fix docs (#2225)

* fix docs

* fix docs

README_en.md

@@ -575,9 +575,9 @@ For other pipelines in Python scripts, just adjust the `pipeline` parameter of t
 * <details open>
   <summary> <b> ⏱️ Time Series Analysis </b></summary>
 
-  * [📈 Time Series Forecasting Module Usage Guide](./docs/module_usage/tutorials/ts_modules/time_series_forecast_en.md)
+  * [📈 Time Series Forecasting Module Usage Guide](./docs/module_usage/tutorials/time_series_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)
+  * [🕒 Time Series Classification Module Usage Guide](./docs/module_usage/tutorials/time_series_modules/time_series_classification_en.md)
   </details>
     
 * <details open>

docs/module_usage/tutorials/cv_modules/semantic_segmentation.md

@@ -293,7 +293,7 @@ python main.py -c paddlex/configs/semantic_segmentation/PP-LiteSeg-T.yaml \
 
 * 指定模型的.yaml 配置文件路径（此处为` PP-LiteSeg-T.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/best_model/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/best_model/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 

docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md

@@ -35,7 +35,7 @@ for res in output:
 关于更多 PaddleX 的单模型推理的 API 的使用方法，可以参考的使用方法，可以参考[PaddleX单模型Python脚本使用说明](../../instructions/model_python_API.md)。
 
 ## 四、二次开发
-如果你追求更高精度的现有模型，可以使用PaddleX的二次开发能力，开发更好的文档图像方向分类模型模型。在使用PaddleX开发文档图像方向分类模型模型之前，请务必安装PaddleX的分类相关的模型训练能力，安装过程可以参考 [PaddleX本地安装教程](../../../installation/installation.md)
+如果你追求更高精度的现有模型，可以使用PaddleX的二次开发能力，开发更好的文档图像方向分类模型。在使用PaddleX开发文档图像方向分类模型之前，请务必安装PaddleX的分类相关的模型训练能力，安装过程可以参考 [PaddleX本地安装教程](../../../installation/installation.md)
 
 ### 4.1 数据准备
 在进行模型训练前，需要准备相应任务模块的数据集。PaddleX 针对每一个模块提供了数据校验功能，**只有通过数据校验的数据才可以进行模型训练**。此外，PaddleX为每一个模块都提供了 Demo 数据集，您可以基于官方提供的 Demo 数据完成后续的开发。若您希望用私有数据集进行后续的模型训练，可以参考[PaddleX图像分类任务模块数据准备教程](../../../data_annotations/cv_modules/image_classification.md)。
@@ -118,7 +118,7 @@ python main.py -c paddlex/configs/doc_text_orientation/PP-LCNet_x1_0_doc_ori.yam
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/doc_img_ori_classification/01.png)
 </details>
 
-#### 4.1.3 数据集格式转换/数据集划分（可选）（折叠）
+#### 4.1.3 数据集格式转换/数据集划分（可选）
 在您完成数据校验之后，可以通过**修改配置文件**或是**追加超参数**的方式对数据集的格式进行转换，也可以对数据集的训练/验证比例进行重新划分。
 
 <details>

docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification_en.md

@@ -260,7 +260,7 @@ Similar to model training and evaluation, the following steps are required:
 
 * Specify the model weights path: -o Predict.model_dir="./output/best_accuracy/inference"
 
-Specify the input data path: `-o Predict.inputh="..."` Other related parameters can be set by modifying the fields under Global and Predict in the `.yaml` configuration file. For details, refer to PaddleX Common Model Configuration File Parameter Description.
+Specify the input data path: `-o Predict.input="..."` Other related parameters can be set by modifying the fields under Global and Predict in the `.yaml` configuration file. For details, refer to PaddleX Common Model Configuration File Parameter Description.
 
 Alternatively, you can use the PaddleX wheel package for inference, easily integrating the model into your own projects.
 
@@ -270,7 +270,7 @@ The model can be directly integrated into the PaddleX pipeline or into your own
 
 1.**Pipeline Integration**
 
-The document image classification module can be integrated into PaddleX pipelines such as the [Document Scene Information Extraction Pipeline (PP-ChatOCRv3)](/docs_new/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the The document image classification module's model.
+The document image classification module can be integrated into PaddleX pipelines such as the [Document Scene Information Extraction Pipeline (PP-ChatOCRv3)](../../..//pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the The document image classification module's model.
 
 2.**Module Integration**
 

docs/module_usage/tutorials/ocr_modules/seal_text_detection.md

@@ -39,7 +39,7 @@ for res in output:
 如果你追求更高精度的现有模型，可以使用PaddleX的二次开发能力，开发更好的印章文本检测模型。在使用PaddleX开发印章文本检测模型之前，请务必安装 PaddleOCR 插件，安装过程可以参考[PaddleX本地安装教程](../../../installation/installation.md)。
 
 ### 4.1 数据准备
-在进行模型训练前，需要准备相应任务模块的数据集。PaddleX 针对每一个模块提供了数据校验功能，**只有通过数据校验的数据才可以进行模型训练**。此外，PaddleX 为每一个模块都提供了 Demo 数据集，您可以基于官方提供的 Demo 数据完成后续的开发。若您希望用私有数据集进行后续的模型训练，可以参考[PaddleX文本检测/文本识别任务模块数据标注教程](../../../data_annotations/ocr_modules/text_detection_regognition.md)。
+在进行模型训练前，需要准备相应任务模块的数据集。PaddleX 针对每一个模块提供了数据校验功能，**只有通过数据校验的数据才可以进行模型训练**。此外，PaddleX 为每一个模块都提供了 Demo 数据集，您可以基于官方提供的 Demo 数据完成后续的开发。若您希望用私有数据集进行后续的模型训练，可以参考[PaddleX文本检测/文本识别任务模块数据标注教程](../../../data_annotations/ocr_modules/text_detection_recognition.md)。
 
 #### 4.1.1 Demo 数据下载
 您可以参考下面的命令将 Demo 数据集下载到指定文件夹：

docs/module_usage/tutorials/ocr_modules/seal_text_detection_en.md

@@ -10,7 +10,7 @@ The seal text detection module typically outputs multi-point bounding boxes arou
 <details>
    <summary> 👉 Model List Details</summary>
 
-|Model Name| Hmean（%）|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size (M)| Introduce |
+|Model Name| Hmean（%）|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size (M)| Description |
 |-|-|-|-|-|-|
 |PP-OCRv4_server_seal_det |98.21|84.341|2425.06|109 M|The server-side seal text detection model of PP-OCRv4 boasts higher accuracy and is suitable for deployment on better-equipped servers.|
 |PP-OCRv4_mobile_seal_det|96.47|10.5878|131.813|4.6 M| The mobile-side seal text detection model of PP-OCRv4, on the other hand, offers greater efficiency and is suitable for deployment on end devices.|
@@ -43,7 +43,7 @@ If you seek higher accuracy, you can leverage PaddleX's custom development capab
 
 ### 4.1 Dataset Preparation
 
-Before model training, you need to prepare a dataset for the task. PaddleX provides data validation functionality for each module. **Only data that passes validation can be used for model training.** Additionally, PaddleX provides demo datasets for each module, which you can use to complete subsequent development. If you wish to use private datasets for model training, refer to [PaddleX Seal Text Detection Task Module Data Preparation Tutorial](../../../data_annotations/cv_modules/text_detection_seal_en.md).
+Before model training, you need to prepare a dataset for the task. PaddleX provides data validation functionality for each module. **Only data that passes validation can be used for model training.** Additionally, PaddleX provides demo datasets for each module, which you can use to complete subsequent development. If you wish to use private datasets for model training, refer to [PaddleX Text Detection and Recognition Task Module Data Preparation Tutorial](../../../data_annotations/ocr_modules/text_detection_recognition_en.md).
 
