Home Explore Help
Register Sign In
zhengchun
/
PaddleX
1
0
Fork 0
Files Issues 0 Pull Requests 0 Wiki
Browse Source

Develop (#2143)

* modify installation_other_devices.md for export (#2133)

* fix resize about w,h order (#2132)

* Update README.md

* Update document_scene_information_extraction.md

* Update document_scene_information_extraction_en.md

* Update document_scene_information_extraction_en.md

* bugfix

* update doc (#2138)

* Support Cython generator type (#2136)

* update doc (#2140)

* [Feat] Add pipeline serving (#2077)

* Support pipeline serving

* Refactor

* Update det and instance_seg apps

* Fix bugs and enhance typing

* Set device when creating app

* Add TS apps

* Add ppchatocrv3 app

* Fix bugs and add anomaly detection app

* Fix bugs

* Update ppchatocrv3

* Update ppchatocrv3 APIs

* Update serving CLI

* Update ppchatocrv3

* Update and fix

* Fix bugs

* Update APIs

* Fix and update

* Remove bs setting

* new doc (#2134)

* update readme (#2139)

* uodate readme

* update readme

---------

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

* fix README.md

* fix README_en.md

* Develop (#2142)

* update doc

* update README

* update README

---------

Co-authored-by: a31413510 <31413510@qq.com>
Co-authored-by: Tingquan Gao <gaotingquan@baidu.com>
Co-authored-by: Lin Manhui <bob1998425@hotmail.com>
Co-authored-by: AmberC0209 <55582609+AmberC0209@users.noreply.github.com>
Co-authored-by: Tingquan Gao <35441050@qq.com>
cuicheng01 1 year ago
parent
19ce18da97
commit
2426c9864c
2 changed files with 87 additions and 91 deletions
Split View Show Diff Stats
  1. 30 32
      README.md
  2. 57 59
      README_en.md

+ 30 - 32
README.md
View File 

@@ -265,8 +265,6 @@ PaddleX的各个产线均支持**在线体验**和本地**快速推理**，您
 
     
 </table>
 
 
-
 
-
 
 > ❗注：以上功能均基于 GPU/CPU 实现。PaddleX 还可在昆仑、昇腾、寒武纪和海光等主流硬件上进行快速推理和二次开发。下表详细列出了模型产线的支持情况，具体支持的模型列表请参阅[模型列表(MLU)](../docs/support_list/model_list_mlu.md)/[模型列表(NPU)](../docs/support_list/model_list_npu.md)/[模型列表(XPU)](../docs/support_list/model_list_xpu.md)/[模型列表(DCU)](../docs/support_list/model_list_dcu.md)。我们正在适配更多的模型，并在主流硬件上推动高性能和服务化部署的实施。
 
 
 <details>
 
@@ -369,7 +367,7 @@ python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.
 
 * **安装PaddleX**
 
 
 ```bash
 
-pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0.beta1-py3-none-any.whl
 
+pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0b1-py3-none-any.whl
 
 ```
 
   
 > ❗ 更多安装方式参考 [PaddleX 安装教程](./docs/installation/installation.md)
 
@@ -409,23 +407,22 @@ paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddle
 
 其他产线的命令行使用，只需将 `pipeline` 参数调整为相应产线的名称。下面列出了每个产线对应的命令：
 
 
 <details>
 
-  <summary><b>👉 更多产线的命令行使用及说明</b></summary>
 
+  <summary><b>👉 更多产线的命令行使用</b></summary>
 
 
 | 产线名称      | 使用命令                                                                                                                                                                                             |
 
 |-----------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 
-| 文档场景信息抽取  |                                                                                                                                                                                                  |
 
 | 通用图像分类    | `paddlex --pipeline image_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg --device gpu:0`                           |
 
 | 通用目标检测    | `paddlex --pipeline object_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png --device gpu:0`                                   |
 
 | 通用实例分割    | `paddlex --pipeline instance_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_instance_segmentation_004.png --device gpu:0`                         |
 
