internally built dataset. GPU inference times are based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.</b></p>
 
 ## 2. Quick Start
-The model pipelines provided by PaddleX can be experienced locally using the command line or Python for pedestrian attribute recognition.
+
+All model production lines provided by PaddleX can be quickly experienced. You can experience the effect of the pedestrian attribute recognition pipeline on the community platform, or you can use the command line or Python locally to experience the effect of the pedestrian attribute recognition pipeline.
 
 ### 2.1 Online Experience
-Online experience is not currently supported.
+
+You can [experience the pedestrian attribute recognition pipeline online](https://aistudio.baidu.com/community/app/387978/webUI?source=appCenter) by recognizing the demo images provided by the official platform, for example:
+
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/pedestrian_attribute_recognition/ped_attr_aistudio.png"/>
+
+If you are satisfied with the performance of the production line, you can directly integrate and deploy it. You can choose to download the deployment package from the cloud, or refer to the methods in [Section 2.2 Local Experience](#22-local-experience) for local deployment. If you are not satisfied with the effect, you can <b>fine-tune the models in the production line using your private data</b>. If you have local hardware resources for training, you can start training directly on your local machine; if not, the Star River Zero-Code platform provides a one-click training service. You don't need to write any code—just upload your data and start the training task with one click.
 
 ### 2.2 Local Experience
 Before using the pedestrian attribute recognition pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Local Installation Guide](../../../installation/installation.en.md).

docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.md

@@ -67,10 +67,15 @@ comments: true
 <p><b>注：以上精度指标为 PaddleX 内部自建数据集 mA。GPU 推理耗时基于 NVIDIA Tesla T4 机器，精度类型为 FP32， CPU 推理速度基于 Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz，线程数为 8，精度类型为 FP32。</b></p>
 
 ## 2. 快速开始
-PaddleX 所提供的模型产线可以在本地使用命令行或 Python 体验行人属性识别产线的效果。
+PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河社区线体验行人属性识别产线的效果，也可以在本地使用命令行或 Python 体验行人属性识别产线的效果。
 
 ### 2.1 在线体验
-暂不支持在线体验
+
+您可以[在线体验](https://aistudio.baidu.com/community/app/387978/webUI?source=appCenter)行人属性识别产线的效果，用官方提供的 Demo 图片进行识别，例如：
+
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/pedestrian_attribute_recognition/ped_attr_aistudio.png"/>
+
+如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
 
 ### 2.2 本地体验
 在本地使用行人属性识别产线前，请确保您已经按照[PaddleX本地安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.en.md

@@ -46,14 +46,21 @@ Small object detection is a specialized technique for identifying tiny objects w
 <p><b>Note: The above accuracy metrics are based on the </b><a href="https://github.com/VisDrone/VisDrone-Dataset">VisDrone-DET</a><b> validation set mAP(0.5:0.95). All GPU inference times are based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.</b></p>
 
 ## 2. Quick Start
-PaddleX supports experiencing the small object detection pipeline's effects through command line or Python locally.
 
-Before using the small object detection pipeline locally, ensure you have installed the PaddleX wheel package following the [PaddleX Local Installation Tutorial](../../../installation/installation.en.md).
+All model production lines provided by PaddleX can be quickly experienced. You can experience the effect of the small object detection pipeline on the community platform, or you can use the command line or Python locally to experience the effect of the small object detection pipeline.
 
-### 2.1 Local Experience
-> ❗ Before using the general small object detection pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Local Installation Guide](../../../installation/installation.en.md).
+### 2.1 Online Experience
 