 #### 4.1.1 Demo Data Download
 
@@ -275,7 +275,7 @@ The model can be directly integrated into the PaddleX pipeline or into your own
 
 1. **Pipeline Integration**
 
-The document Seal Text Detection module can be integrated into PaddleX pipelines such as the [General OCR Pipeline](../../../pipeline_usage/tutorials/ocr_pipelines/OCR_en.md) and [Document Scene Information Extraction Pipeline v3 (PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the text detection module of the relevant pipeline.
+The document Seal Text Detection module can be integrated into PaddleX pipelines such as the [General OCR Pipeline](../../../pipeline_usage/tutorials/ocr_pipelines/OCR_en.md) and [Document Scene Information Extraction Pipeline v3 (PP-ChatOCRv3)](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md). Simply replace the model path to update the text detection module of the relevant pipeline.
 
 2. **Module Integration**
 

docs/module_usage/tutorials/ocr_modules/text_image_unwarping.md

@@ -32,7 +32,7 @@ for res in output:
     res.save_to_img("./output/")
     res.save_to_json("./output/res.json")
 ```
-关于更多 PaddleX 的单模型推理的 API 的使用方法，可以参考[PaddleX单模型Python脚本使用说明](/docs_new/module_usage/instructions/model_python_API.md)。
+关于更多 PaddleX 的单模型推理的 API 的使用方法，可以参考[PaddleX单模型Python脚本使用说明](../../instructions/model_python_API.md)。
 
 ## 四、二次开发
 当前模块暂时不支持微调训练，仅支持推理集成。关于该模块的微调训练，计划在未来支持。

docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md

@@ -1,3 +1,5 @@
+简体中文 | [English](time_series_anomaly_detection_en.md)
+
 # 时序异常检测模块使用教程
 
 ## 一、概述
@@ -131,13 +133,13 @@ python main.py -c paddlex/configs/ts_anomaly_detection/AutoEncoder_ad.yaml \
 
 **（1）数据集格式转换**
 
-时序异常检测支持 `xlsx 和 xlss` 格式的数据集转换为 `csv` 格式。
+时序异常检测支持 `xlsx 和 xls` 格式的数据集转换为 `csv` 格式。
 
 数据集校验相关的参数可以通过修改配置文件中 `CheckDataset` 下的字段进行设置，配置文件中部分参数的示例说明如下：
 
 * `CheckDataset`:
   * `convert`:
-    * `enable`: 是否进行数据集格式转换，支持 `xlsx 和 xlss` 格式的数据集转换为 `CSV` 格式，默认为 `False`;
+    * `enable`: 是否进行数据集格式转换，支持 `xlsx 和 xls` 格式的数据集转换为 `CSV` 格式，默认为 `False`;
     * `src_dataset_type`: 如果进行数据集格式转换，无需设置源数据集格式，默认为 `null`；
 则需要修改配置如下：
 
@@ -260,7 +262,7 @@ python main.py -c paddlex/configs/ts_anomaly_detection/AutoEncoder_ad.yaml \
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
 
-在模型评估时，需要指定模型权重文件路径，每个配置文件中都内置了默认的权重保存路径，如需要改变，只需要通过追加命令行参数的形式进行设置即可，如`-o Evaluate.weight_path=``./output/best_model/model.pdparams`。
+在模型评估时，需要指定模型权重文件路径，每个配置文件中都内置了默认的权重保存路径，如需要改变，只需要通过追加命令行参数的形式进行设置即可，如`-o Evaluate.weight_path=./output/best_model/model.pdparams`。
 
 在完成模型评估后，通常有以下产出：
 
@@ -285,7 +287,7 @@ python main.py -c paddlex/configs/ts_anomaly_detection/AutoEncoder_ad.yaml \
 
 * 指定模型的`.yaml` 配置文件路径（此处为`AutoEncoder_ad.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
 

docs/module_usage/tutorials/time_series_modules/time_series_classification.md

@@ -1,3 +1,5 @@
+简体中文 | [English](time_series_classification_en.md)
+
 # 时序分类模块使用教程
 
 ## 一、概述
@@ -138,13 +140,13 @@ python main.py -c paddlex/configs/ts_classification/TimesNet_cls.yaml \
 
 **（1）数据集格式转换**
 
-时序分类支持 `xlsx 和 xlss` 格式的数据集转换为 `csv` 格式。
+时序分类支持 `xlsx 和 xls` 格式的数据集转换为 `csv` 格式。
 
 数据集校验相关的参数可以通过修改配置文件中 `CheckDataset` 下的字段进行设置，配置文件中部分参数的示例说明如下：
 
 * `CheckDataset`:
   * `convert`:
-    * `enable`: 是否进行数据集格式转换，支持 `xlsx和xlss` 格式的数据集转换为 `CSV` 格式，默认为 `False`;
+    * `enable`: 是否进行数据集格式转换，支持 `xlsx和xls` 格式的数据集转换为 `CSV` 格式，默认为 `False`;
     * `src_dataset_type`: 如果进行数据集格式转换，无需设置源数据集格式，默认为 `null`；
 则需要修改配置如下：
 
@@ -268,11 +270,11 @@ python main.py -c paddlex/configs/ts_classification/TimesNet_cls.yaml \
   <summary>👉 <b>更多说明（点击展开）</b></summary>
 
 
-在模型评估时，需要指定模型权重文件路径，每个配置文件中都内置了默认的权重保存路径，如需要改变，只需要通过追加命令行参数的形式进行设置即可，如`-o Evaluate.weight_path=``./output/best_model/model.pdparams`。
+在模型评估时，需要指定模型权重文件路径，每个配置文件中都内置了默认的权重保存路径，如需要改变，只需要通过追加命令行参数的形式进行设置即可，如`-o Evaluate.weight_path=./output/best_model/model.pdparams`。
 
 在完成模型评估后，通常有以下产出：
 
-在完成模型评估后，会产出`evaluate_result.json，其记录了`评估的结果，具体来说，记录了评估任务是否正常完成，以及模型的评估指标，包含 Acc Top1。
+在完成模型评估后，会产出`evaluate_result.json，其记录了`评估的结果，具体来说，记录了评估任务是否正常完成，以及模型的评估指标，包含 Acc 和 F1 score。
 
 </details>
 
@@ -290,9 +292,9 @@ python main.py -c paddlex/configs/ts_classification/TimesNet_cls.yaml \
 ```
 与模型训练和评估类似，需要如下几步：
 
-* 指定模型的`.yaml` 配置文件路径（此处为`DLinear.yaml`）
+* 指定模型的`.yaml` 配置文件路径（此处为`TimesNet_cls.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX时序任务模型配置文件参数说明](../../../module_usage/instructions/config_parameters_time_series.md)。
 

docs/module_usage/tutorials/time_series_modules/time_series_forecasting.md

@@ -1,3 +1,5 @@
+简体中文 | [English](time_series_forecast_en.md)
+
 # 时序预测模块使用教程
 
 ## 一、概述
@@ -163,13 +165,13 @@ python main.py -c paddlex/configs/ts_forecast/DLinear.yaml \
 
 **（1）数据集格式转换**
 
-时序预测支持 `xlsx 和 xlss` 格式的数据集转换为 `csv` 格式。
+时序预测支持 `xlsx 和 xls` 格式的数据集转换为 `csv` 格式。
 
 数据集校验相关的参数可以通过修改配置文件中 `CheckDataset` 下的字段进行设置，配置文件中部分参数的示例说明如下：
 
 * `CheckDataset`:
   * `convert`:
-    * `enable`: 是否进行数据集格式转换，支持 `xlsx和xlss` 格式的数据集转换为 `CSV` 格式，默认为 `False`;
+    * `enable`: 是否进行数据集格式转换，支持 `xlsx和xls` 格式的数据集转换为 `CSV` 格式，默认为 `False`;
     * `src_dataset_type`: 如果进行数据集格式转换，无需设置源数据集格式，默认为 `null`，；
 则需要修改配置如下：
 