-| 通用语义分割    | `paddlex --pipeline semantic_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png --device gpu:0`                              |
 
-| 通用图像多标签分类 | `paddlex --pipeline multilabel_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/garbage_demo.png --device gpu:0`                                          |
 
-| 小目标检测     | `paddlex --pipeline smallobject_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/garbage_demo.png --device gpu:0`                                              |
 
-| 图像异常检测    |                                                                                                                                                                                                  |
 
+| 通用语义分割    | `paddlex --pipeline semantic_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/application/semantic_segmentation/makassaridn-road_demo.png --device gpu:0`                              |
 
+| 通用图像多标签分类 | `paddlex --pipeline multi_label_image_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg --device gpu:0`                                          |
 
+| 小目标检测     | `paddlex --pipeline small_object_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/small_object_detection.jpg --device gpu:0`                                              |
 
+| 图像异常检测    |    `paddlex --pipeline anomaly_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/uad_grid.png --device gpu:0 ` |
 
 | 通用OCR     | `paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png --device gpu:0`                                                             |
 
 | 通用表格识别    | `paddlex --pipeline table_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg --device gpu:0`                                             |
 
-| 通用时序预测    | `paddlex --pipeline ts_forecast --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_fc.csv --device` gpu:0                                                                    |
 
-| 通用时序异常检测  | `paddlex --pipeline ts_anomaly_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/doc_images/practical_tutorial/timeseries_anomaly_detection/test.csv --device gpu:0` |
 
-| 通用时序分类    | `paddlex --pipeline ts_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/doc_images/practical_tutorial/timeseries_classification/test.csv --device gpu:0`       |
 
+| 通用时序预测    | `paddlex --pipeline ts_fc --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_fc.csv --device gpu:0`                                                                    |
 
+| 通用时序异常检测  | `paddlex --pipeline ts_ad --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_ad.cs --device gpu:0` |
 
+| 通用时序分类    | `paddlex --pipeline ts_cls --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_cls.csv --device gpu:0`       |
 
 
 </details>
 
 
@@ -437,12 +434,10 @@ from paddlex import create_pipeline
 
 
 pipeline = create_pipeline(pipeline=[产线名称])
 
 output = pipeline.predict([输入图片名称])
 
-for batch in output:
 
-    for item in batch:
 
-        res = item['result']
 
-        res.print()
 
-        res.save_to_img("./output/")
 
-        res.save_to_json("./output/")
 
+for res in output:
 
+    res.print()
 
+    res.save_to_img("./output/")
 