-#### 2.1.1 Command Line Experience
+You can [experience the small object detection pipeline online](https://aistudio.baidu.com/community/app/387975/webUI?source=appCenter) by recognizing the demo images provided by the official platform, for example:
+
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/small_object_detection/small_obj_det_aistudio.jpg"/>
+
+If you are satisfied with the performance of the production line, you can directly integrate and deploy it. You can choose to download the deployment package from the cloud, or refer to the methods in [Section 2.2 Local Experience](#22-local-experience) for local deployment. If you are not satisfied with the effect, you can <b>fine-tune the models in the production line using your private data</b>. If you have local hardware resources for training, you can start training directly on your local machine; if not, the Star River Zero-Code platform provides a one-click training service. You don't need to write any code—just upload your data and start the training task with one click.
+
+### 2.2 Local Experience
+Before using the small object detection pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Local Installation Guide](../../../installation/installation.en.md).
+
+#### 2.2.1 Command Line Experience
 * You can quickly experience the small object detection pipeline effect with a single command. Use the [test file](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/small_object_detection.jpg), and replace `--input` with the local path for prediction.
 
 ```bash

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md

@@ -50,10 +50,19 @@ comments: true
 
 ## 2. 快速开始
 
-### 2.1 本地体验
->❗ 在本地使用通用小目标检测产线前，请确保您已经按照[PaddleX本地安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河社区线体验小目标检测产线的效果，也可以在本地使用命令行或 Python 体验小目标检测产线的效果。
 
-#### 2.1.1 命令行方式体验
+### 2.1 在线体验
+您可以[在线体验](https://aistudio.baidu.com/community/app/387975/webUI?source=appCenter)小目标检测产线的效果，用官方提供的 Demo 图片进行识别，例如：
+
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/small_object_detection/small_obj_det_aistudio.jpg"/>
+
+如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
+
+### 2.2 本地体验
+❗ 在本地使用小目标检测产线前，请确保您已经按照[PaddleX安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+
+#### 2.2.1 命令行方式体验
 * 一行命令即可快速体验小目标检测产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/small_object_detection.jpg)，并将 `--input` 替换为本地路径，进行预测
 
 ```bash
@@ -74,7 +83,7 @@ paddlex --pipeline small_object_detection \
 可视化结果保存在`save_path`下，其中小目标检测的可视化结果如下：
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/small_object_detection/02.png"/>
 
-#### 2.1.2 Python脚本方式集成
+#### 2.2.2 Python脚本方式集成
 * 上述命令行是为了快速体验查看效果，一般来说，在项目中，往往需要通过代码集成，您可以通过几行代码即可完成产线的快速推理，推理代码如下：
 
 ```python

docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.en.md

@@ -63,15 +63,21 @@ Vehicle attribute recognition is a crucial component in computer vision systems.
 <p><b>Note: The above accuracy metrics are mA on the VeRi dataset. GPU inference times are based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.</b></p>
 
 ## 2. Quick Start
-The pre-trained models provided by PaddleX can quickly demonstrate results. You can experience the effects of the vehicle attribute recognition pipeline online or locally using command line or Python.
+
+All model production lines provided by PaddleX can be quickly experienced. You can experience the effect of the vehicle attribute recognition pipeline on the community platform, or you can use the command line or Python locally to experience the effect of the vehicle attribute recognition pipeline.
 
 ### 2.1 Online Experience
-Not supported yet.
+
+You can [experience the vehicle attribute recognition pipeline](https://aistudio.baidu.com/community/app/387979/webUI?source=appCenter) by recognizing the demo images provided by the official platform, for example:
+
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/vehicle_attribute_recognition/vehicle_attribute_aistudio.png"/>
+
+If you are satisfied with the performance of the production line, you can directly integrate and deploy it. You can choose to download the deployment package from the cloud, or refer to the methods in [Section 2.2 Local Experience](#22-local-experience) for local deployment. If you are not satisfied with the effect, you can <b>fine-tune the models in the production line using your private data</b>. If you have local hardware resources for training, you can start training directly on your local machine; if not, the Star River Zero-Code platform provides a one-click training service. You don't need to write any code—just upload your data and start the training task with one click.
 
 ### 2.2 Local Experience
-Before using the vehicle attribute recognition pipeline locally, ensure you have installed the PaddleX wheel package according to the [PaddleX Local Installation Tutorial](../../../installation/installation.en.md).
+Before using the vehicle attribute recognition pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Local Installation Guide](../../../installation/installation.en.md).
 
-#### 2.2.1 Experience via Command Line
+#### 2.2.1 Command Line Experience
 You can quickly experience the vehicle attribute recognition pipeline with a single command. Use the [test file](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_attribute_002.jpg) and replace `--input` with the local path for prediction.
 