@@ -295,7 +297,7 @@ python main.py -c paddlex/configs/ts_forecast/DLinear.yaml \
 
 
 
-在模型评估时，需要指定模型权重文件路径，每个配置文件中都内置了默认的权重保存路径，如需要改变，只需要通过追加命令行参数的形式进行设置即可，如`-o Evaluate.weight_path=``./output/best_model/model.pdparams`。
+在模型评估时，需要指定模型权重文件路径，每个配置文件中都内置了默认的权重保存路径，如需要改变，只需要通过追加命令行参数的形式进行设置即可，如`-o Evaluate.weight_path=./output/best_model/model.pdparams`。
 
 在完成模型评估后，通常有以下产出：
 
@@ -319,7 +321,7 @@ python main.py -c paddlex/configs/ts_forecast/DLinear.yaml \
 
 * 指定模型的`.yaml` 配置文件路径（此处为`DLinear.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 

docs/module_usage/tutorials/ts_modules/time_series_anomaly_detection_en.md

@@ -131,13 +131,13 @@ After completing the data validation, you can convert the dataset format and re-
 
 **(1) Dataset Format Conversion**
 
-Time series anomaly detection supports converting `xlsx` and `xlss` format datasets to `csv` format.
+Time series anomaly detection supports converting `xlsx` and `xls` format datasets to `csv` format.
 
 Parameters related to dataset validation can be set by modifying the fields under `CheckDataset` in the configuration file. Some example parameter descriptions in the configuration file are as follows:
 
 * `CheckDataset`:
   * `convert`:
-    * `enable`: Whether to convert the dataset format, supporting `xlsx` and `xlss` formats to `CSV` format, default is `False`;
+    * `enable`: Whether to convert the dataset format, supporting `xlsx` and `xls` formats to `CSV` format, default is `False`;
     * `src_dataset_type`: If dataset format conversion is performed, the source dataset format does not need to be set, default is `null`;
 
 To enable format conversion, modify the configuration as follows:

docs/module_usage/tutorials/ts_modules/time_series_classification_en.md

@@ -143,13 +143,13 @@ After completing data validation, you can convert the dataset format and re-spli
 
 **(1) Dataset Format Conversion**
 
-Time-series classification supports converting `xlsx` and `xlss` format datasets to `csv` format.
+Time-series classification supports converting `xlsx` and `xls` format datasets to `csv` format.
 
 Parameters related to dataset validation can be set by modifying the fields under `CheckDataset` in the configuration file. Examples of some parameters in the configuration file are as follows:
 
 * `CheckDataset`:
   * `convert`:
-    * `enable`: Whether to perform dataset format conversion, supporting conversion from `xlsx` and `xlss` formats to `CSV` format, default is `False`;
+    * `enable`: Whether to perform dataset format conversion, supporting conversion from `xlsx` and `xls` formats to `CSV` format, default is `False`;
     * `src_dataset_type`: If dataset format conversion is performed, the source dataset format does not need to be set, default is `null`;
 
 To enable format conversion, modify the configuration as follows:
@@ -282,7 +282,7 @@ When evaluating the model, you need to specify the model weights file path. Each
 
 After completing the model evaluation, typically, the following outputs are generated:
 
-Upon completion of model evaluation, an `evaluate_result.json` file is produced, which records the evaluation results, specifically whether the evaluation task was completed successfully and the model's evaluation metrics, including Top-1 Accuracy.
+Upon completion of model evaluation, an `evaluate_result.json` file is produced, which records the evaluation results, specifically whether the evaluation task was completed successfully and the model's evaluation metrics, including Top-1 Accuracy and F1 score.
 
 </details>
 

docs/module_usage/tutorials/ts_modules/time_series_forecast_en.md

@@ -173,13 +173,13 @@ After completing dataset verification, you can convert the dataset format or re-
 
 **(1) Dataset Format Conversion**
 
-Time Series Forecasting supports converting `xlsx` and `xlss` format datasets to the required format.
+Time Series Forecasting supports converting `xlsx` and `xls` format datasets to the required format.
 
 Parameters related to dataset verification can be set by modifying the `CheckDataset` fields in the configuration file. Example explanations for some parameters in the configuration file are as follows:
 
 * `CheckDataset`:
   * `convert`:
-    * `enable`: Whether to enable dataset format conversion, supporting `xlsx` and `xlss` format conversion, default is `False`;
+    * `enable`: Whether to enable dataset format conversion, supporting `xlsx` and `xls` format conversion, default is `False`;
     * `src_dataset_type`: If dataset format conversion is enabled, the source dataset format needs to be set, default is `null`.
 
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md

@@ -576,7 +576,7 @@ Choose the appropriate deployment method for your model pipeline based on your n
 If the default model weights provided by the General Time Series Anomaly Detection Pipeline do not meet your requirements for accuracy or speed in your specific scenario, you can try to further fine-tune the existing model using **your own domain-specific or application-specific data** to improve the recognition performance of the pipeline in your scenario.
 
 ### 4.1 Model Fine-tuning
-Since the General Time Series Anomaly Detection Pipeline includes a time series anomaly detection module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/ts_modules/time_series_anomaly_detection_en.md#iv-custom-development) section in the [Time Series Modules Development Tutorial](../../../module_usage/tutorials/ts_modules/time_series_anomaly_detection_en.md) to fine-tune the time series anomaly detection model using your private dataset.
+Since the General Time Series Anomaly Detection Pipeline includes a time series anomaly detection module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/time_series_modules/time_series_anomaly_detection_en.md#iv-custom-development) section in the [Time Series Modules Development Tutorial](../../../module_usage/tutorials/time_series_modules/time_series_anomaly_detection_en.md) to fine-tune the time series anomaly detection model using your private dataset.
 
 ### 4.2 Model Application
 After fine-tuning with your private dataset, you will obtain local model weights files.

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md

@@ -525,7 +525,7 @@ Choose the appropriate deployment method based on your needs to proceed with sub
 If the default model weights provided by the General Time Series Classification Pipeline do not meet your requirements for accuracy or speed in your specific scenario, you can try to further fine-tune the existing model using **your own domain-specific or application-specific data** to improve the recognition performance of the pipeline in your scenario.
 
 ### 4.1 Model Fine-tuning
-Since the General Time Series Classification Pipeline includes a time series classification module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/ts_modules/time_series_classification_en.md#iv-custom-development) section in the [Time Series Classification Module Tutorial](../../../module_usage/tutorials/ts_modules/time_series_classification_en.md) to fine-tune the time series classification model using your private dataset.
+Since the General Time Series Classification Pipeline includes a time series classification module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/time_series_modules/time_series_classification_en.md#iv-custom-development) section in the [Time Series Classification Module Tutorial](../../../module_usage/tutorials/time_series_modules/time_series_classification_en.md) to fine-tune the time series classification model using your private dataset.
 
 ### 4.2 Model Application
 After fine-tuning the model with your private dataset, you will obtain local model weights.

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md

@@ -577,7 +577,7 @@ Choose the appropriate deployment method for your model pipeline based on your n
 If the default model weights provided by the General Time Series Forecasting Pipeline do not meet your requirements in terms of accuracy or speed in your specific scenario, you can try to further fine-tune the existing model using **your own domain-specific or application-specific data** to improve the recognition performance of the pipeline in your scenario.
 