+    res.save_to_json("./output/")
 
 ```
 
 执行了如下几个步骤：
 
 
@@ -456,21 +451,24 @@ for batch in output:
 
 
 | 产线名称           | 对应参数               | 详细说明                                                                                                      |
 
 |--------------------|------------------------|---------------------------------------------------------------------------------------------------------------|
 
-| 文档场景信息抽取   | `PP-ChatOCRv3-doc` | [文档场景信息抽取v3产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md) |
 
-| 通用图像分类       | `image_classification` | [通用图像分类产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md) |
 
-| 通用目标检测       | `object_detection` | [通用目标检测产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md) |
 
-| 通用实例分割       | `instance_segmentation` | [通用实例分割产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md) |
 
-| 通用语义分割       | `semantic_segmentation` | [通用语义分割产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md) |
 
-| 通用图像多标签分类 | `multilabel_classification` | [通用图像多标签分类产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md) |
 
-| 小目标检测         | `small_object_detection` | [小目标检测产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md) |
 
-| 图像异常检测       | `image_classification` | [图像异常检测产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md) |
 
-| 通用 OCR            | `OCR` | [通用 OCR 产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md) |
 
-| 通用表格识别       | `table_recognition` | [通用表格识别产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md) |
 
-| 通用时序预测       | `ts_forecast` | [通用时序预测产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md) |
 
-| 通用时序异常检测   | `ts_anomaly_detection` | [通用时序异常检测产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md) |
 
-| 通用时序分类       | `ts_cls` | [通用时序分类产线 Python 脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md) |
 
+
 
+| 文档场景信息抽取   | `PP-ChatOCRv3-doc` | [文档场景信息抽取v3产线Python脚本使用说明](./docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md#22-本地体验) |
 
+| 通用图像分类       | `image_classification` | [通用图像分类产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md#222-python脚本方式集成) |
 
+| 通用目标检测       | `object_detection` | [通用目标检测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md#222-python脚本方式集成) |
 
+| 通用实例分割       | `instance_segmentation` | [通用实例分割产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md#222-python脚本方式集成) |
 
+| 通用语义分割       | `semantic_segmentation` | [通用语义分割产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md#222-python脚本方式集成) |
 
+| 通用图像多标签分类 | `multi_label_image_classification` | [通用图像多标签分类产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md#22-python脚本方式集成) |
 
+| 小目标检测         | `small_object_detection` | [小目标检测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md#22-python脚本方式集成) |
 
+| 图像异常检测       | `anomaly_detection` | [图像异常检测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md#22-python脚本方式集成) |
 
+| 通用OCR            | `OCR` | [通用OCR产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md#222-python脚本方式集成) |
 
+| 通用表格识别       | `table_recognition` | [通用表格识别产线Python脚本使用说明](./docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md#22-python脚本方式集成) |
 
+| 通用时序预测       | `ts_fc` | [通用时序预测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md#222-python脚本方式集成) |
 
+| 通用时序异常检测   | `ts_ad` | [通用时序异常检测产线Python脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md#222-python脚本方式集成) |
 
+| 通用时序分类       | `ts_cls` | [通用时序分类产线Python脚本使用说明](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md#222-python脚本方式集成) |
 
+
 
 </details>
 
 
+
 
 ## 📖 文档
 
 <details>
 
   <summary> <b> ⬇️ 安装 </b></summary>
 
@@ -508,7 +506,7 @@ for batch in output:
 
    * [🗣️ 通用语义分割产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md)
 
    * [🏷️ 图像多标签分类产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md)
 
    * [🔍 小目标检测产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md)
 
-   * [🖼️ 图像异常检测产线使用教程](./docs/module_usage/tutorials/cv_modules/anomaly_detection.md)
 
+   * [🖼️ 图像异常检测产线使用教程](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md)
 
   
 
 * <details>

+ 57 - 59
README_en.md
View File 

@@ -44,28 +44,28 @@ ntegrates numerous **ready-to-use pre-trained models**, enabling **full-process
 
 
 ## 📣 Recent Updates
 
 
-🔥🔥 **9.30, 2024**, PaddleX 3.0 Beta1 open source version is officially released, providing **more than 200 models** that can be called with a minimalist Python API; achieve model full-process development based on unified commands, and open source the basic capabilities of the **PP-ChatOCRv3** featured model production line; support **more than 100 models for high-performance inference and service-oriented deployment** (iterating continuously), **more than 7 key visual models for edge-side deployment**; **more than 70 models have been adapted for the full development process of Ascend 910B**, **more than 15 models have been adapted for the full development process of Kunlun chips and Cambricon**
 
+🔥🔥 **9.30, 2024**, PaddleX 3.0 Beta1 open source version is officially released, providing **more than 200 models** that can be called with a minimalist Python API; achieve model full-process development based on unified commands, and open source the basic capabilities of the **PP-ChatOCRv3** featured model pipeline; support **more than 100 models for high-performance inference and service-oriented deployment** (iterating continuously), **more than 7 key visual models for edge-side deployment**; **more than 70 models have been adapted for the full development process of Ascend 910B**, **more than 15 models have been adapted for the full development process of Kunlun chips and Cambricon**
 
 