 ```bash

docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.md

@@ -64,12 +64,18 @@ comments: true
 <p><b>注：以上精度指标为 VeRi 数据集mA。GPU 推理耗时基于 NVIDIA Tesla T4 机器，精度类型为 FP32， CPU 推理速度基于 Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz，线程数为 8，精度类型为 FP32。</b></p>
 
 ## 2. 快速开始
-PaddleX 所提供的模型产线可以在本地使用命令行或 Python 体验车辆属性识别产线的效果。
+PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河社区线体验车辆属性识别产线的效果，也可以在本地使用命令行或 Python 体验车辆属性识别产线的效果。
 
 ### 2.1 在线体验
-暂不支持在线体验
+
+您可以[在线体验](https://aistudio.baidu.com/community/app/387979/webUI?source=appCenter)车辆属性识别产线的效果，用官方提供的 Demo 图片进行识别，例如：
+
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/vehicle_attribute_recognition/vehicle_attribute_aistudio.png"/>
+
+如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
 
 ### 2.2 本地体验
+
 在本地使用车辆属性识别产线前，请确保您已经按照[PaddleX本地安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
 
 #### 2.2.1 命令行方式体验
@@ -601,20 +607,20 @@ print(result["vehicles"])
 
 若您需要使用微调后的模型权重，只需对产线配置文件做修改，将微调后模型权重的本地路径替换至产线配置文件中的对应位置即可：
 
-```
+```yaml
 pipeline_name: vehicle_attribute_recognition
 
 SubModules:
   Detection:
     module_name: object_detection
     model_name: PP-YOLOE-L_vehicle
-    model_dir: null
+    model_dir: null # 替换为微调后的车辆检测模型权重路径
     batch_size: 1
     threshold: 0.5
   Classification:
     module_name: multilabel_classification
     model_name: PP-LCNet_x1_0_vehicle_attribute
-    model_dir: null
+    model_dir: null # 替换为微调后的车辆属性识别模型权重路径
     batch_size: 1
     threshold: 0.7
 ```

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md

@@ -416,7 +416,7 @@ PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河
 如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
 
 ### 2.2 本地体验
-&gt;❗ 在本地使用通用OCR产线前，请确保您已经按照[PaddleX安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+❗ 在本地使用通用OCR产线前，请确保您已经按照[PaddleX安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
 
 #### 2.2.1 命令行方式体验
 * 一行命令即可快速体验OCR产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png)，并将 `--input` 替换为本地路径，进行预测

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.en.md

@@ -266,11 +266,19 @@ The formula recognition pipeline is designed to solve formula recognition tasks
 <b>Note: The above accuracy metrics are measured using an internally built formula recognition test set within PaddleX. The BLEU score of LaTeX_OCR_rec on the LaTeX-OCR formula recognition test set is 0.8821. All model GPU inference times are based on machines with Tesla V100 GPUs, with precision type FP32.</b>
 
 ## 2. Quick Start
-PaddleX supports experiencing the formula recognition pipeline locally using the command line or Python.
+All model production lines provided by PaddleX can be quickly experienced. You can experience the effect of the formula recognition pipeline on the community platform, or you can use the command line or Python locally to experience the effect of the formula recognition pipeline.
 
-Before using the formula recognition pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Local Installation Tutorial](../../../installation/installation.en.md).
+### 2.1 Online Experience
+You can [experience the formula recognition pipeline online](https://aistudio.baidu.com/community/app/387976/webUI?source=appCenter) by recognizing the demo images provided by the official platform, for example:
 
-### 2.1 Command Line Experience
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/formula_recognition/formula_aistudio.png"/>
+
+If you are satisfied with the performance of the production line, you can directly integrate and deploy it. You can choose to download the deployment package from the cloud, or refer to the methods in [Section 2.2 Local Experience](#22-local-experience) for local deployment. If you are not satisfied with the effect, you can <b>fine-tune the models in the production line using your private data</b>. If you have local hardware resources for training, you can start training directly on your local machine; if not, the Star River Zero-Code platform provides a one-click training service. You don't need to write any code—just upload your data and start the training task with one click.
+
+### 2.2 Local Experience
+> ❗ Before using the formula recognition pipelin locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Installation Guide](../../../installation/installation.en.md).
+
+#### 2.2.1 Command Line Experience
 You can quickly experience the effect of the formula recognition pipeline with one command. Use the [test file](https://paddle-model-ecology.bj.bcebos.com/paddlex/demo_image/pipelines/general_formula_recognition_001.png), and replace `--input` with the local path for prediction.
 