 #### 4.1 Model Fine-tuning
-Since the General Time Series Forecasting Pipeline includes a time series forecasting module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/ts_modules/time_series_forecast_en.md#iv-custom-development) section in the [Time Series Forecasting Module Development Tutorial](../../../module_usage/tutorials/ts_modules/time_series_forecast_en.md) and use your private dataset to fine-tune the time series forecasting model.
+Since the General Time Series Forecasting Pipeline includes a time series forecasting module, if the performance of the pipeline does not meet expectations, you need to refer to the [Customization](../../../module_usage/tutorials/time_series_modules/time_series_forecast_en.md#iv-custom-development) section in the [Time Series Forecasting Module Development Tutorial](../../../module_usage/tutorials/time_series_modules/time_series_forecast_en.md) and use your private dataset to fine-tune the time series forecasting model.
 
 #### 4.2 Model Application
 After fine-tuning with your private dataset, you will obtain local model weight files.

docs/practical_tutorials/ts_anomaly_detection.md

@@ -5,7 +5,7 @@
 PaddleX 提供了丰富的模型产线，模型产线由一个或多个模型组合实现，每个模型产线都能够解决特定的场景任务问题。PaddleX 所提供的模型产线均支持快速体验，如果效果不及预期，也同样支持使用私有数据微调模型，并且 PaddleX 提供了 Python API，方便将产线集成到个人项目中。在使用之前，您首先需要安装 PaddleX， 安装方式请参考[ ](../INSTALL.md)[PaddleX本地安装教程](../installation/installation.md)。此处以一个设备节点的异常检测的任务为例子，介绍模型产线工具的使用流程。
 
 ## 1. 选择产线
-首先，需要根据您的任务场景，选择对应的 PaddleX 产线，本任务该任务旨在识别和标记出设备节点中的异常行为或异常状态，帮助企业和组织及时发现和解决应用服务器节点中的问题，提高系统的可靠性和可用性。了解到这个任务属于时序异常检测任务，对应 PaddleX 的时序异常检测产线。如果无法确定任务和产线的对应关系，您可以在 PaddleX 支持的[PaddleX产线列表(CPU/GPU)](../support_list/pipelines_list.md)中了解相关产线的能力介绍。
+首先，需要根据您的任务场景，选择对应的 PaddleX 产线，本任务旨在识别和标记出设备节点中的异常行为或异常状态，帮助企业和组织及时发现和解决应用服务器节点中的问题，提高系统的可靠性和可用性。了解到这个任务属于时序异常检测任务，对应 PaddleX 的时序异常检测产线。如果无法确定任务和产线的对应关系，您可以在 PaddleX 支持的[PaddleX产线列表(CPU/GPU)](../support_list/pipelines_list.md)中了解相关产线的能力介绍。
 
 ## 2. 快速体验
 PaddleX 提供了两种体验的方式，一种是可以直接通过 PaddleX 在本地体验，另外一种是可以在 **AI Studio 星河社区**上体验。
@@ -49,7 +49,8 @@ tar -xf ./dataset/msl.tar -C ./dataset/
 * **数据注意事项**
   * 时序异常检测是一个无监督学习任务，因此不需要标注训练数据。收集的训练样本尽可能保证都是正常数据，即没有异常，训练集的标签列均设置为 0，或者不设置标签列也是可以的。验证集为了验证精度，需要进行标注，对于在某个时间点是异常的点，该时间点的标签设置为 1，正常的时间点的标签为 0。
   * 缺失值处理：为了保证数据的质量和完整性，可以基于专家经验或统计方法进行缺失值填充。
-  * 非重复性：保证数据是安装时间顺序按行收集的，同一个时间点不能重复出现。
+  * 非重复性：保证数据是按照时间顺序按行收集的，同一个时间点不能重复出现。
+
 ### 4.2 数据集校验
 在对数据集校验时，只需一行命令：
 
@@ -103,7 +104,7 @@ python main.py -c paddlex/configs/ts_anomaly_detection/PatchTST_ad.yaml \
 在训练之前，请确保您已经对数据集进行了校验。完成 PaddleX 模型的训练，只需如下一条命令：
 
 ```
-    python main.py -c paddlex/configs/ts_anomaly_detection/PatchTST_ad.yaml \
+  python main.py -c paddlex/configs/ts_anomaly_detection/PatchTST_ad.yaml \
     -o Global.mode=train \
     -o Global.dataset_dir=./dataset/msl \
     -o Train.epochs_iters=5 \
@@ -126,22 +127,24 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
   * `epochs_iters`：训练轮次数设置；
   * `learning_rate`：训练学习率设置；
   * `batch_size`：训练单卡批大小设置；
-  * `time_col`: 时间列，须结合自己的数据设置时间序列数据集的时间列的列名称;
-  * `feature_cols`:特征变量表示能够判断设备是否异常的相关变量，例如设备是否异常，可能与设备运转时的散热量有关。结合自己的数据，设置特征变量的列名称，可以为多个，多个之间用','分隔。本教程中设备监控数据集中的时间列名有 55 个特征变量，如：0, 1 等;
-  * `freq`：频率，须结合自己的数据设置时间频率，如：1min、5min、1h;
-  * `input_len`: 输入给模型的时间序列长度，会按照该长度对时间序列切片，预测该长度下这一段时序序列是否有异常；输入长度建议结合实际场景考虑。本教程中输入长度为 96。表示希望预测 96 个时间点是否有异常。
+  * `time_col`: 时间列，须结合自己的数据设置时间序列数据集的时间列的列名称；
+  * `feature_cols`:特征变量表示能够判断设备是否异常的相关变量，例如设备是否异常，可能与设备运转时的散热量有关。结合自己的数据，设置特征变量的列名称，可以为多个，多个之间用','分隔。本教程中设备监控数据集中的时间列名有 55 个特征变量，如：0, 1 等；
+  * `freq`：频率，须结合自己的数据设置时间频率，如：1min、5min、1h；
+  * `input_len`: 输入给模型的时间序列长度，会按照该长度对时间序列切片，预测该长度下这一段时序序列是否有异常；输入长度建议结合实际场景考虑。本教程中输入长度为 96。表示希望预测 96 个时间点是否有异常；
   * `label`：代表时序时间点是否异常的编号，异常点为 1，正常点为 0。本教程中异常监控数据集为 label。
 更多超参数介绍，请参考 [PaddleX时序任务模型配置文件参数说明](../module_usage/instructions/config_parameters_time_series.md)。以上参数可以通过追加令行参数的形式进行设置，如指定模式为模型训练：`-o Global.mode=train`；指定前 1 卡 gpu 训练：`-o Global.device=gpu:0`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。
 
-**更多说明（点击展开）**
 
-（折叠开始）
+
+<details>
+   <summary> 更多说明（点击展开） </summary>
 
 * 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段进行设置。
 * PaddleX 对您屏蔽了动态图权重和静态图权重的概念。在模型训练的过程中，会同时产出动态图和静态图的权重，在模型推理时，默认选择静态图权重推理。
 * 训练其他模型时，需要的指定相应的配置文件，模型和配置的文件的对应关系，可以查阅[PaddleX模型列表（CPU/GPU）](../support_list/models_list.md)。
 在完成模型训练后，所有产出保存在指定的输出目录（默认为`./output/`）下，通常有以下产出：
 
+
 **训练产出解释:**
 
 在完成模型训练后，所有产出保存在指定的输出目录（默认为`./output/`）下，通常有以下产出：
@@ -149,8 +152,9 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
 * `train_result.json`：训练结果记录文件，记录了训练任务是否正常完成，以及产出的权重指标、相关文件路径等；
 * `train.log`：训练日志文件，记录了训练过程中的模型指标变化、loss 变化等；
 * `config.yaml`：训练配置文件，记录了本次训练的超参数的配置；
-* `best_accuracy.pdparams.tar`、`scaler.pkl`、`.checkpoints` 、`.inference`：模型权重相关文件，包括网络参数、优化器、EMA、静态图网络参数、静态图网络结构等；
-（折叠结束）
+* `best_accuracy.pdparams.tar`、`scaler.pkl`、`.checkpoints` 、`.inference*`：模型权重相关文件，包括网络参数、优化器、静态图权重等；
+
+</details>
 
 ### 5.2 模型评估
 在完成模型训练后，可以对指定的模型权重文件在验证集上进行评估，验证模型精度。使用 PaddleX 进行模型评估，只需一行命令：
@@ -166,7 +170,7 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
 
 在完成模型评估后，通常有以下产出：
 
-在完成模型评估后，会产出`evaluate_result.json，其记录了`评估的结果，具体来说，记录了评估任务是否正常完成，以及模型的评估指标，包含 f1、recall 和 precision。
+在完成模型评估后，会产出`evaluate_result.json`，其记录了评估的结果，具体来说，记录了评估任务是否正常完成，以及模型的评估指标，包含 f1、recall 和 precision。
 
 ### 5.3 模型调优
 在学习了模型训练和评估后，我们可以通过调整超参数来提升模型的精度。通过合理调整训练轮数，您可以控制模型的训练深度，避免过拟合或欠拟合；而学习率的设置则关乎模型收敛的速度和稳定性。因此，在优化模型性能时，务必审慎考虑这两个参数的取值，并根据实际情况进行灵活调整，以获得最佳的训练效果。
@@ -186,6 +190,7 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
 |实验一|5|0.0001|16|96|1卡|79.5|
 |实验二|5|0.0005|16|96|1卡|80.1|
 |实验三|5|0.001|16|96|1卡|80.9|
+
 增大训练轮次实验结果：
 
 |实验|轮次|学习率|batch_size|输入长度|训练环境|验证集F1 score (%)|
@@ -205,7 +210,7 @@ python main.py -c paddlex/configs/ts_anomaly_detection/PatchTST_ad.yaml \
 
 * 指定模型的`.yaml` 配置文件路径（此处为`PatchTST_ad.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX时序任务模型配置文件参数说明](../module_usage/instructions/config_parameters_time_series.md)。
 

docs/practical_tutorials/ts_anomaly_detection_en.md

@@ -39,7 +39,7 @@ PaddleX provides five end-to-end time series anomaly detection models. For detai
 
 To demonstrate the entire process of time series anomaly detection, we will use the publicly available MSL (Mars Science Laboratory) dataset for model training and validation. The PSM (Planetary Science Mission) dataset, sourced from NASA, comprises 55 dimensions and includes telemetry anomaly data reported by the spacecraft's monitoring system for unexpected event anomalies (ISA). With its practical application background, it better reflects real-world anomaly scenarios and is commonly used to test and validate the performance of time series anomaly detection models. This tutorial will perform anomaly detection based on this dataset.
 
-We have converted the dataset into a standard data format, and you can obtain a sample dataset using the following command. For an introduction to the data format, please refer to the [Time Series Anomaly Detection Module Development Tutorial](../module_usage/tutorials/ts_modules/time_series_anomaly_detection_en.md)。.
+We have converted the dataset into a standard data format, and you can obtain a sample dataset using the following command. For an introduction to the data format, please refer to the [Time Series Anomaly Detection Module Development Tutorial](../module_usage/tutorials/time_series_modules/time_series_anomaly_detection_en.md).
 
 
 You can use the following commands to download the demo dataset to a specified folder:
@@ -50,7 +50,7 @@ wget https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/doc_images/pr
 tar -xf ./dataset/msl.tar -C ./dataset/
 ```
 