-🔥 **6.27, 2024**, PaddleX 3.0 Beta open source version is officially released, supporting the use of various mainstream hardware for production line and model development in a low-code manner on the local side.
 
+🔥 **6.27, 2024**, PaddleX 3.0 Beta open source version is officially released, supporting the use of various mainstream hardware for pipeline and model development in a low-code manner on the local side.
 
 
 🔥 **3.25, 2024**, PaddleX 3.0 cloud release, supporting the creation of pipelines in the AI Studio Galaxy Community in a zero-code manner.
 
 
 ## 📊 What can PaddleX do？
 
 
-All pipelines of PaddleX support **online experience** and local **fast inference**. You can quickly experience the pre-trained effects of each production line. If you are satisfied with the pre-trained effects of the production line, you can directly perform [high-performance deployment](./docs/pipeline_deploy/high_performance_deploy_en.md) / [service deployment](./docs/pipeline_deploy/service_deploy_en.md) / [lite deployment](./docs/pipeline_deploy/lite_deploy_en.md) on the production line. If not satisfied, you can also **second development** to improve the production line effect. For the complete production line development process, please refer to the [PaddleX Production Line Development Tool Local Use Tutorial](./docs/pipeline_usage/pipeline_develop_guide_en.md).
 
+All pipelines of PaddleX support **online experience** and local **fast inference**. You can quickly experience the effects of each pre-trained pipeline. If you are satisfied with the effects of the pre-trained pipeline, you can directly perform [high-performance deployment](./docs/pipeline_deploy/high_performance_deploy_en.md) / [serving deployment](./docs/pipeline_deploy/service_deploy_en.md) / [edge deployment](./docs/pipeline_deploy/lite_deploy_en.md) on the pipeline. If not satisfied, you can also **second development** to improve the pipeline effect. For the complete pipeline development process, please refer to the [PaddleX pipeline Development Tool Local Use Tutorial](./docs/pipeline_usage/pipeline_develop_guide_en.md).
 
 
-In addition, PaddleX provides developers with a full-process efficient model training and deployment tool based on a [cloud-based graphical development interface](https://aistudio.baidu.com/pipeline/mine). Developers **do not need code development**, just need to prepare a dataset that meets the production line requirements to **quickly start model training**. For details, please refer to the tutorial ["Developing Industrial-level AI Models with Zero Threshold"](https://aistudio.baidu.com/practical/introduce/546656605663301).
 
+In addition, PaddleX provides developers with a full-process efficient model training and deployment tool based on a [cloud-based graphical development interface](https://aistudio.baidu.com/pipeline/mine). Developers **do not need code development**, just need to prepare a dataset that meets the pipeline requirements to **quickly start model training**. For details, please refer to the tutorial ["Developing Industrial-level AI Models with Zero Threshold"](https://aistudio.baidu.com/practical/introduce/546656605663301).
 
 
 <table>
 
     <tr>
 
-        <th>Model Production Line</th>
 
+        <th>Model pipeline</th>
 
         <th>Online Experience</th>
 
         <th>Quick Inference</th>
 
         <th>High-Performance Deployment</th>
 
         <th>Service Deployment</th>
 
         <th>Edge Deployment</th>
 
         <th>Secondary Development</th>
 
-        <th><a href="https://aistudio.baidu.com/pipeline/mine">Galaxy Zero-Code Production Line</a></td> 
+        <th><a href="https://aistudio.baidu.com/pipeline/mine">Galaxy Zero-Code pipeline</a></td> 
     </tr>
 
     <tr>
 
         <td>General OCR</td>
 
@@ -259,7 +259,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
 
     </tr>
 
 </table>
 
 
-> ❗Note: All the above features are implemented based on GPU/CPU. PaddleX can also perform fast inference and secondary development on mainstream hardware such as Kunlun, Ascend, Cambricon, and Hygon. The following table details the support status of the model production line, and for the specific list of supported models, please refer to [Model List (MLU)](../docs/support_list/model_list_mlu_en.md) / [Model List (NPU)](../docs/support_list/model_list_npu_en.md) / [Model List (XPU)](../docs/support_list/model_list_xpu_en.md) / [Model List DCU](../docs/support_list/model_list_dcu_en.md). We are adapting more models and promoting the implementation of high-performance and service-oriented deployment on mainstream hardware.
 
+> ❗Note: All the above features are implemented based on GPU/CPU. PaddleX can also perform fast inference and secondary development on mainstream hardware such as Kunlun, Ascend, Cambricon, and Hygon. The following table details the support status of the model pipeline, and for the specific list of supported models, please refer to [Model List (MLU)](./docs/support_list/model_list_mlu_en.md) / [Model List (NPU)](./docs/support_list/model_list_npu_en.md) / [Model List (XPU)](./docs/support_list/model_list_xpu_en.md) / [Model List DCU](./docs/support_list/model_list_dcu_en.md). We are adapting more models and promoting the implementation of high-performance and service-oriented deployment on mainstream hardware.
 
 
 
 <details>
 
@@ -267,7 +267,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
 
 
 <table>
 
   <tr>
 
-    <th>Production Line Name</th>
 
+    <th>pipeline Name</th>
 
     <th>NPU 910B</th>
 
     <th>XPU R200/R300</th>
 
     <th>MLU 370X8</th>
 
@@ -363,7 +363,7 @@ python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.
 
 * **Installing PaddleX**
 
 
 ```bash
 
-pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0.beta1-py3-none-any.whl 
+pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0b1-py3-none-any.whl
 
 ```
 
 
 > ❗For more installation methods, refer to the [PaddleX Installation Guide](./docs/installation/installation_en.md).
 
@@ -371,7 +371,7 @@ pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddlex-3.0.0
 
 
 ### 💻 CLI Usage
 
 
-One command can quickly experience the production line effect, the unified CLI format is:
 
+One command can quickly experience the pipeline effect, the unified CLI format is:
 
 
 ```bash
 
 paddlex --pipeline [Pipeline Name] --input [Input Image] --device [Running Device]
 
@@ -400,26 +400,26 @@ The visualization result is as follows:
 
 
 </details>
 
 
-For other pipelines, just adjust the `pipeline` parameter to the corresponding name of the production line. Below is a list of each production line's corresponding parameter name and detailed usage explanation:
 
+For other pipelines, just adjust the `pipeline` parameter to the corresponding name of the pipeline. Below is a list of each pipeline's corresponding parameter name and detailed usage explanation:
 
 
 <details>
 
   <summary>👉 More CLI usage and explanations for pipelines</summary>
 
 
-| Production Line Name           | Corresponding Parameter               | Detailed Explanation                                                                                                      |
 
+| pipeline Name           | Corresponding Parameter               | Detailed Explanation                                                                                                      |
 
 |-------------------------------|-------------------------------------|---------------------------------------------------------------------------------------------------------------|
 
 | Document Scene Information Extraction |                                                                                                                                                                                                                              |
 
-| General Image Classification         | `paddlex --pipeline image_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg  --device gpu:0`                           |
 
-| General Object Detection            | `paddlex --pipeline object_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png  --device gpu:0`                                   |
 
-| General Instance Segmentation       | `paddlex --pipeline instance_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_instance_segmentation_004.png  --device gpu:0`                         |
 
-| General Semantic Segmentation       | `paddlex --pipeline semantic_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png  --device gpu:0`                              |
 
-| General Image Multilabel Classification | `paddlex --pipeline multilabel_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/garbage_demo.png  --device gpu:0`                                          |
 
-| Small Object Detection              | `paddlex --pipeline smallobject_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/garbage_demo.png  --device gpu:0`                                              |
 