 ```bash
@@ -309,7 +317,7 @@ sudo apt-get install texlive texlive-latex-base texlive-latex-extra -y
 
 <b>Note</b>: Due to the need to render each formula image during the formula recognition visualization process, the process takes a long time. Please be patient.
 
-### 2.2 Integration via Python Script
+#### 2.2.2 Python Script Integration
 A few lines of code can quickly complete the production line inference. Taking the formula recognition production line as an example:
 
 ```python

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -270,11 +270,19 @@ comments: true
 <b>注：以上精度指标测量自 PaddleX 内部自建公式识别测试集。LaTeX_OCR_rec在LaTeX-OCR公式识别测试集的BLEU score为 0.8821。所有模型 GPU 推理耗时基于 Tesla V100 GPUs 机器，精度类型为 FP32。</b>
 
 ## 2. 快速开始
-PaddleX 支持在本地使用命令行或 Python 体验公式识别产线的效果。
+PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河社区线体验公式识别产线的效果，也可以在本地使用命令行或 Python 体验公式识别产线的效果。
 
-在本地使用公式识别产线前，请确保您已经按照[PaddleX本地安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+### 2.1 在线体验
+您可以[在线体验](https://aistudio.baidu.com/community/app/387976/webUI?source=appCenter)公式识别产线的效果，用官方提供的 Demo 图片进行识别，例如：
 
-### 2.1 命令行方式体验
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/formula_recognition/formula_aistudio.png"/>
+
+如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
+
+### 2.2 本地体验
+❗ 在本地使用公式识别产线前，请确保您已经按照[PaddleX安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+
+#### 2.2.1 命令行方式体验
 一行命令即可快速体验公式识别产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/demo_image/pipelines/general_formula_recognition_001.png)，并将 `--input` 替换为本地路径，进行预测
 
 ```bash
@@ -310,7 +318,7 @@ sudo apt-get install texlive texlive-latex-base texlive-latex-extra -y
 ```
 <b>备注</b>： 由于公式识别可视化过程中需要对每张公式图片进行渲染，因此耗时较长，请您耐心等待。
 
-### 2.2 Python脚本方式集成
+#### 2.2.2 Python脚本方式集成
 几行代码即可完成产线的快速推理，以公式识别产线为例：
 
 ```python

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md

@@ -456,11 +456,19 @@ SVTRv2 is a server text recognition model developed by the OpenOCR team of Fudan
 
 
 ## 2. Quick Start
-The pre-trained model pipelines provided by PaddleX can be quickly experienced. You can experience the seal text recognition pipeline locally using the command line or Python.
+All model production lines provided by PaddleX can be quickly experienced. You can experience the effect of the seal text recognition pipeline on the community platform, or you can use the command line or Python locally to experience the effect of the seal text recognition pipeline.
 