-* **Data Considerations**
+**Data Considerations**
  * Time series anomaly detection is an unsupervised learning task, thus labeled training data is not required. The collected training samples should ideally consist solely of normal data, i.e., devoid of anomalies, with the label column in the training set set to 0 or, alternatively, the label column can be omitted entirely. For the validation set, to assess accuracy, labeling is necessary. Points that are anomalous at a particular timestamp should have their labels set to 1, while normal points should have labels of 0.
  * Handling Missing Values: To ensure data quality and integrity, missing values can be imputed based on expert knowledge or statistical methods.
  * Non-Repetitiveness: Ensure that data is collected in chronological order by row, with no duplication of timestamps.
@@ -102,7 +102,7 @@ The above verification results have omitted some data parts. `check_pass` being
 **Note**: Only data that passes the verification can be used for training and evaluation.
 
 ### 4.3 Dataset Format Conversion/Dataset Splitting (Optional)
-If you need to convert the dataset format or re-split the dataset, refer to Section 4.1.3 in the [Time Series Anomaly Detection Module Development Tutorial](../module_usage/tutorials/ts_modules/time_series_anomaly_detection_en.md).
+If you need to convert the dataset format or re-split the dataset, refer to Section 4.1.3 in the [Time Series Anomaly Detection Module Development Tutorial](../module_usage/tutorials/time_series_modules/time_series_anomaly_detection_en.md).
 
 ## 5. Model Training and Evaluation
 ### 5.1 Model Training
@@ -134,6 +134,31 @@ Each model in PaddleX provides a configuration file for model development to set
   * `batch_size`: Training batch size for a single GPU.
   * `time_col`: Time column, set the column name of the time series dataset's time column based on your data.
   * `feature_cols`: Feature variables indicating variables related to whether the device is abnormal. 
+  * `freq`: Frequency of the time series dataset.
+  * `input_len`: The length of the time series input to the model. The time series will be sliced according to this length, and the model will predict whether there is an anomaly in this segment of the time series for that length. The recommended input length should be considered in the context of the actual scenario. In this tutorial, the input length is 96, which means we hope to predict whether there are anomalies at 96 time points.
+  * `label`: Represents the number indicating whether a time point in the time series is abnormal. Anomalous points are labeled as 1, and normal points are labeled as 0. In this tutorial, the anomaly monitoring dataset uses label for this purpose.
+
+For more introductions to hyperparameters, please refer to [PaddleX Time Series Task Model Configuration File Parameter Instructions](../module_usage/instructions/config_parameters_time_series_en.md). The above parameters can be set by appending command-line arguments. For example, to specify the mode as model training: `-o Global.mode=train`; to specify the first GPU for training: `-o Global.device=gpu:0`; to set the number of training epochs to 10: `-o Train.epochs_iters=10`.
+
+<details>
+   <summary> More Details (Click to Expand)  </summary>
+
+* During the model training process, PaddleX automatically saves the model weight files, with the default directory being output. If you need to specify a different save path, you can configure it through the `-o Global.output` field in the configuration file.
+* PaddleX abstracts away the concepts of dynamic graph weights and static graph weights from you. During model training, both dynamic and static graph weights are produced simultaneously. By default, static graph weights are selected for inference.
+* When training other models, you need to specify the corresponding configuration file. The correspondence between models and configuration files can be found in the [PaddleX Model List (CPU/GPU)](../support_list/models_list_en.md)
+
+After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including the following:
+
+**Explanation of Training Outputs:**
+
+After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including the following:
+
+`train_result.json`: A training result record file that logs whether the training task was completed normally, as well as the output weight metrics, relevant file paths, etc.
+`train.log`: A training log file that records changes in model metrics, loss values, and other information during the training process.
+`config.yaml`: The training configuration file that records the hyperparameter configurations for this training session.
+`best_accuracy.pdparams.tar`, `scaler.pkl`, `.checkpoints`, `.inference*`: Files related to model weights, including network parameters, optimizers, static graph network parameters, etc.
+
+</details>
 