-| Image Anomaly Detection            |                                                                                                                                                                                                                              |
 
-| General OCR                        | `paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png  --device gpu:0`                                                             |
 
-| General Table Recognition          | `paddlex --pipeline table_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg  --device gpu:0`                                             |
 
-| General Time Series Forecasting    | `paddlex --pipeline ts_forecast --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_fc.csv  --device` gpu:0                                                                    |
 
-| General Time Series Anomaly Detection | `paddlex --pipeline ts_anomaly_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/doc_images/practical_tutorial/timeseries_anomaly_detection/test.csv  --device gpu:0` |
 
-| General Time Series Classification  | `paddlex --pipeline ts_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/doc_images/practical_tutorial/timeseries_classification/test.csv  --device gpu:0`       |
 
+| General Image Classification         | `paddlex --pipeline image_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg --device gpu:0`                           |
 
+| General Object Detection            | `paddlex --pipeline object_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png --device gpu:0`                                   |
 
+| General Instance Segmentation       | `paddlex --pipeline instance_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_instance_segmentation_004.png --device gpu:0`                         |
 
+| General Semantic Segmentation       | `paddlex --pipeline semantic_segmentation --input https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/application/semantic_segmentation/makassaridn-road_demo.png --device gpu:0`                              |
 
+| General Image Multilabel Classification | `paddlex --pipeline multi_label_image_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg --device gpu:0`                                          |
 
+| Small Object Detection              | `paddlex --pipeline small_object_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/small_object_detection.jpg --device gpu:0`                                              |
 
+| Image Anomaly Detection            | `paddlex --pipeline anomaly_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/uad_grid.png --device gpu:0`  |
 
+| General OCR                        | `paddlex --pipeline OCR --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_002.png --device gpu:0`                                                             |
 
+| General Table Recognition          | `paddlex --pipeline table_recognition --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg --device gpu:0`                                             |
 
+| General Time Series Forecasting    | `paddlex --pipeline ts_fc --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_fc.csv --device gpu:0`                                                                    |
 
+| General Time Series Anomaly Detection | `paddlex --pipeline ts_ad --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_ad.cs --device gpu:0` |
 
+| General Time Series Classification  | `paddlex --pipeline ts_cls --input https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_cls.csv --device gpu:0`       |
 
 
 
 
@@ -427,41 +427,39 @@ For other pipelines, just adjust the `pipeline` parameter to the corresponding n
 
 
 ### 📝 Python Script Usage
 
 
-A few lines of code can complete the quick inference of the production line, the unified Python script format is as follows:
 
+A few lines of code can complete the quick inference of the pipeline, the unified Python script format is as follows:
 
 ```python
 
 from paddlex import create_pipeline
 
 
 pipeline = create_pipeline(pipeline=[Pipeline Name])
 
 output = pipeline.predict([Input Image Name])
 
-for batch in output:
 
-    for item in batch:
 
-        res = item['result']
 
-        res.print()
 
-        res.save_to_img("./output/")
 
-        res.save_to_json("./output/")
 
+for res in output:
 
+    res.print()
 
+    res.save_to_img("./output/")
 
+    res.save_to_json("./output/")
 
 ```
 
 The following steps are executed:
 
 
-* `create_pipeline()` instantiates the production line object
 
-* Passes the image and calls the `predict` method of the production line object for inference prediction
 
+* `create_pipeline()` instantiates the pipeline object
 
+* Passes the image and calls the `predict` method of the pipeline object for inference prediction
 
 * Processes the prediction results
 
 
-For other pipelines in Python scripts, just adjust the `pipeline` parameter of the `create_pipeline()` method to the corresponding name of the production line. Below is a list of each production line's corresponding parameter name and detailed usage explanation:
 
+For other pipelines in Python scripts, just adjust the `pipeline` parameter of the `create_pipeline()` method to the corresponding name of the pipeline. Below is a list of each pipeline's corresponding parameter name and detailed usage explanation:
 
 <details>
 
   <summary>👉 More Python script usage for pipelines</summary>
 
 
-| Production Line Name           | Corresponding Parameter               | Detailed Explanation                                                                                                      |
 
+| pipeline Name           | Corresponding Parameter               | Detailed Explanation                                                                                                      |
 
 |-------------------------------|-------------------------------------|---------------------------------------------------------------------------------------------------------------|
 
 | PP-ChatOCRv3-doc   | `PP-ChatOCRv3-doc` | [PP-ChatOCRv3-doc Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md) |
 
 |  Image Classification       | `image_classification` | [ Image Classification Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md) |
 
 |  Object Detection       | `object_detection` | [ Object Detection Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md) |
 
 |  Instance Segmentation       | `instance_segmentation` | [ Instance Segmentation Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation_en.md) |
 
 |  Semantic Segmentation       | `semantic_segmentation` | [ Semantic Segmentation Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation_en.md) |
 
-|  Image Multi-Label Classification | `multilabel_classification` | [ Image Multi-Label Classification Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_lassification_en.md) |
 
+|  Image Multi-Label Classification | `multilabel_classification` | [ Image Multi-Label Classification Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md) |
 
 | Small Object Detection         | `small_object_detection` | [Small Object Detection Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md) |
 
 | Image Anomaly Detection       | `image_classification` | [Image Anomaly Detection Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md) |
 
-|  OCR            | `OCR` | [ OCR Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/ocr_pipelies/OCR_en.md) |
 
-|  Form Recognition       | `table_recognition` | [ Form Recognition Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/ocr_pipelies/table_recognition_en.md) |
 
+|  OCR            | `OCR` | [ OCR Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/ocr_pipelines/OCR_en.md) |
 
+|  Form Recognition       | `table_recognition` | [ Form Recognition Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md) |
 
 |  Time Series Forecast       | `ts_forecast` | [ Time Series Forecast Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md) |
 
 |  Time Series Anomaly Detection   | `ts_anomaly_detection` | [ Time Series Anomaly Detection Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md) |
 
 |  Time Series Classification       | `ts_cls` | [ Time Series Classification Pipeline Python Script Usage Instructions](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md) |
 
@@ -477,48 +475,48 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 
 </details>
 
 
 <details open>
 
-<summary> <b> 🔥 Production Line Usage </b></summary>
 
+<summary> <b> 🔥 pipeline Usage </b></summary>
 
 
-* [📑 PaddleX Production Line Usage Overview](./docs/pipeline_usage/pipeline_develop_guide_en.md)
 
+* [📑 PaddleX pipeline Usage Overview](./docs/pipeline_usage/pipeline_develop_guide_en.md)
 
 
 * <details>
 
     <summary> <b> 📝 Text and Image Intelligent Analysis </b></summary>
 
 
-   * [📄 Document Scene Information Extraction v3 Production Line Usage Guide](./docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md)
 
+   * [📄 Document Scene Information Extraction v3 pipeline Usage Guide](./docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md)
 
   </details>
 
 
 * <details>
 
     <summary> <b> 🔍 OCR </b></summary>
 
 
-    * [📜 General OCR Production Line Usage Guide](./docs/pipeline_usage/tutorials/ocr_pipelies/OCR_en.md)
 
-    * [📊 Form Recognition Production Line Usage Guide](./docs/pipeline_usage/tutorials/ocr_pipelies/table_recognition_en.md)
 
+    * [📜 General OCR pipeline Usage Guide](./docs/pipeline_usage/tutorials/ocr_pipelines/OCR_en.md)
 
+    * [📊 Form Recognition pipeline Usage Guide](./docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md)
 
   </details>
 
 
 * <details>
 
     <summary> <b> 🎥 Computer Vision </b></summary>
 
 
-   * [🖼️ General Image Classification Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md)
 