-Before using the seal text recognition pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Local Installation Tutorial](../../../installation/installation.en.md).
+### 2.1 Online Experience
+You can [experience the seal text recognition pipeline online](https://aistudio.baidu.com/community/app/387977/webUI?source=appCenter) by recognizing the demo images provided by the official platform, for example:
 
-### 2.1 Command Line Experience
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/seal_recognition/seal_aistudio.png"/>
+
+If you are satisfied with the performance of the production line, you can directly integrate and deploy it. You can choose to download the deployment package from the cloud, or refer to the methods in [Section 2.2 Local Experience](#22-local-experience) for local deployment. If you are not satisfied with the effect, you can <b>fine-tune the models in the production line using your private data</b>. If you have local hardware resources for training, you can start training directly on your local machine; if not, the Star River Zero-Code platform provides a one-click training service. You don't need to write any code—just upload your data and start the training task with one click.
+
+### 2.2 Local Experience
+> ❗ Before using the seal text recognition pipeline locally, please ensure that you have completed the installation of the PaddleX wheel package according to the [PaddleX Installation Guide](../../../installation/installation.en.md).
+
+#### 2.2.1 Command Line Experience
 You can quickly experience the seal text recognition pipeline with a single command. Use the [test file](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/seal_text_det.png), and replace `--input` with the local path for prediction.
 
 ```bash
@@ -479,234 +487,22 @@ After running, the results will be printed to the terminal, as follows:
 <details><summary> 👉Click to Expand</summary>
 