 ### 5.2 Model Evaluation
 After completing model training, you can evaluate the specified model weights file on the validation set to verify the model's accuracy. Using PaddleX for model evaluation requires just one command:

docs/practical_tutorials/ts_classification.md

@@ -49,7 +49,7 @@ tar -xf ./dataset/ts_classify_examples.tar -C ./dataset/
   * 时间频率一致：确保所有数据序列的时间频率一致，如每小时、每日或每周，对于不一致的时间序列，可以通过重采样方法调整到统一的时间频率。
   * 时间序列长度一致：确保每一个group的时间序列的长度一致。
   * 缺失值处理：为了保证数据的质量和完整性，可以基于专家经验或统计方法进行缺失值填充。
-  * 非重复性：保证数据是安装时间顺序按行收集的，同一个时间点不能重复出现。
+  * 非重复性：保证数据是按照时间顺序按行收集的，同一个时间点不能重复出现。
 ### 4.2 数据集校验
 在对数据集校验时，只需一行命令：
 
@@ -123,25 +123,38 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
   * `epochs_iters`：训练轮次数设置；
   * `learning_rate`：训练学习率设置；
   * `batch_size`：训练单卡批大小设置；
-  * `time_col`: 时间列，须结合自己的数据设置时间序列数据集的时间列的列名称;
-  * `target_cols`:结合自己的数据，设置时间序列数据集的目标变量的列名称，可以为多个，多个之间用','分隔。一般目标变量和希望预测的目标越相关，模型精度通常越高。本教程中心跳监控数据集中的时间列名有 61 个特征变量，如：dim_0, dim_1 等;
-  * `freq`：频率，须结合自己的数据设置时间频率，如：1min、5min、1h;
-  * `group_id`：一个群组编号表示的是一个时序样本，相同编号的时序序列组成一个样本。结合自己的数据设置指定群组编号的列名称, 如：group_id。
+  * `time_col`: 时间列，须结合自己的数据设置时间序列数据集的时间列的列名称；
+  * `target_cols`:结合自己的数据，设置时间序列数据集的目标变量的列名称，可以为多个，多个之间用','分隔。一般目标变量和希望预测的目标越相关，模型精度通常越高。本教程中心跳监控数据集中的时间列名有 61 个特征变量，如：dim_0, dim_1 等；
+  * `freq`：频率，须结合自己的数据设置时间频率，如：1min、5min、1h；
+  * `group_id`：一个群组编号表示的是一个时序样本，相同编号的时序序列组成一个样本。结合自己的数据设置指定群组编号的列名称, 如：group_id；
   * `static_cov_cols`：代表时序的类别编号列，同一个样本的标签相同。结合自己的数据设置类别的列名称，如：label。
 更多超参数介绍，请参考 [PaddleX时序任务模型配置文件参数说明](../module_usage/instructions/config_parameters_time_series.md)。
 
 **注：**
 
-* 以上参数可以通过追加令行参数的形式进行设置，如指定模式为模型训练：`-o Global.mode=train`；指定前 1 卡 gpu 训练：`-o Global.device=gpu:0`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。
-* 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段
+* 以上参数可以通过追加令行参数的形式进行设置，如指定模式为模型训练：`-o Global.mode=train`；指定前 1 卡 gpu 训练：`-o Global.device=gpu:0`；设置训练轮次数为 10：`-o Train.epochs_iters=10`；
+* 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段。
+
+<details>
+   <summary> 更多说明（点击展开） </summary>
+
+* 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段进行设置。
+* PaddleX 对您屏蔽了动态图权重和静态图权重的概念。在模型训练的过程中，会同时产出动态图和静态图的权重，在模型推理时，默认选择静态图权重推理。
+* 训练其他模型时，需要的指定相应的配置文件，模型和配置的文件的对应关系，可以查阅[PaddleX模型列表（CPU/GPU）](../support_list/models_list.md)。
+在完成模型训练后，所有产出保存在指定的输出目录（默认为`./output/`）下，通常有以下产出：
+
+
 **训练产出解释:**
 
 在完成模型训练后，所有产出保存在指定的输出目录（默认为`./output/`）下，通常有以下产出：
 
-* train_result.json：训练结果记录文件，记录了训练任务是否正常完成，以及产出的权重指标、相关文件路径等；
-* train.log：训练日志文件，记录了训练过程中的模型指标变化、loss 变化等；
-* config.yaml：训练配置文件，记录了本次训练的超参数的配置；
-* .pdparams、.pkl、model_meta、checkpoint、best_accuracy.pdparams.tar模型权重相关文件，包括网络参数、优化器、归一化、网络参数、数据信息和最佳模型权重压缩包等；
+* `train_result.json`：训练结果记录文件，记录了训练任务是否正常完成，以及产出的权重指标、相关文件路径等；
+* `train.log`：训练日志文件，记录了训练过程中的模型指标变化、loss 变化等；
+* `config.yaml`：训练配置文件，记录了本次训练的超参数的配置；
+* `best_accuracy.pdparams.tar`、`scaler.pkl`、`.checkpoints` 、`.inference*`：模型权重相关文件，包括网络参数、优化器、静态图权重等；
+
+</details>
+
 ### 5.2 模型评估
 在完成模型训练后，可以对指定的模型权重文件在验证集上进行评估，验证模型精度。使用 PaddleX 进行模型评估，只需一行命令：
 
@@ -200,7 +213,7 @@ python main.py -c paddlex/configs/ts_classification/TimesNet_cls.yaml \
 
 * 指定模型的`.yaml` 配置文件路径（此处为`TimesNet_cls.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX时序任务模型配置文件参数说明](../module_usage/instructions/config_parameters_time_series.md)。
 

docs/practical_tutorials/ts_classification_en.md

@@ -36,7 +36,7 @@ PaddleX provides a time series classification model. Refer to the [Model List](.
 ### 4.1 Data Preparation
 To demonstrate the entire time series classification process, we will use the public [Heartbeat Dataset](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ts_classify_examples.tar) for model training and validation. The Heartbeat Dataset is part of the UEA Time Series Classification Archive, addressing the practical task of heartbeat monitoring for medical diagnosis. The dataset comprises multiple time series groups, with each data point consisting of a label variable, group ID, and 61 feature variables. This dataset is commonly used to test and validate the performance of time series classification prediction models.
 
-We have converted the dataset into a standard format, which can be obtained using the following commands. For data format details, refer to the [Time Series Classification Module Development Tutorial](../module_usage/tutorials/ts_modules/time_series_classification_en.md).
+We have converted the dataset into a standard format, which can be obtained using the following commands. For data format details, refer to the [Time Series Classification Module Development Tutorial](../module_usage/tutorials/time_series_modules/time_series_classification_en.md).
 
 Dataset Acquisition Command:
 