-   * [🎯 General Object Detection Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/object_detection_en.md)
 
-   * [📋 General Instance Segmentation Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation_en.md)
 
-   * [🗣️ General Semantic Segmentation Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation_en.md)
 
-   * [🏷️ Image Multi-Label Classification Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md)
 
-   * [🔍 Small Object Detection Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md)
 
-   * [🖼️ Image Anomaly Detection Production Line Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md)
 
+   * [🖼️ General Image Classification pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md)
 
+   * [🎯 General Object Detection pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/object_detection_en.md)
 
+   * [📋 General Instance Segmentation pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation_en.md)
 
+   * [🗣️ General Semantic Segmentation pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation_en.md)
 
+   * [🏷️ Image Multi-Label Classification pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md)
 
+   * [🔍 Small Object Detection pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection_en.md)
 
+   * [🖼️ Image Anomaly Detection pipeline Usage Guide](./docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md)
 
   </details>
 
   
 * <details>
 
     <summary> <b> ⏱️ Time Series Analysis</b> </summary>
 
 
-   * [📈 General Time Series Forecasting Production Line Usage Guide](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md)
 
-   * [📉 General Time Series Anomaly Detection Production Line Usage Guide](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md)
 
-   * [🕒 General Time Series Classification Production Line Usage Guide](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md)
 
+   * [📈 General Time Series Forecasting pipeline Usage Guide](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md)
 
+   * [📉 General Time Series Anomaly Detection pipeline Usage Guide](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md)
 
+   * [🕒 General Time Series Classification pipeline Usage Guide](./docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md)
 
   </details>
 
 
 * <details>
 
     <summary> <b>🔧 Related Documentation</b> </summary>
 
 
-   * [🖥️ PaddleX Production Line Command Line Usage Guide](./docs/pipeline_usage/instructions/pipeline_CLI_usage_en.md)
 
-   * [📝 PaddleX Production Line Python Script Usage Guide](./docs/pipeline_usage/instructions/pipeline_python_API_en.md)
 
+   * [🖥️ PaddleX pipeline Command Line Usage Guide](./docs/pipeline_usage/instructions/pipeline_CLI_usage_en.md)
 
+   * [📝 PaddleX pipeline Python Script Usage Guide](./docs/pipeline_usage/instructions/pipeline_python_API_en.md)
 
   </details>
 
   
 </details>
 
@@ -578,9 +576,9 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 
 * <details>
 
   <summary> <b> ⏱️ Time Series Analysis </b></summary>
 
 
-  * [📈 Time Series Forecasting Module Usage Guide](./docs/module_usage/tutorials/time_series_modules/time_series_forecasting_en.md)
 
-  * [🚨 Time Series Anomaly Detection Module Usage Guide](./docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection_en.md)
 
-  * [🕒 Time Series Classification Module Usage Guide](./docs/module_usage/tutorials/time_series_modules/time_series_classification_en.md)
 
+  * [📈 Time Series Forecasting Module Usage Guide](./docs/module_usage/tutorials/ts_modules/time_series_forecast_en.md)
 
+  * [🚨 Time Series Anomaly Detection Module Usage Guide](./docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md)
 
+  * [🕒 Time Series Classification Module Usage Guide](./docs/module_usage/tutorials/ts_modules/time_series_classification_en.md)
 
   </details>
 
     
 * <details>
 
@@ -594,7 +592,7 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 
 </details>
 
 
 <details>
 
-  <summary> <b> 🏗️ Model Production Line Deployment </b></summary>
 
+  <summary> <b> 🏗️ Model pipeline Deployment </b></summary>
 
 
   * [🚀 PaddleX High-Performance Deployment Guide](./docs/pipeline_deploy/high_performance_deploy_en.md)
 
   * [🖥️ PaddleX Service Deployment Guide](./docs/pipeline_deploy/service_deploy_en.md)