 ```bash
-{'res': {'input_path': 'seal_text_det.png', 'model_settings': {'use_doc_preprocessor': False, 'use_layout_detection': True}, 'layout_det_res': {'input_path': None, 'page_index': None, 'boxes': [{'cls_id': 16, 'label': 'seal', 'score': 0.975529670715332, 'coordinate': [6.191284, 0.16680908, 634.39325, 628.85345]}]}, 'seal_res_list': [{'input_path': None, 'page_index': None, 'model_settings': {'use_doc_preprocessor': False, 'use_textline_orientation': False}, 'dt_polys': [array([[320,  38],
-       [479,  92],
-       [483,  94],
-       [486,  97],
-       [579, 226],
-       [582, 230],
-       [582, 235],
-       [584, 383],
-       [584, 388],
-       [582, 392],
-       [578, 396],
-       [573, 398],
-       [566, 398],
-       [502, 380],
-       [497, 377],
-       [494, 374],
-       [491, 369],
-       [491, 366],
-       [488, 259],
-       [424, 172],
-       [318, 136],
-       [251, 154],
-       [200, 174],
-       [137, 260],
-       [133, 366],
-       [132, 370],
-       [130, 375],
-       [126, 378],
-       [123, 380],
-       [ 60, 398],
-       [ 55, 398],
-       [ 49, 397],
-       [ 45, 394],
-       [ 43, 390],
-       [ 41, 383],
-       [ 43, 236],
-       [ 44, 230],
-       [ 45, 227],
-       [141,  96],
-       [144,  93],
-       [148,  90],
-       [311,  38],
+{'res': {'input_path': 'seal_text_det.png', 'model_settings': {'use_doc_preprocessor': False, 'use_layout_detection': True}, 'layout_det_res': {'input_path': None, 'page_index': None, 'boxes': [{'cls_id': 16, 'label': 'seal', 'score': 0.975531280040741, 'coordinate': [6.195526, 0.1579895, 634.3982, 628.84595]}]}, 'seal_res_list': [{'input_path': None, 'page_index': None, 'model_settings': {'use_doc_preprocessor': False, 'use_textline_orientation': False}, 'dt_polys': [array([[320,  38],
+       ...,
        [315,  38]]), array([[461, 347],
-       [465, 350],
-       [468, 354],
-       [470, 360],
-       [470, 425],
-       [469, 429],
-       [467, 433],
-       [462, 437],
-       [456, 439],
-       [169, 439],
-       [165, 439],
-       [160, 436],
-       [157, 432],
-       [155, 426],
-       [154, 360],
-       [155, 356],
-       [158, 352],
-       [161, 348],
-       [168, 346],
+       ...,
        [456, 346]]), array([[439, 445],
-       [441, 447],
-       [443, 451],
-       [444, 453],
-       [444, 497],
-       [443, 502],
-       [440, 504],
-       [437, 506],
-       [434, 507],
-       [189, 505],
-       [184, 504],
-       [182, 502],
-       [180, 498],
-       [179, 496],
-       [181, 453],
-       [182, 449],
-       [184, 446],
-       [188, 444],
+       ...,
        [434, 444]]), array([[158, 468],
-       [199, 502],
-       [242, 522],
-       [299, 534],
-       [339, 532],
-       [373, 526],
-       [417, 508],
-       [459, 475],
-       [462, 474],
-       [467, 474],
-       [472, 476],
-       [502, 507],
-       [503, 510],
-       [504, 515],
-       [503, 518],
-       [501, 521],
-       [452, 559],
-       [450, 560],
-       [391, 584],
-       [390, 584],
-       [372, 590],
-       [370, 590],
-       [305, 596],
-       [302, 596],
-       [224, 581],
-       [221, 580],
-       [164, 553],
-       [162, 551],
-       [114, 509],
-       [112, 507],
-       [111, 503],
-       [112, 498],
-       [114, 496],
-       [146, 468],
-       [149, 466],
-       [154, 466]])], 'text_det_params': {'limit_side_len': 736, 'limit_type': 'min', 'thresh': 0.2, 'box_thresh': 0.6, 'unclip_ratio': 0.5}, 'text_type': 'seal', 'textline_orientation_angles': [-1, -1, -1, -1], 'text_rec_score_thresh': 0, 'rec_texts': ['天津君和缘商贸有限公司', '发票专用章', '吗繁物', '5263647368706'], 'rec_scores': [0.9934046268463135, 0.9999403953552246, 0.998250424861908, 0.9913849234580994], 'rec_polys': [array([[320,  38],
-       [479,  92],
-       [483,  94],
-       [486,  97],
-       [579, 226],
-       [582, 230],
-       [582, 235],
-       [584, 383],
-       [584, 388],
-       [582, 392],
-       [578, 396],
-       [573, 398],
-       [566, 398],
-       [502, 380],
-       [497, 377],
-       [494, 374],
-       [491, 369],
-       [491, 366],
-       [488, 259],
-       [424, 172],
-       [318, 136],
-       [251, 154],
-       [200, 174],
-       [137, 260],
-       [133, 366],
-       [132, 370],
-       [130, 375],
-       [126, 378],
-       [123, 380],
-       [ 60, 398],
-       [ 55, 398],
-       [ 49, 397],
-       [ 45, 394],
-       [ 43, 390],
-       [ 41, 383],
-       [ 43, 236],
-       [ 44, 230],
-       [ 45, 227],
-       [141,  96],
-       [144,  93],
-       [148,  90],
-       [311,  38],
+       ...,
+       [154, 466]])], 'text_det_params': {'limit_side_len': 736, 'limit_type': 'min', 'thresh': 0.2, 'box_thresh': 0.6, 'unclip_ratio': 0.5}, 'text_type': 'seal', 'textline_orientation_angles': array([-1, ..., -1]), 'text_rec_score_thresh': 0, 'rec_texts': ['天津君和缘商贸有限公司', '发票专用章', '吗繁物', '5263647368706'], 'rec_scores': array([0.9934051 , ..., 0.99139398]), 'rec_polys': [array([[320,  38],
+       ...,
        [315,  38]]), array([[461, 347],
-       [465, 350],
-       [468, 354],
-       [470, 360],
-       [470, 425],
-       [469, 429],
-       [467, 433],
-       [462, 437],
-       [456, 439],
-       [169, 439],
-       [165, 439],
-       [160, 436],
-       [157, 432],
-       [155, 426],
-       [154, 360],
-       [155, 356],
-       [158, 352],
-       [161, 348],
-       [168, 346],
+       ...,
        [456, 346]]), array([[439, 445],
-       [441, 447],
-       [443, 451],
-       [444, 453],
-       [444, 497],
-       [443, 502],
-       [440, 504],
-       [437, 506],
-       [434, 507],
-       [189, 505],
-       [184, 504],
-       [182, 502],
-       [180, 498],
-       [179, 496],
-       [181, 453],
-       [182, 449],
-       [184, 446],
-       [188, 444],
+       ...,
        [434, 444]]), array([[158, 468],
-       [199, 502],
-       [242, 522],
-       [299, 534],
-       [339, 532],
-       [373, 526],
-       [417, 508],
-       [459, 475],
-       [462, 474],
-       [467, 474],
-       [472, 476],
-       [502, 507],
-       [503, 510],
-       [504, 515],
-       [503, 518],
-       [501, 521],
-       [452, 559],
-       [450, 560],
-       [391, 584],
-       [390, 584],
-       [372, 590],
-       [370, 590],
-       [305, 596],
-       [302, 596],
-       [224, 581],
-       [221, 580],
-       [164, 553],
-       [162, 551],
-       [114, 509],
-       [112, 507],
-       [111, 503],
-       [112, 498],
-       [114, 496],
-       [146, 468],
-       [149, 466],
+       ...,
        [154, 466]])], 'rec_boxes': array([], dtype=float64)}]}}
 ```
 
@@ -718,7 +514,7 @@ The visualized results are saved under `save_path`, and the visualized result of
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/seal_recognition/03.png"/>
 
-### 2.1.2 Python Script Integration
+#### 2.2.2 Python Script Integration
 
 * The above command line is for quickly experiencing and viewing the effect. Generally, in a project, you often need to integrate through code. You can complete the quick inference of the pipeline with just a few lines of code. The inference code is as follows:
 
@@ -733,9 +529,9 @@ output = pipeline.predict(
     use_doc_unwarping=False,
 )
 for res in output:
-    res.print() 
-    res.save_to_img("./output/") 
-    res.save_to_json("./output/") 
+    res.print()
+    res.save_to_img("./output/")
+    res.save_to_json("./output/")
 ```
 
 In the above Python script, the following steps were executed:

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md

@@ -494,11 +494,19 @@ devanagari_PP-OCRv3_mobile_rec_infer.tar">推理模型</a>/<a href="">训练模
 </details>
 
 ## 2. 快速开始
-PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可以在本地使用命令行或 Python 体验印章文本识别产线的效果。
+PaddleX 所提供的模型产线均可以快速体验效果，你可以在星河社区线体验印章文本识别产线的效果，也可以在本地使用命令行或 Python 体验印章文本识别产线的效果。
 
-在本地使用印章文本识别产线前，请确保您已经按照[PaddleX本地安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+### 2.1 在线体验
+您可以[在线体验](https://aistudio.baidu.com/community/app/387977/webUI?source=appCenter)印章文本识别产线的效果，用官方提供的 Demo 图片进行识别，例如：
 
-### 2.1 命令行方式体验
+<img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/seal_recognition/seal_aistudio.png"/>
+
+如果您对产线运行的效果满意，可以直接进行集成部署。您可以选择从云端下载部署包，也可以参考[2.2节本地体验](#22-本地体验)中的方法进行本地部署。如果对效果不满意，您可以利用私有数据<b>对产线中的模型进行微调训练</b>。如果您具备本地训练的硬件资源，可以直接在本地开展训练；如果没有，星河零代码平台提供了一键式训练服务，无需编写代码，只需上传数据后，即可一键启动训练任务。
+
+### 2.2 本地体验
+❗ 在本地使用印章文本识别产线前，请确保您已经按照[PaddleX安装教程](../../../installation/installation.md)完成了PaddleX的wheel包安装。
+
+#### 2.2.1 命令行方式体验
 一行命令即可快速体验印章文本识别产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/seal_text_det.png)，并将 `--input` 替换为本地路径，进行预测
 
 ```bash
@@ -545,7 +553,7 @@ paddlex --pipeline seal_recognition \
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/seal_recognition/03.png"/>
 
 
-### 2.1.2 Python脚本方式集成
+#### 2.2.2 Python脚本方式集成
 
 * 上述命令行是为了快速体验查看效果，一般来说，在项目中，往往需要通过代码集成，您可以通过几行代码即可完成产线的快速推理，推理代码如下：