@@ -46,7 +46,7 @@ wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ts_classify_example
 tar -xf ./dataset/ts_classify_examples.tar -C ./dataset/
 ```
 
-* **Data Considerations**
+**Data Considerations**
   * Based on collected real data, clarify the classification objectives of the time series data and define corresponding classification labels. For example, in stock price classification, labels might be "Rise" or "Fall." For a time series that is "Rising" over a period, it can be considered a sample (group), where each time point in this period shares a common group_id.
   * Uniform Time Series Length: Ensure that the length of the time series for each group is consistent.
 Missing Value Handling: To guarantee the quality and integrity of the data, missing values can be imputed based on expert experience or statistical methods.
@@ -97,7 +97,7 @@ The above verification results have omitted some data parts. `check_pass` being
 **Note**: Only data that passes the verification can be used for training and evaluation.
 
 ### 4.3 Dataset Format Conversion / Dataset Splitting (Optional)
-If you need to convert the dataset format or re-split the dataset, please refer to Section 4.1.3 in the [Time Series Classification Module Development Tutorial](../module_usage/tutorials/ts_modules/time_series_classification_en.md).
+If you need to convert the dataset format or re-split the dataset, please refer to Section 4.1.3 in the [Time Series Classification Module Development Tutorial](../module_usage/tutorials/time_series_modules/time_series_classification_en.md).
 
 ## 5. Model Training and Evaluation
 
@@ -140,14 +140,25 @@ For more hyperparameter introductions, please refer to [PaddleX Time Series Task
 * The above parameters can be set by appending command-line parameters, e.g., specifying the mode as model training: `-o Global.mode=train`; specifying the first GPU for training: `-o Global.device=gpu:0`; setting the number of training epochs to 10: `-o Train.epochs_iters=10`.
 * During model training, PaddleX automatically saves model weight files, with the default being `output`. To specify a save path, use the `-o Global.output` field in the configuration file.
 
-**Training Output Explanation**:
+<details>
+   <summary> More Details (Click to Expand)  </summary>
 
-After completing model training, all outputs are saved in the specified output directory (default is `./output/`), typically including:
+* During the model training process, PaddleX automatically saves the model weight files, with the default directory being output. If you need to specify a different save path, you can configure it through the `-o Global.output` field in the configuration file.
+* PaddleX abstracts away the concepts of dynamic graph weights and static graph weights from you. During model training, both dynamic and static graph weights are produced simultaneously. By default, static graph weights are selected for inference.
+* When training other models, you need to specify the corresponding configuration file. The correspondence between models and configuration files can be found in the [PaddleX Model List (CPU/GPU)](../support_list/models_list_en.md)
 
-* train_result.json: Training result record file, recording whether the training task completed normally, as well as the output weight metrics, relevant file paths, etc.;
-* train.log: Training log file, recording changes in model metrics, loss, etc. during training;
-* config.yaml: Training configuration file;
-* The model weight-related files such as .pdparams, .pkl, model_meta, checkpoint, and best_accuracy.pdparams.tar contain network parameters, optimizers, normalization configurations, network parameters again (possibly for clarity or differentiation), data information, and compressed packages of the best model weights, among other things.
+After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including the following:
+
+**Explanation of Training Outputs:**
+
+After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including the following:
+
+`train_result.json`: A training result record file that logs whether the training task was completed normally, as well as the output weight metrics, relevant file paths, etc.
+`train.log`: A training log file that records changes in model metrics, loss values, and other information during the training process.
+`config.yaml`: The training configuration file that records the hyperparameter configurations for this training session.
+`best_accuracy.pdparams.tar`, `scaler.pkl`, `.checkpoints`, `.inference*`: Files related to model weights, including network parameters, optimizers, static graph network parameters, etc.
+
+</details>
 
 ### 5.2 Model Evaluation
 After completing model training, you can evaluate the specified model weights file on the validation set to verify the model's accuracy. Using PaddleX for model evaluation requires just one command:

docs/practical_tutorials/ts_forecast.md

@@ -23,7 +23,7 @@ for res in output:
 注：由于时序数据和场景紧密相关，时序任务的在线体验官方内置模型仅是在一个特定场景下的模型方案，并非通用方案，不适用其他场景，因此体验方式不支持使用任意的文件来体验官方模型方案效果。但是，在完成自己场景数据下的模型训练之后，可以选择自己训练的模型方案，并使用对应场景的数据进行在线体验。
 
 ## 3. 选择模型
-PaddleX 提供了5个端到端的时序预测模型
+PaddleX 提供了5个端到端的时序预测模型，具体可参考 [模型列表](../support_list/models_list.md)，其中模型的benchmark如下：
 
 |模型名称|mse|mae|模型存储大小（M)|介绍|
 |-|-|-|-|-|
@@ -54,7 +54,7 @@ tar -xf ./dataset/electricity.tar -C ./dataset/
   * 为了训练出高精度的模型，贴近实际场景的真实数据尤为关键，因此通常需要一批真实数据加入训练集。
   * 标注时序预测任务数据时，基于收集的真实数据，将所有数据按照时间的顺序排列即可。训练时将数据自动分为多个时间片段，历史的时间序列数据和未来的序列分别表示训练模型输入数据和其对应的预测目标，构成了一组训练样本。
   * 缺失值处理：为了保证数据的质量和完整性，可以基于专家经验或统计方法进行缺失值填充。
-  * 非重复性：保证数据是安装时间顺序按行收集的，同一个时间点不能重复出现。
+  * 非重复性：保证数据是按照时间顺序按行收集的，同一个时间点不能重复出现。
 ### 4.2 数据集校验
 在对数据集校验时，只需一行命令：
 
@@ -212,18 +212,26 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
   * `epochs_iters`：训练轮次数设置；
   * `learning_rate`：训练学习率设置；
   * `batch_size`：训练单卡批大小设置；
-  * `time_col`: 时间列，须结合自己的数据设置时间序列数据集的时间列的列名称;
-  * `target_cols`:目标变量列，须结合自己的数据设置时间序列数据集的目标变量的列名称，可以为多个，多个之间用','分隔;
-  * `freq`：频率，须结合自己的数据设置时间频率，如：1min、5min、1h;
-  * `input_len`: 输入给模型的历史时间序列长度；输入长度建议结合实际场景及预测长度综合考虑，一般来说设置的越大，能够参考的历史信息越多，模型精度通常越高。
-  * `predict_len`:希望模型预测未来序列的长度；预测长度建议结合实际场景综合考虑，一般来说设置的越大，希望预测的未来序列越长，模型精度通常越低。
+  * `time_col`: 时间列，须结合自己的数据设置时间序列数据集的时间列的列名称；
+  * `target_cols`:目标变量列，须结合自己的数据设置时间序列数据集的目标变量的列名称，可以为多个，多个之间用','分隔；
+  * `freq`：频率，须结合自己的数据设置时间频率，如：1min、5min、1h；
+  * `input_len`: 输入给模型的历史时间序列长度；输入长度建议结合实际场景及预测长度综合考虑，一般来说设置的越大，能够参考的历史信息越多，模型精度通常越高；
+  * `predict_len`:希望模型预测未来序列的长度；预测长度建议结合实际场景综合考虑，一般来说设置的越大，希望预测的未来序列越长，模型精度通常越低；
   * `patience`：early stop机制参数，指在停止训练之前，容忍模型在验证集上的性能多少次连续没有改进；耐心值越大，一般训练时间越长。
 更多超参数介绍，请参考 [PaddleX时序任务模型配置文件参数说明](../module_usage/instructions/config_parameters_time_series.md)。
 
-**注：**
+* 以上参数可以通过追加令行参数的形式进行设置，如指定模式为模型训练：`-o Global.mode=train`；指定前 1 卡 gpu 训练：`-o Global.device=gpu:0`；设置训练轮次数为 10：`-o Train.epochs_iters=10`；
+* 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段。
+
+<details>
+   <summary> 更多说明（点击展开） </summary>
+
+* 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段进行设置。
+* PaddleX 对您屏蔽了动态图权重和静态图权重的概念。在模型训练的过程中，会同时产出动态图和静态图的权重，在模型推理时，默认选择静态图权重推理。
+* 训练其他模型时，需要的指定相应的配置文件，模型和配置的文件的对应关系，可以查阅[PaddleX模型列表（CPU/GPU）](../support_list/models_list.md)。
+在完成模型训练后，所有产出保存在指定的输出目录（默认为`./output/`）下，通常有以下产出：
+
 
-* 以上参数可以通过追加令行参数的形式进行设置，如指定模式为模型训练：`-o Global.mode=train`；指定前 1 卡 gpu 训练：`-o Global.device=gpu:0`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。
-* 模型训练过程中，PaddleX 会自动保存模型权重文件，默认为`output`，如需指定保存路径，可通过配置文件中 `-o Global.output` 字段
 **训练产出解释:**
 
 在完成模型训练后，所有产出保存在指定的输出目录（默认为`./output/`）下，通常有以下产出：
@@ -231,7 +239,10 @@ PaddleX 中每个模型都提供了模型开发的配置文件，用于设置相
 * train_result.json：训练结果记录文件，记录了训练任务是否正常完成，以及产出的权重指标、相关文件路径等；
 * train.log：训练日志文件，记录了训练过程中的模型指标变化、loss 变化等；
 * config.yaml：训练配置文件，记录了本次训练的超参数的配置；
-* `best_accuracy.pdparams.tar`、`scaler.pkl`、`.checkpoints` 、`.inference`：模型权重相关文件，包括网络参数、优化器、EMA、静态图网络参数、静态图网络结构等。
+* `best_accuracy.pdparams.tar`、`scaler.pkl`、`.checkpoints` 、`.inference`：模型权重相关文件，包括网络参数、优化器、静态图权重等。
+
+</details>
+
 ### 5.2 模型评估
 在完成模型训练后，可以对指定的模型权重文件在验证集上进行评估，验证模型精度。使用 PaddleX 进行模型评估，只需一行命令：
 
@@ -292,7 +303,7 @@ python main.py -c paddlex/configs/ts_forecast/DLinear.yaml \
 
 * 指定模型的`.yaml` 配置文件路径（此处为`DLinear.yaml`）
 * 指定模式为模型推理预测：`-o Global.mode=predict`
-* 指定模型权重路径：`-o Predict.model_dir=``"./output/inference"`
+* 指定模型权重路径：`-o Predict.model_dir="./output/inference"`
 * 指定输入数据路径：`-o Predict.input="..."`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Predict`下的字段来进行设置，详细请参考[PaddleX时序任务模型配置文件参数说明](../module_usage/instructions/config_parameters_time_series.md)。
 
@@ -308,7 +319,7 @@ for res in output:
     res.print() # 打印预测的结构化输出
     res.save_to_csv("./output/") # 保存csv格式结果
 ```
-更多参数请参考时序异常检测产线使用教程
+更多参数请参考[时序预测产线使用教程](../pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md)。
 
 2. 此外，PaddleX 时序预测产线也提供了服务化部署方式，详细说明如下：
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/service_deploy.md)。

docs/practical_tutorials/ts_forecast_en.md

@@ -24,7 +24,7 @@ for res in output:
 Note: Due to the tight correlation between time series data and scenarios, the official online experience models for time series tasks are tailored to specific scenarios and are not universal. Therefore, the online experience does not support using arbitrary files to test the official model solutions. However, after training your own model with scenario-specific data, you can select your trained model solution and use corresponding scenario data for online experience.
 
 ## 3. Choose a Model
-PaddleX provides five end-to-end time series forecasting models:
+PaddleX provides five end-to-end time series forecasting models. For details, refer to the [Model List](../support_list/models_list_en.md). The benchmarks of these models are as follows:
 
 | Model Name | MSE | MAE | Model Size (M) | Description |
 |-|-|-|-|-|
@@ -42,7 +42,7 @@ Based on your actual usage scenario, select an appropriate model for training. A
 ### 4.1 Data Preparation
 To demonstrate the entire time series forecasting process, we will use the [Electricity](https://archive.ics.uci.edu/dataset/321/electricityloaddiagrams20112014) dataset for model training and validation. This dataset collects electricity consumption at a certain node from 2012 to 2014, with data collected every hour. Each data point consists of the current timestamp and corresponding electricity consumption. This dataset is commonly used to test and validate the performance of time series forecasting models.
 
-In this tutorial, we will use this dataset to predict the electricity consumption for the next 96 hours. We have already converted this dataset into a standard data format, and you can obtain a sample dataset by running the following command. For an introduction to the data format, you can refer to the [Time Series Prediction Module Development Tutorial](../module_usage/tutorials/ts_modules/time_series_forecast_en.md).
+In this tutorial, we will use this dataset to predict the electricity consumption for the next 96 hours. We have already converted this dataset into a standard data format, and you can obtain a sample dataset by running the following command. For an introduction to the data format, you can refer to the [Time Series Prediction Module Development Tutorial](../module_usage/tutorials/time_series_modules/time_series_forecast_en.md).
 
 
 You can use the following commands to download the demo dataset to a specified folder:
@@ -53,7 +53,8 @@ wget https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/doc_images/pr
 tar -xf ./dataset/electricity.tar -C ./dataset/
 ```
 
-* **Data Considerations**
+**Data Considerations**
+
  * When annotating data for time series forecasting tasks, based on the collected real data, all data is arranged in chronological order. During training, the data is automatically divided into multiple time segments, where the historical time series data and the future sequences respectively represent the input data for training the model and its corresponding prediction targets, forming a set of training samples.
  * Handling Missing Values: To ensure data quality and integrity, missing values can be imputed based on expert knowledge or statistical methods.
  * Non-Repetitiveness: Ensure that data is collected in chronological order by row, with no duplication of timestamps.
@@ -189,7 +190,7 @@ The above verification results have omitted some data parts. `check_pass` being
 **Note**: Only data that passes the verification can be used for training and evaluation.
 
 ### 4.3 Dataset Format Conversion/Dataset Splitting (Optional)
-If you need to convert the dataset format or re-split the dataset, you can modify the configuration file or append hyperparameters for settings. Refer to Section 4.1.3 in the [Time Series Prediction Module Development Tutorial](../module_usage/tutorials/ts_modules/time_series_forecast_en.md).
+If you need to convert the dataset format or re-split the dataset, you can modify the configuration file or append hyperparameters for settings. Refer to Section 4.1.3 in the [Time Series Prediction Module Development Tutorial](../module_usage/tutorials/time_series_modules/time_series_forecast_en.md).
 
 ## 5. Model Training and Evaluation
 
@@ -234,6 +235,29 @@ For more hyperparameter introductions, refer to [PaddleX Time Series Task Model
 * The above parameters can be set by appending command-line parameters, e.g., specifying the mode as model training: `-o Global.mode=train`; specifying the first GPU for training: `-o Global.device=gpu:0`; setting the number of training epochs to 10: `-o Train.epochs_iters=10`.
 * During model training, PaddleX automatically saves the model weight files, with the default being `output`. If you need to specify a save path, you can use the `-o Global.output` field in the configuration file.
 
+
+
+<details>
+   <summary> More Details (Click to Expand)  </summary>
+
+* During the model training process, PaddleX automatically saves the model weight files, with the default directory being output. If you need to specify a different save path, you can configure it through the `-o Global.output` field in the configuration file.
+* PaddleX abstracts away the concepts of dynamic graph weights and static graph weights from you. During model training, both dynamic and static graph weights are produced simultaneously. By default, static graph weights are selected for inference.
+* When training other models, you need to specify the corresponding configuration file. The correspondence between models and configuration files can be found in the [PaddleX Model List (CPU/GPU)](../support_list/models_list_en.md)
+
+After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including the following:
+
+**Explanation of Training Outputs:**
+
+After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including the following:
+
+`train_result.json`: A training result record file that logs whether the training task was completed normally, as well as the output weight metrics, relevant file paths, etc.
+`train.log`: A training log file that records changes in model metrics, loss values, and other information during the training process.
+`config.yaml`: The training configuration file that records the hyperparameter configurations for this training session.
+`best_accuracy.pdparams.tar`, `scaler.pkl`, `.checkpoints`, `.inference*`: Files related to model weights, including network parameters, optimizers, static graph network parameters, etc.
+
+</details>
+
+
 ### 5.2 Model Evaluation
 
 After completing model training, you can evaluate the specified model weights file on the validation set to verify the model's accuracy. Using PaddleX for model evaluation requires just one command: