Doc review2 (#2235)

* doc review modification

* repair error yaml modify

docs/data_annotations/cv_modules/instance_segmentation.md

@@ -38,7 +38,7 @@ pip install labelme
 
 * 在 `fruit` 文件夹中创建待标注数据集的类别标签文件 `label.txt`，并在 `label.txt` 中按行写入待标注数据集的类别。以水果实例分割数据集的 `label.txt` 为例，如下图所示：
 
-![alt text](/tmp//images/data_prepare/instance_segmentation/06.png)
+![alt text](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/data_prepare/instance_segmentation/06.png)
 
 #### 2.3.2 启动 Labelme
 终端进入到带标注数据集根目录，并启动 `labelme` 标注工具。
@@ -102,4 +102,4 @@ dataset_dir                  # 数据集根目录，目录名称可以改变
 
 * 实例分割数据要求采用 `COCO` 数据格式标注出数据集中每张图像各个目标区域的像素边界和类别，采用 `[x1,y1,x2,y2,...,xn,yn]` 表示物体的多边形边界（segmentation）。其中，`(xn,yn)` 表示多边形各个角点坐标。标注信息存放到 `annotations` 目录下的 `json` 文件中，训练集 `instance_train.json` 和验证集 `instance_val.json` 分开存放。
 * 如果你有一批未标注数据，我们推荐使用 `LabelMe` 进行数据标注。对于使用 `LabelMe` 标注的数据集，PaddleX产线支持进行数据格式转换。
-* 为确保格式转换顺利完成，请严格遵循示例数据集的文件命名和组织方式： [LabelMe 示例数据集](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/instance_seg_labelme_examples.tar)。
+* 为确保格式转换顺利完成，请严格遵循示例数据集的文件命名和组织方式： [LabelMe 示例数据集](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/instance_seg_labelme_examples.tar)。

docs/module_usage/instructions/config_parameters_common.md

@@ -3,51 +3,50 @@
 # PaddleX通用模型配置文件参数说明
 
 # Global
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|model|str|指定模型名称|-|必需|
-|mode|str|指定模式（check_dataset/train/evaluate/export/predict）|-|必需|
-|dataset_dir|str|数据集路径|-|必需|
-|device|str|指定使用的设备|-|必需|
-|output|str|输出路径|"output"|可选|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|model|str|指定模型名称|yaml文件中指定的模型名称|
+|mode|str|指定模式（check_dataset/train/evaluate/export/predict）|check_dataset|
+|dataset_dir|str|数据集路径|yaml文件中指定的数据集路径|
+|device|str|指定使用的设备|yaml文件中指定的设备id|
+|output|str|输出路径|"output"|
 # CheckDataset
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|convert.enable|bool|是否进行数据集格式转换|False|可选|
-|convert.src_dataset_type|str|需要转换的源数据集格式|null|可选|
-|split.enable|bool|是否重新划分数据集|False|可选|
-|split.train_percent|int|设置训练集的百分比，类型为0-100之间的任意整数，需要保证和val_percent值加和为100；|null|可选|
-|split.val_percent|int|设置验证集的百分比，类型为0-100之间的任意整数，需要保证和train_percent值加和为100；|null|可选|
-|split.gallery_percent|int|设置验证集中被查询样本的百分比，类型为0-100之间的任意整数，需要保证和train_percent、query_percent，值加和为100；该参数只有图像特征模块才会使用|null|可选|
-|split.query_percent|int|设置验证集中查询样本的百分比，类型为0-100之间的任意整数，需要保证和train_percent、gallery_percent，值加和为100；该参数只有图像特征模块才会使用|null|可选|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|convert.enable|bool|是否进行数据集格式转换；图像分类、行人属性识别、车辆属性识别、文档方向分类、主体检测、行人检测、车辆检测、人脸检测、异常检测、文本检测、印章文本检测、文本识别、表格识别、图像矫正、版面区域检测暂不支持数据格式转换；图像多标签分类支持COCO格式的数据转换；图像特征、语义分割、实例分割支持LabelMe格式的数据转换；目标检测和小目标检测支持VOC、LabelMe格式的数据转换；公式识别支持PKL格式的数据转换；时序预测、时序异常检测、时序分类支持xlsx和xls格式的数据转换|False|
+|convert.src_dataset_type|str|需要转换的源数据集格式|null|
+|split.enable|bool|是否重新划分数据集|False|
+|split.train_percent|int|设置训练集的百分比，类型为0-100之间的任意整数，需要保证和val_percent值加和为100；|null|
+|split.val_percent|int|设置验证集的百分比，类型为0-100之间的任意整数，需要保证和train_percent值加和为100；|null|
+|split.gallery_percent|int|设置验证集中被查询样本的百分比，类型为0-100之间的任意整数，需要保证和train_percent、query_percent，值加和为100；该参数只有图像特征模块才会使用|null|
+|split.query_percent|int|设置验证集中查询样本的百分比，类型为0-100之间的任意整数，需要保证和train_percent、gallery_percent，值加和为100；该参数只有图像特征模块才会使用|null|
 
 # Train
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|num_classes|int|数据集中的类别数|-|必需|
-|epochs_iters|int|模型对训练数据的重复学习次数|-|必需|
-|batch_size|int|训练批大小|-|必需|
-|learning_rate|float|初始学习率|-|必需|
-|pretrain_weight_path|str|预训练权重路径|null|可选|
-|warmup_steps|int|预热步数|-|必需|
-|resume_path|str|模型中断后的恢复路径|null|可选|
-|log_interval|int|训练日志打印间隔|-|必需|
-|eval_interval|int|模型评估间隔|-|必需|
-|save_interval|int|模型保存间隔|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|num_classes|int|数据集中的类别数；如果您需要在私有数据集进行训练，需要对该参数进行设置；图像矫正、文本检测、印章文本检测、文本识别、公式识别、表格识别、时序预测、时序异常检测、时序分类不支持该参数|yaml文件中指定类别数|
+|epochs_iters|int|模型对训练数据的重复学习次数|yaml文件中指定的重复学习次数|
+|batch_size|int|训练批大小|yaml文件中指定的训练批大小|
+|learning_rate|float|初始学习率|yaml文件中指定的初始学习率|
+|pretrain_weight_path|str|预训练权重路径|null|
+|warmup_steps|int|预热步数|yaml文件中指定的预热步数|
+|resume_path|str|模型中断后的恢复路径|null|
+|log_interval|int|训练日志打印间隔|yaml文件中指定的训练日志打印间隔|
+|eval_interval|int|模型评估间隔|yaml文件中指定的模型评估间隔|
+|save_interval|int|模型保存间隔；异常检测、语义分割、图像矫正、时序预测、时序异常检测、时序分类暂不支持该参数|yaml文件中指定的模型保存间隔|
 
 # Evaluate
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|weight_path|str|评估模型路径|-|必需|
-|log_interval|int|评估日志打印间隔|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|weight_path|str|评估模型路径|默认训练产出的本地路径，当指定为None时，表示使用官方权重|
+|log_interval|int|评估日志打印间隔|yaml文件中指定的评估日志打印间隔|
 # Export
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|weight_path|str|导出模型的动态图权重路径|各模型官方动态图权重URL|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|weight_path|str|导出模型的动态图权重路径|默认训练产出的本地路径，当指定为None时，表示使用官方权重|
 # Predict
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|batch_size|int|预测批大小|-|必需|
-|model_dir|str|预测模型路径|PaddleX模型官方权重|可选|
-|input|str|预测输入路径|-|必需|
-
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|batch_size|int|预测批大小|yaml文件中指定的预测批大小|
+|model_dir|str|预测模型路径|默认训练产出的本地推理模型路径，当指定为None时，表示使用官方权重|
+|input|str|预测输入路径|yaml文件中指定的预测输入路径|

docs/module_usage/instructions/config_parameters_common_en.md

@@ -1,56 +1,55 @@
 [简体中文](config_parameters_common.md) | English
 
-
-# PaddleX General Model Configuration File Parameter Explanation
+# PaddleX Common Model Configuration File Parameter Explanation
 
 # Global
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |
-|-|-|-|-|-|
-| model | str | Specifies the model name | - | Required |
-| mode | str | Specifies the mode (check_dataset/train/evaluate/export/predict) | - | Required |
-| dataset_dir | str | Path to the dataset | - | Required |
-| device | str | Specifies the device to use | - | Required |
-| output | str | Output path | "output" | Optional |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| model | str | Specifies the model name | Model name specified in the YAML file |
+| mode | str | Specifies the mode (check_dataset/train/evaluate/export/predict) | check_dataset |
+| dataset_dir | str | Path to the dataset | Dataset path specified in the YAML file |
+| device | str | Specifies the device to use | Device ID specified in the YAML file |
+| output | str | Output path | "output" |
 
 # CheckDataset
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |
-|-|-|-|-|-|
-| convert.enable | bool | Whether to enable dataset format conversion | False | Optional |
-| convert.src_dataset_type | str | Source dataset format to convert | null | Optional |
-| split.enable | bool | Whether to re-split the dataset | False | Optional |
-| split.train_percent | int | Sets the percentage of the training set, an integer between 0-100, which needs to sum up to 100 with val_percent | null | Optional |
-| split.val_percent | int | Sets the percentage of the validation set, an integer between 0-100, which needs to sum up to 100 with train_percent | null | Optional |
-| split.gallery_percent | int | Sets the percentage of gallery samples in the validation set, an integer between 0-100, which needs to sum up to 100 with train_percent and query_percent; this parameter is only used in the image feature module | null | Optional |
-| split.query_percent | int | Sets the percentage of query samples in the validation set, an integer between 0-100, which needs to sum up to 100 with train_percent and gallery_percent; this parameter is only used in the image feature module | null | Optional |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| convert.enable | bool | Whether to convert the dataset format; Image classification, pedestrian attribute recognition, vehicle attribute recognition, document orientation classification, object detection, pedestrian detection, vehicle detection, face detection, anomaly detection, text detection, seal text detection, text recognition, table recognition, image rectification, and layout area detection do not support data format conversion; Image multi-label classification supports COCO format conversion; Image feature, semantic segmentation, and instance segmentation support LabelMe format conversion; Object detection and small object detection support VOC and LabelMe format conversion; Formula recognition supports PKL format conversion; Time series prediction, time series anomaly detection, and time series classification support xlsx and xls format conversion | False |
+| convert.src_dataset_type | str | The source dataset format to be converted | null |
+| split.enable | bool | Whether to re-split the dataset | False |
+| split.train_percent | int | Sets the percentage of the training set, an integer between 0-100, ensuring the sum with val_percent is 100; | null |
+| split.val_percent | int | Sets the percentage of the validation set, an integer between 0-100, ensuring the sum with train_percent is 100; | null |
+| split.gallery_percent | int | Sets the percentage of gallery samples in the validation set, an integer between 0-100, ensuring the sum with train_percent and query_percent is 100; This parameter is only used in the image feature module | null |
+| split.query_percent | int | Sets the percentage of query samples in the validation set, an integer between 0-100, ensuring the sum with train_percent and gallery_percent is 100; This parameter is only used in the image feature module | null |
 
 # Train
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |
-|-|-|-|-|-|
-| num_classes | int | Number of classes in the dataset | - | Required |
-| epochs_iters | int | Number of times the model learns from the training data | - | Required |
-| batch_size | int | Training batch size | - | Required |
-| learning_rate | float | Initial learning rate | - | Required |
-| pretrain_weight_path | str | Pre-trained weight path | null | Optional |
-| warmup_steps | int | Warmup steps | - | Required |
-| resume_path | str | Path to resume the model after interruption | null | Optional |
-| log_interval | int | Interval for printing training logs | - | Required |
-| eval_interval | int | Interval for model evaluation | - | Required |
-| save_interval | int | Interval for saving the model | - | Required |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| num_classes | int | Number of classes in the dataset; If you need to train on a private dataset, you need to set this parameter; Image rectification, text detection, seal text detection, text recognition, formula recognition, table recognition, time series prediction, time series anomaly detection, and time series classification do not support this parameter | Number of classes specified in the YAML file |
+| epochs_iters | int | Number of times the model repeats learning the training data | Number of iterations specified in the YAML file |
+| batch_size | int | Training batch size | Training batch size specified in the YAML file |
+| learning_rate | float | Initial learning rate | Initial learning rate specified in the YAML file |
+| pretrain_weight_path | str | Pre-trained weight path | null |
+| warmup_steps | int | Warm-up steps | Warm-up steps specified in the YAML file |
+| resume_path | str | Model resume path after interruption | null |
+| log_interval | int | Training log printing interval | Training log printing interval specified in the YAML file |
+| eval_interval | int | Model evaluation interval | Model evaluation interval specified in the YAML file |
+| save_interval | int | Model saving interval; not supported for anomaly detection, semantic segmentation, image rectification, time series forecasting, time series anomaly detection, and time series classification  | Model saving interval specified in the YAML file |
 
 # Evaluate
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |
-|-|-|-|-|-|
-| weight_path | str | Path to the model for evaluation | - | Required |
-| log_interval | int | Interval for printing evaluation logs | - | Required |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| weight_path | str | Evaluation model path | Default local path from training output, when specified as None, indicates using official weights |
+| log_interval | int | Evaluation log printing interval | Evaluation log printing interval specified in the YAML file |
 
 # Export
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |
-|-|-|-|-|-|
-| weight_path | str | Path to the dynamic graph weights of the model to export | Official dynamic graph weights URL for each model | Required |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| weight_path | str | Dynamic graph weight path for exporting the model | Default local path from training output, when specified as None, indicates using official weights |
 
 # Predict
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |
-|-|-|-|-|-|
-| batch_size | int | Prediction batch size | - | Required |
-| model_dir | str | Path to the prediction model | Official PaddleX model weights | Optional |
-| input | str | Path to the prediction input | - | Required |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| batch_size | int | Prediction batch size | The prediction batch size specified in the YAML file |
+| model_dir | str | Path to the prediction model | The default local inference model path produced by training. When specified as None, it indicates the use of official weights |
+| input | str | Path to the prediction input | The prediction input path specified in the YAML file |

docs/module_usage/instructions/config_parameters_time_series.md

@@ -3,62 +3,64 @@
 # PaddleX时序任务模型配置文件参数说明
 
 # Global
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|model|str|指定模型名称|-|必需|
-|mode|str|指定模式（check_dataset/train/evaluate/export/predict）|-|必需|
-|dataset_dir|str|数据集路径|-|必需|
-|device|str|指定使用的设备|-|必需|
-|output|str|输出路径|"output"|可选|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|model|str|指定模型名称|yaml文件中指定的模型名称|
+|mode|str|指定模式（check_dataset/train/evaluate/export/predict）|check_dataset|
+|dataset_dir|str|数据集路径|yaml文件中指定的数据集路径|
+|device|str|指定使用的设备|yaml文件中指定的设备id|
+|output|str|输出路径|"output"|
+
 # CheckDataset
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|convert.enable|bool|是否进行数据集格式转换|False|可选|
-|convert.src_dataset_type|str|需要转换的源数据集格式|null|不可选|
-|split.enable|bool|是否重新划分数据集|False|可选|
-|split.train_percent|int|设置训练集的百分比，类型为0-100之间的任意整数，需要保证和val_percent值加和为100；|-|可选|
-|split.val_percent|int|设置验证集的百分比，类型为0-100之间的任意整数，需要保证和train_percent值加和为100；|-|可选|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|convert.enable|bool|是否进行数据集格式转换；时序预测、时序异常检测、时序分类支持xlsx和xls格式的数据转换|False|
+|convert.src_dataset_type|str|需要转换的源数据集格式|null|
+|split.enable|bool|是否重新划分数据集|False|
+|split.train_percent|int|设置训练集的百分比，类型为0-100之间的任意整数，需要保证和val_percent值加和为100；|null|
+|split.val_percent|int|设置验证集的百分比，类型为0-100之间的任意整数，需要保证和train_percent值加和为100；|null|
+
 # Train
 ### 时序任务公共参数
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|epochs_iters|int|模型对训练数据的重复学习次数|-|必需|
-|batch_size|int|批大小|-|必需|
-|learning_rate|float|初始学习率|-|必需|
-|time_col|str|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。|-|必需|
-|freq|str or int|频率，须结合自己的数据设置时间频率，如：1min、5min、1h。|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|epochs_iters|int|模型对训练数据的重复学习次数|yaml文件中指定的重复学习次数|
+|batch_size|int|批大小|yaml文件中指定的批大小|
+|learning_rate|float|初始学习率|yaml文件中指定的初始学习率|
+|time_col|str|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。|yaml文件中指定的时间列|
+|freq|str or int|频率，须结合自己的数据设置时间频率，如：1min、5min、1h。|yaml文件中指定的频率|
 ### 时序预测参数
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|target_cols|str|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|-|必需|
-|input_len|int|对于时序预测任务，该参数表示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。|-|必需|
-|predict_len|int|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。|-|必需|
-|patience|int|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。|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|target_cols|str|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|OT|
+|input_len|int|对于时序预测任务，该参数表示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。|96|
+|predict_len|int|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。|96|
+|patience|int|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。|10|
 ### 时序异常检测
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|input_len|int|对于时序异常检测任务，该参数表示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。如：输入长度为 96，则表示希望预测 96 个时间点是否有异常。|-|必需|
-|feature_cols|str|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。|-|必需|
-|label_col|str|代表时序时间点是否异常的编号，异常点为 1，正常点为 0。|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|input_len|int|对于时序异常检测任务，该参数表示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。如：输入长度为 96，则表示希望预测 96 个时间点是否有异常。|96|
+|feature_cols|str|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。|feature_0,feature_1|
+|label_col|str|代表时序时间点是否异常的编号，异常点为 1，正常点为 0。|label|
 ### 时序分类
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|num_classes|int|数据集中的类别数|-|必需|
-|target_cols|str|用于判别类别的特征变量列，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|-|必需|
-|freq|str or int|频率，须结合自己的数据设置时间频率，如：1min、5min、1h。|-|必需|
-|group_id|str|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。|-|必需|
-|static_cov_cols|str|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。|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|target_cols|str|用于判别类别的特征变量列，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|dim_0,dim_1,dim_2|
+|freq|str or int|频率，须结合自己的数据设置时间频率，如：1min、5min、1h。|1|
+|group_id|str|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。| group_id|
+|static_cov_cols|str|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。|label|
 # Evaluate
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|weight_path|str|评估模型路径|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|weight_path|str|评估模型路径|默认训练产出的本地路径，当指定为None时，表示使用官方权重|
+
 # Export
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|weight_path|str|导出模型的动态图权重路径|各模型官方动态图权重URL|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|weight_path|str|导出模型的动态图权重路径|默认训练产出的本地路径，当指定为None时，表示使用官方权重|
 # Predict
-|参数名|数据类型|描述|默认值|必需/可选|
-|-|-|-|-|-|
-|model_dir|str|预测模型路径|模型官方权重|可选|
-|input|str|预测输入路径|-|必需|
-|batch_size|int|预测批大小|-|必需|
+|参数名|数据类型|描述|默认值|
+|-|-|-|-|
+|batch_size|int|预测批大小|yaml文件中指定的预测批大小|
+|model_dir|str|预测模型路径|默认训练产出的本地推理模型路径，当指定为None时，表示使用官方权重|
+|input|str|预测输入路径|yaml文件中指定的预测输入路径|

docs/module_usage/instructions/config_parameters_time_series_en.md

@@ -4,89 +4,69 @@
 
 # Global
 
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| model | str | Specifies the model name | - | Required |  
-| mode | str | Specifies the mode (check_dataset/train/evaluate/export/predict) | - | Required |  
-| dataset_dir | str | Path to the dataset | - | Required |  
-| device | str | Specifies the device to use | - | Required |  
-| output | str | Output directory path | "output" | Optional |
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| model | str | Specifies the model name | Model name specified in the YAML file |
+| mode | str | Specifies the mode (check_dataset/train/evaluate/export/predict) | check_dataset |
+| dataset_dir | str | Path to the dataset | Dataset path specified in the YAML file |
+| device | str | Specifies the device to use | Device ID specified in the YAML file |
+| output | str | Output path | "output" |
 
 # CheckDataset
 
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| convert.enable | bool | Whether to enable dataset format conversion | False | Optional |  
-| convert.src_dataset_type | str | The source dataset format to convert from | null | Required |  
-| split.enable | bool | Whether to re-split the dataset | False | Optional |  
-| split.train_percent | int | Sets the percentage of the training set, an integer between 0-100. It should sum up to 100 with `val_percent`. | - | Optional |  
-| split.val_percent | int | Sets the percentage of the validation set, an integer between 0-100. It should sum up to 100 with `train_percent`. | - | Optional |  
-  
-# Train
-
-### Common parameters for time series tasks
-
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| epochs_iters | int | Number of times the model learns from the training data | - | Required |  
-| batch_size | int | Batch size for training | - | Required |  
-| learning_rate | float | Initial learning rate | - | Required |  
-| time_col | str | Time column, must be set to the column name that represents the time series data's timestamp in your dataset. | - | Required |  
-| freq | str or int | Frequency, must be set to the time frequency of your data, such as '1min', '5min', '1h'. | - | Required |  
-  
-**Note**: The default values for these parameters are not specified ("-"), indicating that they must be explicitly provided by the user based on their specific dataset and requirements.
-
-### Time series forecasting parameters
-
-
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| target_cols | str | Target variable column(s), must be set to the column name(s) that represent the target variable(s) in your time series dataset. Multiple columns can be specified by separating them with commas. | - | Required |  
-| input_len | int | For time series prediction tasks, this parameter represents the length of historical time series data input to the model. The input length should be considered in conjunction with the prediction length and the specific scenario. Generally, a larger input length allows the model to reference more historical information, which may lead to higher accuracy. | - | Required |  
-| predict_len | int | The desired length of the future sequence that the model should predict. The prediction length should be considered in conjunction with the specific scenario. Generally, a larger prediction length means predicting a longer future sequence, which may lead to lower model accuracy. | - | Required |  
-| patience | int | A parameter for the early stopping mechanism, indicating how many times the model's performance on the validation set can be consecutively unchanged before stopping training. A larger patience value generally results in longer training time. | - | Required |  
-  
-**Note**: The default values for these parameters are not specified ("-"), indicating that they must be explicitly provided by the user based on their specific dataset and requirements.
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| convert.enable | bool | Whether to convert the dataset format; time series prediction, anomaly detection, and classification support data conversion from xlsx and xls formats | False |
+| convert.src_dataset_type | str | The source dataset format to be converted | null |
+| split.enable | bool | Whether to re-split the dataset | False |
+| split.train_percent | int | Sets the percentage of the training set, an integer between 0-100, ensuring the sum with val_percent is 100; | null |
+| split.val_percent | int | Sets the percentage of the validation set, an integer between 0-100, ensuring the sum with train_percent is 100; | null |
 
-### Time series anomaly detection parameters
 
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| input_len | int | For time series anomaly detection tasks, this parameter represents 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 are anomalies within this segment. The input length should be considered based on the specific scenario. For example, an input length of 96 indicates the desire to predict whether there are anomalies at 96 time points. | - | Required |  
-| feature_cols | str | Feature columns represent variables that can be used to determine whether a device is anomalous. For instance, whether a device is anomalous may be related to the amount of heat it generates during operation. Based on your data, set the column names of the feature variables. Multiple columns can be specified by separating them with commas. | - | Required |  
-| label_col | str | Represents the label indicating whether a time series point is anomalous. Anomalous points are labeled as 1, and normal points are labeled as 0. | - | Required |  
-  
-**Note**: The default values for these parameters are not specified ("-"), indicating that they must be explicitly provided by the user based on their specific dataset and requirements. 
-
-### Time series classification parameters
-
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| num_classes | int | The number of classes in the dataset. | - | Required |  
-| target_cols | str | The column(s) of the feature variable used to determine the class, which must be set according to your dataset in the time series dataset. Multiple columns can be specified by separating them with commas. | - | Required |  
-| freq | str or int | The frequency of the time series, which must be set according to your data. Examples include '1min', '5min', '1h'. | - | Required |  
-| group_id | str | A group ID represents a time series sample. Time series sequences with the same ID constitute a sample. Set the column name for the specified group ID according to your data, e.g., 'group_id'. | - | Required |  
-| static_cov_cols | str | Represents the class ID column for the time series. Samples within the same class share the same label. Set the column name for the class according to your data, e.g., 'label'. | - | Required |  
-  
-**Note**: The default values for these parameters are not specified ("-"), indicating that they must be explicitly provided by the user based on their specific dataset and requirements. 
+# Train
+### Common Parameters for Time Series Tasks
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| epochs_iters | int | The number of times the model repeats learning the training data | Number of iterations specified in the YAML file |
+| batch_size | int | Batch size | Batch size specified in the YAML file |
+| learning_rate | float | Initial learning rate | Initial learning rate specified in the YAML file |
+| time_col | str | Time column, set the column name of the time series dataset's time column based on your data. | Time column specified in the YAML file |
+| freq | str or int | Frequency, set the time frequency based on your data, e.g., 1min, 5min, 1h. | Frequency specified in the YAML file |
+### Time Series Forecasting Parameters
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| target_cols | str | Target variable column(s), set the column name(s) of the target variable(s) in the time series dataset, can be multiple, separated by commas | OT |
+| input_len | int | For time series forecasting tasks, this parameter represents the length of historical time series input to the model; the input length should be considered in conjunction with the prediction length, generally, the larger the setting, the more historical information can be referenced, and the higher the model accuracy. | 96 |
+| predict_len | int | The length of the future sequence that you want the model to predict; the prediction length should be considered in conjunction with the actual scenario, generally, the larger the setting, the longer the future sequence you want to predict, and the lower the model accuracy. | 96 |
+| patience | int | Early stopping mechanism parameter, indicating how many times the model's performance on the validation set can be continuously unimproved before stopping training; a larger patience value generally results in longer training time. | 10 |
+### Time Series Anomaly Detection
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| input_len | int | For time series anomaly detection tasks, this parameter represents the length of the time series input to the model, which will slice the time series according to this length to predict whether there is an anomaly in this segment of the time series; the input length should be considered in conjunction with the actual scenario. For example, an input length of 96 indicates that you want to predict whether there are anomalies in 96 time points. | 96 |
+| feature_cols | str | Feature variables indicating variables related to whether the device is abnormal, e.g., whether the device is abnormal may be related to the heat dissipation during its operation. Set the column name(s) of the feature variable(s) based on your data, can be multiple, separated by commas. | feature_0,feature_1 |
+| label_col | str | Represents the number indicating whether a time series point is abnormal, with 1 for abnormal points and 0 for normal points. | label |
+
+### Time Series Classification
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| target_cols | str | Feature variable columns used for category discrimination. You need to set the column names of the target variables in the time series dataset based on your own data. It can be multiple, separated by commas. | dim_0,dim_1,dim_2 |
+| freq | str or int | Frequency, which needs to be set based on your own data. Examples of time frequencies include: 1min, 5min, 1h. | 1 |
+| group_id | str | A group ID represents a time series sample. Time series sequences with the same ID constitute a sample. Set the column name of the specified group ID based on your own data, e.g., group_id. | group_id |
+| static_cov_cols | str | Represents the category number column of the time series. The labels of the same sample are the same. Set the column name of the category based on your own data, e.g., label. | label |
 
 # Evaluate
-
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| --- | --- | --- | --- | --- |  
-| weight_path | str | The path to the model weights for evaluation. | - | Required |  
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| weight_path | str | Evaluation model path | Default local path from training output, when specified as None, indicates using official weights |
 
 # Export
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| weight_path | str | Dynamic graph weight path for exporting the model | Default local path from training output, when specified as None, indicates using official weights |
 
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |    
-| -------------- | --------- | -------------------------------------------------- | ------------------- | ------------- |    
-| weight_path    | str       | The path to the dynamic graph weight file used for exporting the model |The official dynamic graph weight URLs for each model. | Required      |    
-  
 # Predict
-
-| Parameter Name | Data Type | Description | Default Value | Required/Optional |  
-| -------------- | --------- | ---------------------------------- | --------------- | ------------- |    
-| model_dir      | str       | Path to the directory containing the prediction model |The official weight | Optional      |  
-| input          | str       | Path to the input data for prediction | (No default, user must specify) | Required      |  
-| batch_size     | int       | The number of samples processed in each prediction batch | (No default, user must specify) | Required      |  
-
+| Parameter Name | Data Type | Description | Default Value |
+|-|-|-|-|
+| batch_size | int | Prediction batch size | The prediction batch size specified in the YAML file |
+| model_dir | str | Path to the prediction model | The default local inference model path produced by training. When specified as None, it indicates the use of official weights |
+| input | str | Path to the prediction input | The prediction input path specified in the YAML file |

docs/module_usage/tutorials/cv_modules/anomaly_detection.md

@@ -24,7 +24,7 @@
 完成wheel包的安装后，几行代码即可完成图像异常检测模块的推理，可以任意切换该模块下的模型，您也可以将图像异常检测的模块中的模型推理集成到您的项目中。
 运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/uad_grid.png)到本地。
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "STFPM"
 

docs/module_usage/tutorials/cv_modules/face_detection.md

@@ -23,7 +23,7 @@
 完成whl包的安装后，几行代码即可完成人脸检测模块的推理，可以任意切换该模块下的模型，您也可以将人脸检测的模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/face_detection.png)到本地。
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PicoDet_LCNet_x2_5_face"
 
@@ -103,7 +103,7 @@ python main.py -c paddlex/configs/face_detection/PicoDet_LCNet_x2_5_face.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 
 

docs/module_usage/tutorials/cv_modules/human_detection.md

@@ -49,7 +49,7 @@
 完成wheel包的安装后，几行代码即可完成行人检测模块的推理，可以任意切换该模块下的模型，您也可以将行人检测的模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/human_detection.jpg)到本地。
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PP-YOLOE-S_human"
 
@@ -132,7 +132,7 @@ python main.py -c paddlex/configs/human_detection/PP-YOLOE-S_human.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/ped_det/01.png)
 </details>

docs/module_usage/tutorials/cv_modules/image_classification.md

@@ -686,13 +686,13 @@ python main.py -c paddlex/configs/image_classification/PP-LCNet_x1_0.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/image_classification/01.png)
 </details>
 
 #### 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。。
+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>
   <summary>👉 <b>格式转换/数据集划分详情（点击展开）</b></summary>
@@ -757,7 +757,7 @@ python main.py -c paddlex/configs/image_classification/PP-LCNet_x1_0.yaml  \
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-LCNet_x1_0.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/module_usage/tutorials/cv_modules/image_feature.md

@@ -152,7 +152,7 @@ python main.py -c paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml \
 * `attributes.train_sample_paths`：该数据集训练样本可视化图片相对路径列表；
 * `attributes.gallery_sample_paths`：该数据集被查询样本可视化图片相对路径列表；
 * `attributes.query_sample_paths`：该数据集查询样本可视化图片相对路径列表；
-另外，数据集校验还对数据集中图像数量和图像类别情况进行了分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中图像数量和图像类别情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/img_recognition/01.png)
 </details>
@@ -184,7 +184,7 @@ tar -xf ./dataset/image_classification_labelme_examples.tar -C ./dataset/
 ......
 CheckDataset:
   ......
-  convert: 
+  convert:
     enable: True
     src_dataset_type: LabelMe
   ......
@@ -205,7 +205,7 @@ python main.py -c paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml  \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/image_classification_labelme_examples \
     -o CheckDataset.convert.enable=True \
-    -o CheckDataset.convert.src_dataset_type=LabelMe 
+    -o CheckDataset.convert.src_dataset_type=LabelMe
 ```
 **（2）数据集划分**
 
@@ -248,7 +248,7 @@ python main.py -c paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml  \
     -o CheckDataset.split.enable=True \
     -o CheckDataset.split.train_percent=70 \
     -o CheckDataset.split.gallery_percent=20 \
-    -o CheckDataset.split.query_percent=10 
+    -o CheckDataset.split.query_percent=10
 ```
 > ❗注意 ：由于图像特征模型评估的特殊性，当且仅当 train、query、gallery 集合属于同一类别体系下，数据切分才有意义，在图像特征模的评估过程中，必须满足 gallery 集合和 query 集合属于同一类别体系，其允许和 train 集合不在同一类别体系， 如果 gallery 集合和 query 集合与 train 集合不在同一类别体系，则数据划分后的评估没有意义，建议谨慎操作。
 
@@ -267,7 +267,7 @@ python main.py -c paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml \
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-ShiTuV2_rec.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -296,7 +296,7 @@ python main.py -c paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml \
 
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-ShiTuV2_rec.yaml`）
 * 指定模式为模型评估：`-o Global.mode=evaluate`
-* 指定验证数据集路径：`-o Global.dataset_dir`. 
+* 指定验证数据集路径：`-o Global.dataset_dir`.
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Evaluate`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)。
 
 <details>
@@ -326,7 +326,7 @@ python main.py -c paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml  \
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-ShiTuV2_rec.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"`
-* 指定输入数据路径：`-o Predict.input="..."`. 
+* 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)。
 
 > ❗ 注意：图像特征模型的推理结果为一组向量，需要配合检索模块完成图像的识别。

docs/module_usage/tutorials/cv_modules/instance_segmentation.md

@@ -155,7 +155,7 @@ 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[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，开发更好的实例分割模型。在使用 PaddleX 开发实例分割模型之前，请务必安装 PaddleX 的 分割 相关模型训练插件，安装过程可以参考[PaddleX本地安装教程](https://ku.baidu-int.com/knowledge/HFVrC7hq1Q/yKeL8Lljko/y0mmii50BW/dF1VvOPZmZXXzn?t=mention&mt=doc&dt=doc)中的二次开发部分。
+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，开发更好的实例分割模型。在使用 PaddleX 开发实例分割模型之前，请务必安装 PaddleX 的 分割 相关模型训练插件，安装过程可以参考[PaddleX本地安装教程](../../../installation/installation.md)中的二次开发部分。
 
 ### 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实例分割任务模块数据标注教程](../../../data_annotations/cv_modules/instance_segmentation.md)。
@@ -215,7 +215,7 @@ python main.py -c paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml \
 * `attributes.val_samples`：该数据集验证集样本数量为 19；
 * `attributes.train_sample_paths`：该数据集训练集样本可视化图片相对路径列表；
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
-另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/instanceseg/01.png)
 </details>
@@ -246,7 +246,7 @@ tar -xf ./dataset/instance_seg_labelme_examples.tar -C ./dataset/
 ......
 CheckDataset:
   ......
-  convert: 
+  convert:
     enable: True
     src_dataset_type: LabelMe
   ......
@@ -256,7 +256,7 @@ CheckDataset:
 ```bash
 python main.py -c paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml\
     -o Global.mode=check_dataset \
-    -o Global.dataset_dir=./dataset/instance_seg_labelme_examples 
+    -o Global.dataset_dir=./dataset/instance_seg_labelme_examples
 ```
 数据转换执行之后，原有标注文件会被在原路径下重命名为 `xxx.bak`。
 
@@ -296,7 +296,7 @@ CheckDataset:
 ```bash
 python main.py -c paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml \
     -o Global.mode=check_dataset \
-    -o Global.dataset_dir=./dataset/instance_seg_labelme_examples 
+    -o Global.dataset_dir=./dataset/instance_seg_labelme_examples
 ```
 数据划分执行之后，原有标注文件会被在原路径下重命名为 `xxx.bak`。
 
@@ -322,10 +322,10 @@ python main.py -c paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml \
 ```
 需要如下几步：
 
-* 指定模型的`.yaml` 配置文件路径（此处为`Mask-RT-DETR-L.yaml`）
+* 指定模型的`.yaml` 配置文件路径（此处为 `Mask-RT-DETR-L.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -353,7 +353,7 @@ python main.py -c paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml \
 ```
 与模型训练类似，需要如下几步：
 
-* 指定模型的`.yaml` 配置文件路径（此处为`Mask-RT-DETR-L`）
+* 指定模型的`.yaml` 配置文件路径（此处为 `Mask-RT-DETR-L.yaml`）
 * 指定模式为模型评估：`-o Global.mode=evaluate`
 * 指定验证数据集路径：`-o Global.dataset_dir`
 其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Evaluate`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)。
@@ -382,7 +382,7 @@ python main.py -c paddlex/configs/instance_segmentation/Mask-RT-DETR-L.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`Mask-RT-DETR-L.yaml`）
+* 指定模型的`.yaml` 配置文件路径（此处为 `Mask-RT-DETR-L.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"`
 * 指定输入数据路径：`-o Predict.input="..."`

docs/module_usage/tutorials/cv_modules/mainbody_detection.md

@@ -40,7 +40,7 @@
 完成whl包的安装后，几行代码即可完成主体检测模块的推理，可以任意切换该模块下的模型，您也可以将主体检测的模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png)到本地。
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PP-ShiTuV2_det"
 
@@ -121,7 +121,7 @@ python main.py -c paddlex/configs/mainbody_detection/PP-ShiTuV2_det.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/subj_det/01.png)
 </details>

docs/module_usage/tutorials/cv_modules/mainbody_detection_en.md

@@ -34,13 +34,13 @@ Mainbody detection is a fundamental task in object detection, aiming to identify
 **Note: The evaluation set for the above accuracy metrics is  PaddleClas mainbody detection dataset mAP(0.5:0.95). GPU inference time is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.**
 </details>
 
-## III. Quick Integration  <a id="quick"> </a> 
+## III. Quick Integration  <a id="quick"> </a>
 > ❗ Before quick integration, please install the PaddleX wheel package. For detailed instructions, refer to [PaddleX Local Installation Guide](../../../installation/installation_en.md)
 
 After installing the wheel package, you can perform mainbody detection inference with just a few lines of code. You can easily switch between models under this module, and integrate the mainbody detection model inference into your project. Before running the following code, please download the [demo image](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png) to your local machine.
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PP-ShiTuV2_det"
 
@@ -122,7 +122,7 @@ In the above validation results, `check_pass` being `True` indicates that the da
 * `attributes.val_sample_paths`： A list of relative paths to the visualized images of samples in the validation set of this dataset.
 
 
-The dataset validation also analyzes the distribution of sample counts across all classes in the dataset and generates a histogram (histogram.png) to visualize this distribution. 
+The dataset validation also analyzes the distribution of sample counts across all classes in the dataset and generates a histogram (histogram.png) to visualize this distribution.
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/subj_det/01.png)
 </details>
@@ -180,7 +180,7 @@ python main.py -c paddlex/configs/mainbody_detection/PP-ShiTuV2_det.yaml  \
 </details>
 
 ### 4.2 Model Training
-Model training can be completed with a single command, taking the training of `PP-ShiTuV2_det.yaml` as an example:
+Model training can be completed with a single command, taking the training of `PP-ShiTuV2_det` as an example:
 
 ```bash
 python main.py -c paddlex/configs/mainbody_detection/PP-ShiTuV2_det.yaml \

docs/module_usage/tutorials/cv_modules/ml_classification.md

@@ -152,13 +152,13 @@ python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yam
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/ml_classification/01.png)
 </details>
 
 #### 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。。
+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>
   <summary>👉 <b>格式转换/数据集划分详情（点击展开）</b></summary>
@@ -171,7 +171,7 @@ python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yam
   * `convert`:
     * `enable`: 是否进行数据集格式转换，图像多标签分类支持 `COCO`格式的数据集转换为 `MLClsDataset`格式，默认为 `False`;
     * `src_dataset_type`: 如果进行数据集格式转换，则需设置源数据集格式，默认为 `null`，可选值为 `COCO` ；
-  
+
 例如，您想将`COCO`格式的数据集转换为 `MLClsDataset`格式，则需将配置文件修改为：
 
 ```bash
@@ -183,7 +183,7 @@ tar -xf ./dataset/det_coco_examples.tar -C ./dataset/
 ......
 CheckDataset:
   ......
-  convert: 
+  convert:
     enable: True
     src_dataset_type: COCO
   ......
@@ -193,7 +193,7 @@ CheckDataset:
 ```bash
 python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml \
     -o Global.mode=check_dataset \
-    -o Global.dataset_dir=./dataset/det_coco_examples 
+    -o Global.dataset_dir=./dataset/det_coco_examples
 ```
 数据转换执行之后，原有标注文件会被在原路径下重命名为 `xxx.bak`。
 
@@ -233,7 +233,7 @@ CheckDataset:
 ```bash
 python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml \
     -o Global.mode=check_dataset \
-    -o Global.dataset_dir=./dataset/det_coco_examples 
+    -o Global.dataset_dir=./dataset/det_coco_examples
 ```
 数据划分执行之后，原有标注文件会被在原路径下重命名为 `xxx.bak`。
 
@@ -262,7 +262,7 @@ python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yam
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-LCNet_x1_0_ML.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -327,7 +327,7 @@ python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yam
 
 1.**产线集成**
 
-图像多标签分类模块可以集成的PaddleX产线有[通用图像多标签分类产线](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_lassification.md)，只需要替换模型路径即可完成相关产线的图像多标签分类模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
+图像多标签分类模块可以集成的PaddleX产线有[通用图像多标签分类产线](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md)，只需要替换模型路径即可完成相关产线的图像多标签分类模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
 
 2.**模块集成**
 

docs/module_usage/tutorials/cv_modules/object_detection.md

@@ -32,7 +32,6 @@
     <td>-</td>
     <td>-</td>
     <td>246.2 M</td>
-    <td></td>
   </tr>
   <tr>
     <td>CenterNet-DLA-34</td>
@@ -48,7 +47,7 @@
     <td>-</td>
     <td>-</td>
     <td>319.7 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>DETR-R50</td>
@@ -72,7 +71,7 @@
     <td>-</td>
     <td>-</td>
     <td>148.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet50-vd-FPN</td>
@@ -80,7 +79,7 @@
     <td>-</td>
     <td>-</td>
     <td>148.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet50-vd-SSLDv2-FPN</td>
@@ -88,7 +87,7 @@
     <td>-</td>
     <td>-</td>
     <td>148.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet50</td>
@@ -96,7 +95,7 @@
     <td>-</td>
     <td>-</td>
     <td>120.2 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet101-FPN</td>
@@ -104,7 +103,7 @@
     <td>-</td>
     <td>-</td>
     <td>216.3 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet101</td>
@@ -112,7 +111,7 @@
     <td>-</td>
     <td>-</td>
     <td>188.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNeXt101-vd-FPN</td>
@@ -120,7 +119,7 @@
     <td>-</td>
     <td>-</td>
     <td>360.6 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-Swin-Tiny-FPN</td>
@@ -128,7 +127,7 @@
     <td>-</td>
     <td>-</td>
     <td>159.8 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FCOS-ResNet50</td>
@@ -152,7 +151,7 @@
     <td>16.2311</td>
     <td>71.7257</td>
     <td>16.8 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PicoDet-S</td>
@@ -160,7 +159,7 @@
     <td>14.097</td>
     <td>37.6563</td>
     <td>4.4 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PicoDet-XS</td>
@@ -168,7 +167,7 @@
     <td>13.8102</td>
     <td>48.3139</td>
     <td>5.7 M</td>
-    <td></td>
+
   </tr>
     <tr>
     <td>PP-YOLOE_plus-L</td>
@@ -184,7 +183,7 @@
     <td>19.843</td>
     <td>449.261</td>
     <td>82.3 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PP-YOLOE_plus-S</td>
@@ -192,7 +191,7 @@
     <td>16.8884</td>
     <td>223.059</td>
     <td>28.3 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PP-YOLOE_plus-X</td>
@@ -200,7 +199,7 @@
     <td>57.8995</td>
     <td>1439.93</td>
     <td>349.4 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-H</td>
@@ -216,7 +215,7 @@
     <td>34.5252</td>
     <td>1454.27</td>
     <td>113.7 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-R18</td>
@@ -224,7 +223,7 @@
     <td>19.89</td>
     <td>784.824</td>
     <td>70.7 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-R50</td>
@@ -232,7 +231,7 @@
     <td>41.9327</td>
     <td>1625.95</td>
     <td>149.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-X</td>
@@ -240,7 +239,7 @@
     <td>61.8042</td>
     <td>2246.64</td>
     <td>232.9 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOv3-DarkNet53</td>
@@ -256,7 +255,7 @@
     <td>18.6692</td>
     <td>267.214</td>
     <td>83.8 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOv3-ResNet50_vd_DCN</td>
@@ -264,7 +263,7 @@
     <td>31.6276</td>
     <td>856.047</td>
     <td>163.0 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-L</td>
@@ -280,7 +279,7 @@
     <td>123.324</td>
     <td>688.071</td>
     <td>90.0 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-N</td>
@@ -288,7 +287,7 @@
     <td>79.1665</td>
     <td>155.59</td>
     <td>3.4 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-S</td>
@@ -296,7 +295,7 @@
     <td>184.828</td>
     <td>474.446</td>
     <td>32.0 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-T</td>
@@ -304,7 +303,7 @@
     <td>102.748</td>
     <td>212.52</td>
     <td>18.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-X</td>
@@ -312,7 +311,7 @@
     <td>227.361</td>
     <td>2067.84</td>
     <td>351.5 M</td>
-    <td></td>
+
   </tr>
 </table>
 
@@ -415,13 +414,13 @@ python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
 * `attributes.train_sample_paths`：该数据集训练集样本可视化图片相对路径列表；
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
-另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/obj_det/01.png)
 </details>
 
 #### 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。。
+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>
   <summary>👉 <b>格式转换/数据集划分详情（点击展开）</b></summary>
@@ -455,14 +454,14 @@ CheckDataset:
 随后执行命令：
 
 ```bash
-python main.py -c paddlex/configs/object_detection/PicoDet-L.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/det_labelme_examples
 ```
 当然，以上参数同样支持通过追加命令行参数的方式进行设置，以 `LabelMe` 格式的数据集为例：
 
 ```bash
-python main.py -c paddlex/configs/object_detection/PicoDet-L.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/det_labelme_examples \
     -o CheckDataset.convert.enable=True \
@@ -492,16 +491,16 @@ CheckDataset:
 随后执行命令：
 
 ```bash
-python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
-    -o Global.dataset_dir=./dataset/det_coco_examples 
+    -o Global.dataset_dir=./dataset/det_coco_examples
 ```
 数据划分执行之后，原有标注文件会被在原路径下重命名为 `xxx.bak`。
 
 以上参数同样支持通过追加命令行参数的方式进行设置：
 
 ```bash
-python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/det_coco_examples \
     -o CheckDataset.split.enable=True \

docs/module_usage/tutorials/cv_modules/object_detection_en.md

@@ -32,7 +32,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>246.2 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>CenterNet-DLA-34</td>
@@ -48,7 +48,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>319.7 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>DETR-R50</td>
@@ -72,7 +72,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>148.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet50-vd-FPN</td>
@@ -80,7 +80,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>148.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet50-vd-SSLDv2-FPN</td>
@@ -88,7 +88,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>148.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet50</td>
@@ -96,7 +96,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>120.2 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet101-FPN</td>
@@ -104,7 +104,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>216.3 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNet101</td>
@@ -112,7 +112,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>188.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-ResNeXt101-vd-FPN</td>
@@ -120,7 +120,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>360.6 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FasterRCNN-Swin-Tiny-FPN</td>
@@ -128,7 +128,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>-</td>
     <td>-</td>
     <td>159.8 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>FCOS-ResNet50</td>
@@ -152,7 +152,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>16.2311</td>
     <td>71.7257</td>
     <td>16.8 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PicoDet-S</td>
@@ -160,7 +160,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>14.097</td>
     <td>37.6563</td>
     <td>4.4 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PicoDet-XS</td>
@@ -168,7 +168,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>13.8102</td>
     <td>48.3139</td>
     <td>5.7 M</td>
-    <td></td>
+
   </tr>
     <tr>
     <td>PP-YOLOE_plus-L</td>
@@ -184,7 +184,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>19.843</td>
     <td>449.261</td>
     <td>82.3 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PP-YOLOE_plus-S</td>
@@ -192,7 +192,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>16.8884</td>
     <td>223.059</td>
     <td>28.3 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>PP-YOLOE_plus-X</td>
@@ -200,7 +200,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>57.8995</td>
     <td>1439.93</td>
     <td>349.4 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-H</td>
@@ -216,7 +216,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>34.5252</td>
     <td>1454.27</td>
     <td>113.7 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-R18</td>
@@ -224,7 +224,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>19.89</td>
     <td>784.824</td>
     <td>70.7 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-R50</td>
@@ -232,7 +232,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>41.9327</td>
     <td>1625.95</td>
     <td>149.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>RT-DETR-X</td>
@@ -240,7 +240,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>61.8042</td>
     <td>2246.64</td>
     <td>232.9 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOv3-DarkNet53</td>
@@ -256,7 +256,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>18.6692</td>
     <td>267.214</td>
     <td>83.8 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOv3-ResNet50_vd_DCN</td>
@@ -264,7 +264,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>31.6276</td>
     <td>856.047</td>
     <td>163.0 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-L</td>
@@ -280,7 +280,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>123.324</td>
     <td>688.071</td>
     <td>90.0 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-N</td>
@@ -288,7 +288,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>79.1665</td>
     <td>155.59</td>
     <td>3.4 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-S</td>
@@ -296,7 +296,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>184.828</td>
     <td>474.446</td>
     <td>32.0 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-T</td>
@@ -304,7 +304,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>102.748</td>
     <td>212.52</td>
     <td>18.1 M</td>
-    <td></td>
+
   </tr>
   <tr>
     <td>YOLOX-X</td>
@@ -312,7 +312,7 @@ The object detection module is a crucial component in computer vision systems, r
     <td>227.361</td>
     <td>2067.84</td>
     <td>351.5 M</td>
-    <td></td>
+
   </tr>
 </table>
 
@@ -460,14 +460,14 @@ CheckDataset:
 Then execute the command:
 
 ```bash
-python main.py -c paddlex/configs/object_detection/PicoDet-L.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/det_labelme_examples
 ```
 Of course, the above parameters also support being set by appending command line arguments. Taking a `LabelMe` format dataset as an example:
 
 ```bash
-python main.py -c paddlex/configs/object_detection/PicoDet-L.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/det_labelme_examples \
     -o CheckDataset.convert.enable=True \
@@ -498,16 +498,16 @@ CheckDataset:
 Then execute the command:
 
 ```bash
-python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
-    -o Global.dataset_dir=./dataset/det_coco_examples 
+    -o Global.dataset_dir=./dataset/det_coco_examples
 ```
 After dataset splitting is executed, the original annotation files will be renamed to `xxx.bak` in the original path.
 
 The above parameters also support being set by appending command line arguments:
 
 ```bash
-python main.py -c paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml \
+python main.py -c paddlex/configs/object_detection/PicoDet-S.yaml \
     -o Global.mode=check_dataset \
     -o Global.dataset_dir=./dataset/det_coco_examples \
     -o CheckDataset.split.enable=True \
@@ -529,7 +529,7 @@ The following steps are required:
 
 * Specify the `.yaml` configuration file path for the model (here it is `PicoDet-S.yaml`)
 * Set the mode to model training: `-o Global.mode=train`
-* Specify the path to the training dataset: `-o Global.dataset_dir`. 
+* Specify the path to the training dataset: `-o Global.dataset_dir`.
 Other related parameters can be set by modifying the `Global` and `Train` fields in the `.yaml` configuration file, or adjusted by appending parameters in the command line. For example, to specify training on the first two GPUs: `-o Global.device=gpu:0,1`; to set the number of training epochs to 10: `-o Train.epochs_iters=10`. For more modifiable parameters and their detailed explanations, refer to the configuration file instructions for the corresponding task module of the model [PaddleX Common Configuration File Parameters](../../instructions/config_parameters_common_en.md).
 
 <details>
@@ -598,5 +598,3 @@ The object detection module can be integrated into the [General Object Detection
 2.**Module Integration**
 
 The weights you produce can be directly integrated into the object detection module. Refer to the Python example code in [Quick Integration](#iii-quick-integration), and simply replace the model with the path to your trained model.
-
-

docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.md

@@ -33,6 +33,26 @@ 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[PaddleX单模型Python脚本使用说明](../../instructions/model_python_API.md)。
 
+**备注**：其中 `output` 的值索引为0表示是否佩戴帽子，索引值为1表示是否佩戴眼镜，索引值2-7表示上衣风格，索引值8-13表示下装风格，索引值14表示是否穿靴子，索引值15-17表示背的包的类型，索引值18表示正面是否持物，索引值19-21表示年龄，索引值22表示性别，索引值23-25表示朝向。具体地，属性包含以下类型：
+
+```
+- 性别：男、女
+- 年龄：小于18、18-60、大于60
+- 朝向：朝前、朝后、侧面
+- 配饰：眼镜、帽子、无
+- 正面持物：是、否
+- 包：双肩包、单肩包、手提包
+- 上衣风格：带条纹、带logo、带格子、拼接风格
+- 下装风格：带条纹、带图案
+- 短袖上衣：是、否
+- 长袖上衣：是、否
+- 长外套：是、否
+- 长裤：是、否
+- 短裤：是、否
+- 短裙&裙子：是、否
+- 穿靴：是、否
+```
+
 ## 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，开发更好的行人属性识别模型。在使用 PaddleX 开发行人属性识别之前，请务必安装 PaddleX 的分类相关模型训练插件，安装过程可以参考 [PaddleX本地安装教程](../../../installation/installation.md)中的二次开发部分。
 
@@ -113,7 +133,7 @@ python main.py -c paddlex/configs/pedestrian_attribute/PP-LCNet_x1_0_pedestrian_
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-另外，数据集校验还对数据集中所有图片的长宽分布情况进行了分析分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有图片的长宽分布情况进行了分析分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/ped_attri/image.png)
 
@@ -186,7 +206,7 @@ python main.py -c paddlex/configs/pedestrian_attribute/PP-LCNet_x1_0_pedestrian_
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-LCNet_x1_0_pedestrian_attribute.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -256,7 +276,7 @@ python main.py -c paddlex/configs/pedestrian_attribute/PP-LCNet_x1_0_pedestrian_
 
 1.**产线集成**
 
-行人属性识别模块可以集成的PaddleX产线有[通用图像多标签分类产线](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_lassification.md)，只需要替换模型路径即可完成相关产线的行人属性识别模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
+行人属性识别模块可以集成的PaddleX产线有[通用图像多标签分类产线](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md)，只需要替换模型路径即可完成相关产线的行人属性识别模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
 
 2.**模块集成**
 

docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition_en.md

@@ -35,6 +35,26 @@ for res in output:
 ```
 For more information on using PaddleX's single-model inference API, refer to the [PaddleX Single Model Python Script Usage Instructions](../../instructions/model_python_API_en.md).
 
+**Note**: The index of the `output` value represents the following attributes: index 0 indicates whether a hat is worn, index 1 indicates whether glasses are worn, indexes 2-7 represent the style of the upper garment, indexes 8-13 represent the style of the lower garment, index 14 indicates whether boots are worn, indexes 15-17 represent the type of bag carried, index 18 indicates whether an object is held in front, indexes 19-21 represent age, index 22 represents gender, and indexes 23-25 represent orientation. Specifically, the attributes include the following types:
+
+```
+- Gender: Male, Female
+- Age: Under 18, 18-60, Over 60
+- Orientation: Front, Back, Side
+- Accessories: Glasses, Hat, None
+- Holding Object in Front: Yes, No
+- Bag: Backpack, Shoulder Bag, Handbag
+- Upper Garment Style: Striped, Logo, Plaid, Patchwork
+- Lower Garment Style: Striped, Patterned
+- Short-sleeved Shirt: Yes, No
+- Long-sleeved Shirt: Yes, No
+- Long Coat: Yes, No
+- Pants: Yes, No
+- Shorts: Yes, No
+- Skirt: Yes, No
+- Boots: Yes, No
+```
+
 ## IV. Custom Development
 If you seek higher accuracy from existing models, you can leverage PaddleX's custom development capabilities to develop better pedestrian attribute recognition models. Before developing pedestrian attribute recognition with PaddleX, ensure you have installed the classification-related model training plugins for PaddleX.  The installation process can be found in the custom development section of the [PaddleX Local Installation Guide](../../../installation/installation_en.md).
 

docs/module_usage/tutorials/cv_modules/semantic_segmentation.md

@@ -120,7 +120,7 @@ python main.py -c paddlex/configs/semantic_segmentation/PP-LiteSeg-T.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/semanticseg/01.png)
 </details>

docs/module_usage/tutorials/cv_modules/small_object_detection.md

@@ -29,7 +29,7 @@
     <td>1007.0</td>
     <td>324.93</td>
     <td rowspan="3">基于VisDrone训练的PP-YOLOE_plus小目标检测模型。VisDrone是针对无人机视觉数据的基准数据集，由于目标较小同时具有一定的挑战性而被用于小目标检测任务的训练和评测</td>
-    
+
   </tr>
   <tr>
     <td>PP-YOLOE_plus_SOD-S</td>
@@ -58,7 +58,7 @@
 完成whl包的安装后，几行代码即可完成小目标检测模块的推理，可以任意切换该模块下的模型，您也可以将小目标检测的模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/small_object_detection.jpg)到本地。
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PP-YOLOE_plus_SOD-S"
 
@@ -138,7 +138,7 @@ python main.py -c paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-S.yam
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/smallobj_det/01.png)
 </details>

docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.md

@@ -34,6 +34,8 @@ 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[PaddleX单模型Python脚本使用说明](../../instructions/model_python_API.md)。
 
+**备注**：其中 `output` 的值索引为0-9表示颜色属性，对应的颜色分别是：yellow(黄色), orange(橙色), green(绿色), gray(灰色), red(红色), blue(蓝色), white(白色), golden(金色), brown(棕色), black(黑色)；索引为10-18表示车型属性，对应的车型分别是sedan(轿车), suv(越野车), van(面包车), hatchback(掀背车), mpv(多用途汽车), pickup(皮卡车), bus(公共汽车), truck(卡车), estate(旅行车)。
+
 ## 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，开发更好的车辆属性识别模型。在使用 PaddleX 开发车辆属性识别模型之前，请务必安装 PaddleX 的 分类 相关模型训练插件，安装过程可以参考[PaddleX本地安装教程](../../../installation/installation.md)。
 
@@ -115,13 +117,13 @@ python main.py -c paddlex/configs/vehicle_attribute/PP-LCNet_x1_0_vehicle_attrib
 
 
 
-另外，数据集校验还对数据集中所有图片的长宽分布情况进行了分析分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有图片的长宽分布情况进行了分析分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/vehicle_attri/01.png)
 </details>
 
 #### 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。。
+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>
   <summary>👉 <b>格式转换/数据集划分详情（点击展开）</b></summary>
@@ -186,7 +188,7 @@ python main.py -c paddlex/configs/vehicle_attribute/PP-LCNet_x1_0_vehicle_attrib
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-LCNet_x1_0_vehicle_attribute.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -255,7 +257,7 @@ python main.py -c paddlex/configs/vehicle_attribute/PP-LCNet_x1_0_vehicle_attrib
 
 1.**产线集成**
 
-车辆属性识别模块可以集成的PaddleX产线有[通用图像多标签分类产线](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_lassification.md)，只需要替换模型路径即可完成相关产线的车辆属性识别模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
+车辆属性识别模块可以集成的PaddleX产线有[通用图像多标签分类产线](../../../pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md)，只需要替换模型路径即可完成相关产线的车辆属性识别模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
 
 2.**模块集成**
 

docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition_en.md

@@ -19,6 +19,7 @@ Vehicle attribute recognition is a crucial component in computer vision systems.
 </details>
 
 ## <span id="lable">III. Quick Integration</span>
+
 > ❗ Before quick integration, please install the PaddleX wheel package. For detailed instructions, refer to [PaddleX Local Installation Guide](../../../installation/installation_en.md)
 
 After installing the wheel package, a few lines of code can complete the inference of the vehicle attribute recognition module. You can easily switch models under this module, and you can also integrate the model inference of the vehicle attribute recognition module into your project. Before running the following code, please download the [demo image](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_attribute_007.jpg) to your local machine.
@@ -34,6 +35,9 @@ for res in output:
 ```
 For more information on using PaddleX's single-model inference API, refer to [PaddleX Single Model Python Script Usage Instructions](../../instructions/model_python_API_en.md).
 
+**Note**: In the `output`, values indexed from 0-9 represent color attributes, corresponding to the following colors respectively: yellow, orange, green, gray, red, blue, white, golden, brown, black. Indices 10-18 represent vehicle type attributes, corresponding to the following vehicle types: sedan, suv, van, hatchback, mpv, pickup, bus, truck, estate.
+
+
 ## IV. Custom Development
 If you seek higher accuracy from existing models, you can leverage PaddleX's custom development capabilities to develop better vehicle attribute recognition models. Before using PaddleX to develop vehicle attribute recognition models, ensure you have installed the classification-related model training plugin for PaddleX. The installation process can be found in the [PaddleX Local Installation Guide](../../../installation/installation_en.md).
 

docs/module_usage/tutorials/cv_modules/vehicle_detection.md

@@ -45,7 +45,7 @@
 完成wheel包的安装后，几行代码即可完成车辆检测模块的推理，可以任意切换该模块下的模型，您也可以将车辆检测的模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/vehicle_detection.jpg)到本地。
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PP-YOLOE-S_vehicle"
 
@@ -126,7 +126,7 @@ python main.py -c paddlex/configs/vehicle_detection/PP-YOLOE-S_vehicle.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/vehicle_det/01.png)
 </details>

docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md

@@ -113,7 +113,7 @@ python main.py -c paddlex/configs/doc_text_orientation/PP-LCNet_x1_0_doc_ori.yam
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/doc_img_ori_classification/01.png)
 </details>
@@ -184,7 +184,7 @@ python main.py -c paddlex/configs/doc_text_orientation/PP-LCNet_x1_0_doc_ori.yam
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-LCNet_x1_0_doc_ori.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/module_usage/tutorials/ocr_modules/formula_recognition.md

@@ -27,7 +27,7 @@
     <td>89.7 M</td>
     <td>LaTeX-OCR是一种基于自回归大模型的公式识别算法，通过采用 Hybrid ViT 作为骨干网络，transformer作为解码器，显著提升了公式识别的准确性</td>
   </tr>
-  
+
 </table>
 
 **注：以上精度指标测量自 LaTeX-OCR公式识别测试集。**
@@ -123,12 +123,12 @@ python main.py -c paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/data_prepare/formula_recognition/01.jpg)
 </details>
 
 #### 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。。
+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>
   <summary>👉 <b>格式转换/数据集划分详情（点击展开）</b></summary>
@@ -141,14 +141,14 @@ python main.py -c paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml \
   * `convert`:
     * `enable`: 是否进行数据集格式转换，公式识别支持 `PKL`格式的数据集转换为 `LaTeXOCRDataset`格式，默认为 `True`;
     * `src_dataset_type`: 如果进行数据集格式转换，则需设置源数据集格式，默认为 `PKL`，可选值为 `PKL` ；
-  
+
 例如，您想将 `PKL`格式的数据集转换为 `LaTeXOCRDataset`格式，则需将配置文件修改为：
 
 ```bash
 ......
 CheckDataset:
   ......
-  convert: 
+  convert:
     enable: True
     src_dataset_type: PKL
   ......
@@ -216,7 +216,7 @@ python main.py -c  paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml \
 </details>
 
 ### 4.2 模型训练
-一条命令即可完成模型的训练，以此处公式识别模型 LaTeX_OCR_rec.yaml 的训练为例：
+一条命令即可完成模型的训练，以此处公式识别模型 LaTeX_OCR_rec 的训练为例：
 
 ```bash
 python main.py -c paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml  \
@@ -228,7 +228,7 @@ python main.py -c paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml  \
 * 指定模型的`.yaml` 配置文件路径（此处为`LaTeX_OCR_rec.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/module_usage/tutorials/ocr_modules/layout_detection.md

@@ -26,7 +26,7 @@
 完成whl包的安装后，几行代码即可完成版面区域检测模块的推理，可以任意切换该模块下的模型，您也可以将版面区域检测模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg)到本地。
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PicoDet-L_layout_3cls"
 
@@ -109,7 +109,7 @@ python main.py -c paddlex/configs/structure_analysis/PicoDet-L_layout_3cls.yaml
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/layout_dec/01.png)
 </details>
@@ -123,7 +123,7 @@ python main.py -c paddlex/configs/structure_analysis/PicoDet-L_layout_3cls.yaml
 
 **（1）数据集格式转换**
 
-人脸检测不支持数据格式转换。
+版面区域检测暂不支持数据格式转换。
 
 **（2）数据集划分**
 

docs/module_usage/tutorials/ocr_modules/layout_detection_en.md

@@ -20,13 +20,13 @@ The core task of structure analysis is to parse and segment the content of input
 **Note: The evaluation set for the above accuracy metrics is PaddleOCR's self-built layout region analysis dataset, containing 10,000 images of common document types, including English and Chinese papers, magazines, research reports, etc. GPU inference time is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.**
 </details>
 
-## III. Quick Integration  <a id="quick"> </a> 
+## III. Quick Integration  <a id="quick"> </a>
 > ❗ Before quick integration, please install the PaddleX wheel package. For detailed instructions, refer to [PaddleX Local Installation Tutorial](../../../installation/installation_en.md)
 
 After installing the wheel package, a few lines of code can complete the inference of the structure analysis module. You can switch models under this module freely, and you can also integrate the model inference of the structure analysis module into your project. Before running the following code, please download the [demo image](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg) to your local machine.
 
 ```python
-from paddlex import create_model 
+from paddlex import create_model
 
 model_name = "PicoDet-L_layout_3cls"
 
@@ -124,7 +124,7 @@ After completing dataset verification, you can convert the dataset format or re-
 
 **(1) Dataset Format Conversion**
 
-Structure analysis does not support data format conversion.
+Layout detection does not support data format conversion.
 
 **(2) Dataset Splitting**
 

docs/module_usage/tutorials/ocr_modules/seal_text_detection.md

@@ -112,7 +112,7 @@ python main.py -c paddlex/configs/text_detection_seal/PP-OCRv4_server_seal_det.y
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）： 
+数据集校验还对数据集中所有类别的样本数量分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/curved_text_dec/01.png)
 </details>
@@ -183,7 +183,7 @@ python main.py -c paddlex/configs/text_detection_seal/PP-OCRv4_server_seal_det.y
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-OCRv4_server_seal_det.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/module_usage/tutorials/ocr_modules/table_structure_recognition.md

@@ -136,7 +136,7 @@ python main.py -c paddlex/configs/table_recognition/SLANet.yaml \
 </details>
 
 #### 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。。
+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>
   <summary>👉 <b>格式转换/数据集划分详情（点击展开）</b></summary>
@@ -201,7 +201,7 @@ python main.py -c paddlex/configs/table_recognition/SLANet.yaml \
 * 指定模型的`.yaml` 配置文件路径（此处为`SLANet.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -267,9 +267,9 @@ python main.py -c paddlex/configs/table_recognition/SLANet.yaml  \
 
 1.**产线集成**
 
-表格结构识别模块可以集成的PaddleX产线有[通用表格识别产线](../../../pipeline_usage/tutorials/ocr_pipelies/table_recognition.md)、[文档场景信息抽取产线v3（PP-ChatOCRv3）](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md)，只需要替换模型路径即可完成相关产线的表格结构识别模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
+表格结构识别模块可以集成的PaddleX产线有[通用表格识别产线](../../../pipeline_usage/tutorials/ocr_pipelines/table_recognition.md)、[文档场景信息抽取产线v3（PP-ChatOCRv3）](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md)，只需要替换模型路径即可完成相关产线的表格结构识别模块的模型更新。在产线集成中，你可以使用高性能部署和服务化部署来部署你得到的模型。
 
 
 2.**模块集成**
 
-您产出的权重可以直接集成到表格结构识别模块中，可以参考[快速集成]()的 Python 示例代码，只需要将模型替换为你训练的到的模型路径即可。
+您产出的权重可以直接集成到表格结构识别模块中，可以参考[快速集成](#三快速集成)的 Python 示例代码，只需要将模型替换为你训练的到的模型路径即可。

docs/module_usage/tutorials/ocr_modules/table_structure_recognition_en.md

@@ -211,7 +211,7 @@ the following steps are required:
 
 * 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 set it through the `-o Global.output` field in the configuration file.
 * PaddleX shields you from the concepts of dynamic graph weights and static graph weights. During model training, both dynamic and static graph weights are produced, and static graph weights are selected by default for model inference.
-* When training other models, you need to specify the corresponding configuration file. The correspondence between models and configuration files can be found in [PaddleX Model List (CPU/GPU)](https://ku.baidu-int.com/knowledge/HFVrC7hq1Q/pKzJfZczuc/GvMbk70MZz/0PKFjfhs0UN4Qs?t=mention&mt=doc&dt=doc). After completing the model training, all outputs are saved in the specified output directory (default is `./output/`), typically including:
+* When training other models, you need to specify the corresponding configuration file. The correspondence between models and configuration files can be found in [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:
 
 * `train_result.json`: Training result record file, recording whether the training task was completed normally, as well as the output weight metrics, related file paths, etc.;
 * `train.log`: Training log file, recording changes in model metrics and loss during training;

docs/module_usage/tutorials/ocr_modules/text_detection.md

@@ -19,7 +19,7 @@
 
 ## 三、快速集成
 > ❗ 在快速集成前，请先安装 PaddleX 的 wheel 包，详细请参考 [PaddleX本地安装教程](../../../installation/installation.md)。
-> 
+>
 几行代码即可完成文本检测模块的推理，可以任意切换该模块下的模型，您也可以将文本检测的模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_001.png)到本地。
 
 ```python
@@ -95,7 +95,7 @@ python main.py -c paddlex/configs/text_detection/PP-OCRv4_mobile_det.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 
 
-另外，数据集校验还对数据集中所有图片的长宽分布情况进行了分析分析，并绘制了分布直方图（histogram.png）： 
+另外，数据集校验还对数据集中所有图片的长宽分布情况进行了分析分析，并绘制了分布直方图（histogram.png）：
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/text_det/01.png)
 </details>

docs/module_usage/tutorials/ocr_modules/text_recognition.md

@@ -104,7 +104,7 @@ 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，开发更好的文本识别模型。在使用 PaddleX 开发文本识别模型之前，请务必安装 PaddleX 的 OCR 相关模型训练插件，安装过程可以参考[PaddleX本地安装教程](../../../installation/installation.md)中的二次开发部分。
 
 ### 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](https://ku.baidu-int.com/knowledge/HFVrC7hq1Q/yKeL8Lljko/y0mmii50BW/VtwlUU5Na5lpFB?t=mention&mt=doc&dt=doc)。
+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：
@@ -161,7 +161,7 @@ python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
 * `attributes.val_sample_paths`：该数据集验证集样本可视化图片相对路径列表；
 另外，数据集校验还对数据集中所有字符长度占比的分布情况进行了分析，并绘制了分布直方图（histogram.png）：
 
-![](/tmp/images/modules/text_recog/01.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/text_recog/01.png)
 </details>
 
 #### 4.1.3 数据集格式转换/数据集划分（可选）
@@ -229,9 +229,9 @@ python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
 * 指定模型的`.yaml` 配置文件路径（此处为`PP-OCRv4_mobile_rec.yaml`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX通用模型配置文件参数说明](../../instructions/config_parameters_common.md)。
+
 
-**更多说明（点击展开）**
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>
@@ -255,7 +255,7 @@ python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
 python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
     -o Global.mode=evaluate \
     -o Global.dataset_dir=./dataset/ocr_rec_dataset_examples
-    
+
 ```
 与模型训练类似，需要如下几步：
 
@@ -299,7 +299,7 @@ python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
 
 1.**产线集成**
 
-文本识别模块可以集成的PaddleX产线有[通用 OCR 产线](../../../pipeline_usage/tutorials/ocr_pipelies/OCR.md)、[通用表格识别产线](../../../pipeline_usage/tutorials/ocr_pipelies/table_recognition.md)、[文档场景信息抽取产线v3（PP-ChatOCRv3）](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md)，只需要替换模型路径即可完成相关产线的文本识别模块的模型更新。
+文本识别模块可以集成的PaddleX产线有[通用 OCR 产线](../../../pipeline_usage/tutorials/ocr_pipelines/OCR.md)、[通用表格识别产线](../../../pipeline_usage/tutorials/ocr_pipelines/table_recognition.md)、[文档场景信息抽取产线v3（PP-ChatOCRv3）](../../../pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md)，只需要替换模型路径即可完成相关产线的文本识别模块的模型更新。
 
 2.**模块集成**
 

docs/module_usage/tutorials/ocr_modules/text_recognition_en.md

@@ -3,7 +3,7 @@
 # Text Recognition Module Development Tutorial
 
 ## I. Overview
-The text recognition module is the core component of an OCR (Optical Character Recognition) system, responsible for extracting text information from text regions within images. The performance of this module directly impacts the accuracy and efficiency of the entire OCR system. The text recognition module typically receives bounding boxes (Bounding Boxes) of text regions output by the text detection module as input. Through complex image processing and deep learning algorithms, it converts the text in images into editable and searchable electronic text. The accuracy of text recognition results is crucial for subsequent applications such as information extraction and data mining.
+The text recognition module is the core component of an OCR (Optical Character Recognition) system, responsible for extracting text information from text regions within images. The performance of this module directly impacts the accuracy and efficiency of the entire OCR system. The text recognition module typically receives bounding boxes of text regions output by the text detection module as input. Through complex image processing and deep learning algorithms, it converts the text in images into editable and searchable electronic text. The accuracy of text recognition results is crucial for subsequent applications such as information extraction and data mining.
 
 ## II. Supported Model List
 
@@ -83,7 +83,7 @@ The text recognition module is the core component of an OCR (Optical Character R
 
 **Note: The evaluation set for the above accuracy metrics is the [OCR End-to-End Recognition Task of the PaddleOCR Algorithm Model Challenge - Track 1](https://aistudio.baidu.com/competition/detail/1131/0/introduction) B-rank. GPU inference time for all models is based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speed is based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.**
 
-</details>      
+</details>
 
 ## III. Quick Integration
 Before quick integration, you need to install the PaddleX wheel package. For the installation method, please refer to the [PaddleX Local Installation Tutorial](../../../installation/installation_en.md). After installing the wheel package, a few lines of code can complete the inference of the text recognition module. You can switch models under this module freely, and you can also integrate the model inference of the text recognition module into your project.
@@ -162,7 +162,7 @@ In the above validation result, `check_pass` being `true` indicates that the dat
 * `attributes.val_sample_paths`: A list of relative paths to the visualized validation set samples in this dataset;
 Additionally, the dataset validation also analyzes the distribution of character length ratios in the dataset and generates a distribution histogram (histogram.png):
 
-![](/tmp/images/modules/text_recog/01.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/modules/text_recog/01.png)
 </details>
 
 #### 4.1.3 Dataset Format Conversion/Dataset Splitting (Optional)
@@ -230,10 +230,9 @@ The steps required are:
 
 * Specify the path to the model's `.yaml` configuration file (here it's `PP-OCRv4_mobile_rec.yaml`)
 * Specify the mode as model training: `-o Global.mode=train`
-* Specify the path to the training dataset: `-o Global.dataset_dir`. 
+* Specify the path to the training dataset: `-o Global.dataset_dir`.
 Other related parameters can be set by modifying the `Global` and `Train` fields in the `.yaml` configuration file or adjusted by appending parameters in the command line. For example, to specify training on the first 2 GPUs: `-o Global.device=gpu:0,1`; to set the number of training epochs to 10: `-o Train.epochs_iters=10`. For more modifiable parameters and their detailed explanations, refer to the [PaddleX Common Configuration File Parameters](../../instructions/config_parameters_common_en.md).
 
-**More Information (Click to Expand)**
 
 <details>
   <summary>👉 <b>More Information (Click to Expand)</b></summary>
@@ -258,7 +257,7 @@ After completing model training, you can evaluate the specified model weights fi
 python main.py -c paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml \
     -o Global.mode=evaluate \
     -o Global.dataset_dir=./dataset/ocr_rec_dataset_examples
-    
+
 ```
 Similar to model training, the following steps are required:
 
@@ -269,7 +268,7 @@ Other related parameters can be set by modifying the `Global` and `Evaluate` fie
 
 
 <details>
-  <summary>👉 <b>More Details (Click to Expand)</b></summary>
+  <summary>👉 <b>More Information (Click to Expand)</b></summary>
 
 When evaluating the model, you need to specify the model weights file path. Each configuration file has a default weight save path. If you need to change it, simply append the command line parameter to set it, such as `-o Evaluate.weight_path=./output/best_model/best_model.pdparams`.
 

docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md

@@ -227,7 +227,7 @@ 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`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/module_usage/tutorials/time_series_modules/time_series_classification.md

@@ -234,7 +234,7 @@ 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`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/module_usage/tutorials/time_series_modules/time_series_forecasting.md

@@ -259,7 +259,7 @@ 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`）
 * 指定模式为模型训练：`-o Global.mode=train`
 * 指定训练数据集路径：`-o Global.dataset_dir`
-其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅查阅模型对应任务模块的配置文件说明[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
+其他相关参数均可通过修改`.yaml`配置文件中的`Global`和`Train`下的字段来进行设置，也可以通过在命令行中追加参数来进行调整。如指定前 2 卡 gpu 训练：`-o Global.device=gpu:0,1`；设置训练轮次数为 10：`-o Train.epochs_iters=10`。更多可修改的参数及其详细解释，可以查阅模型对应任务模块的配置文件说明[PaddleX时序任务模型配置文件参数说明](../../instructions/config_parameters_time_series.md)。
 
 <details>
   <summary>👉 <b>更多说明（点击展开）</b></summary>

docs/support_list/models_list.md

@@ -4,370 +4,370 @@
 
 PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模块包含若干模型，具体使用哪些模型，您可以根据下边的 benchmark 数据来选择。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型推理速度，请选择推理速度较快的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
 
-## 图像分类模块
-|模型名称|Top1 Acc（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|CLIP_vit_base_patch16_224|85.36|13.1957|285.493|306.5 M|
-|CLIP_vit_large_patch14_224|88.1|51.1284|1131.28|1.04 G|
-|ConvNeXt_base_224|83.84|12.8473|1513.87|313.9 M|
-|ConvNeXt_base_384|84.90|31.7607|3967.05|313.9 M|
-|ConvNeXt_large_224|84.26|26.8103|2463.56|700.7 M|
-|ConvNeXt_large_384|85.27|66.4058|6598.92|700.7 M|
-|ConvNeXt_small|83.13|9.74075|1127.6|178.0 M|
-|ConvNeXt_tiny|82.03|5.48923|672.559|101.4 M|
-|FasterNet-L|83.5|23.4415|-|357.1 M|
-|FasterNet-M|83.0|21.8936|-|204.6 M|
-|FasterNet-S|81.3|13.0409|-|119.3 M|
-|FasterNet-T0|71.9|12.2432|-|15.1 M|
-|FasterNet-T1|75.9|11.3562|-|29.2 M|
-|FasterNet-T2|79.1|10.703|-|57.4 M|
-|MobileNetV1_x0_5|63.5|1.86754|7.48297|4.8 M|
-|MobileNetV1_x0_25|51.4|1.83478|4.83674|1.8 M|
-|MobileNetV1_x0_75|68.8|2.57903|10.6343|9.3 M|
-|MobileNetV1_x1_0|71.0|2.78781|13.98|15.2 M|
-|MobileNetV2_x0_5|65.0|4.94234|11.1629|7.1 M|
-|MobileNetV2_x0_25|53.2|4.50856|9.40991|5.5 M|
-|MobileNetV2_x1_0|72.2|6.12159|16.0442|12.6 M|
-|MobileNetV2_x1_5|74.1|6.28385|22.5129|25.0 M|
-|MobileNetV2_x2_0|75.2|6.12888|30.8612|41.2 M|
-|MobileNetV3_large_x0_5|69.2|6.31302|14.5588|9.6 M|
-|MobileNetV3_large_x0_35|64.3|5.76207|13.9041|7.5 M|
-|MobileNetV3_large_x0_75|73.1|8.41737|16.9506|14.0 M|
-|MobileNetV3_large_x1_0|75.3|8.64112|19.1614|19.5 M|
-|MobileNetV3_large_x1_25|76.4|8.73358|22.1296|26.5 M|
-|MobileNetV3_small_x0_5|59.2|5.16721|11.2688|6.8 M|
-|MobileNetV3_small_x0_35|53.0|5.22053|11.0055|6.0 M|
-|MobileNetV3_small_x0_75|66.0|5.39831|12.8313|8.5 M|
-|MobileNetV3_small_x1_0|68.2|6.00993|12.9598|10.5 M|
-|MobileNetV3_small_x1_25|70.7|6.9589|14.3995|13.0 M|
-|MobileNetV4_conv_large|83.4|12.5485|51.6453|125.2 M|
-|MobileNetV4_conv_medium|79.9|9.65509|26.6157|37.6 M|
-|MobileNetV4_conv_small|74.6|5.24172|11.0893|14.7 M|
-|MobileNetV4_hybrid_large|83.8|20.0726|213.769|145.1 M|
-|MobileNetV4_hybrid_medium|80.5|19.7543|62.2624|42.9 M|
-|PP-HGNet_base|85.0|14.2969|327.114|249.4 M|
-|PP-HGNet_small|81.51|5.50661|119.041|86.5 M|
-|PP-HGNet_tiny|79.83|5.22006|69.396|52.4 M|
-|PP-HGNetV2-B0|77.77|6.53694|23.352|21.4 M|
-|PP-HGNetV2-B1|79.18|6.56034|27.3099|22.6 M|
-|PP-HGNetV2-B2|81.74|9.60494|43.1219|39.9 M|
-|PP-HGNetV2-B3|82.98|11.0042|55.1367|57.9 M|
-|PP-HGNetV2-B4|83.57|9.66407|54.2462|70.4 M|
-|PP-HGNetV2-B5|84.75|15.7091|115.926|140.8 M|
-|PP-HGNetV2-B6|86.30|21.226|255.279|268.4 M|
-|PP-LCNet_x0_5|63.14|3.67722|6.66857|6.7 M|
-|PP-LCNet_x0_25|51.86|2.65341|5.81357|5.5 M|
-|PP-LCNet_x0_35|58.09|2.7212|6.28944|5.9 M|
-|PP-LCNet_x0_75|68.18|3.91032|8.06953|8.4 M|
-|PP-LCNet_x1_0|71.32|3.84845|9.23735|10.5 M|
-|PP-LCNet_x1_5|73.71|3.97666|12.3457|16.0 M|
-|PP-LCNet_x2_0|75.18|4.07556|16.2752|23.2 M|
-|PP-LCNet_x2_5|76.60|4.06028|21.5063|32.1 M|
-|PP-LCNetV2_base|77.05|5.23428|19.6005|23.7 M|
-|PP-LCNetV2_large |78.51|6.78335|30.4378|37.3 M|
-|PP-LCNetV2_small|73.97|3.89762|13.0273|14.6 M|
-|ResNet18_vd|72.3|3.53048|31.3014|41.5 M|
-|ResNet18|71.0|2.4868|27.4601|41.5 M|
-|ResNet34_vd|76.0|5.60675|56.0653|77.3 M|
-|ResNet34|74.6|4.16902|51.925|77.3 M|
-|ResNet50_vd|79.1|10.1885|68.446|90.8 M|
-|ResNet50|76.5|9.62383|64.8135|90.8 M|
-|ResNet101_vd|80.2|20.0563|124.85|158.4 M|
-|ResNet101|77.6|19.2297|121.006|158.7 M|
-|ResNet152_vd|80.6|29.6439|181.678|214.3 M|
-|ResNet152|78.3|30.0461|177.707|214.2 M|
-|ResNet200_vd|80.9|39.1628|235.185|266.0 M|
-|StarNet-S1|73.6|9.895|23.0465|11.2 M|
-|StarNet-S2|74.8|7.91279|21.9571|14.3 M|
-|StarNet-S3|77.0|10.7531|30.7656|22.2 M|
-|StarNet-S4|79.0|15.2868|43.2497|28.9 M|
-|SwinTransformer_base_patch4_window7_224|83.37|16.9848|383.83|310.5 M|
-|SwinTransformer_base_patch4_window12_384|84.17|37.2855|1178.63|311.4 M|
-|SwinTransformer_large_patch4_window7_224|86.19|27.5498|689.729|694.8 M|
-|SwinTransformer_large_patch4_window12_384|87.06|74.1768|2105.22|696.1 M|
-|SwinTransformer_small_patch4_window7_224|83.21|16.3982|285.56|175.6 M|
-|SwinTransformer_tiny_patch4_window7_224|81.10|8.54846|156.306|100.1 M|
+## [图像分类模块](../module_usage/tutorials/cv_modules/image_classification.md)
+|模型名称|Top1 Acc（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|CLIP_vit_base_patch16_224|85.36|13.1957|285.493|306.5 M|[CLIP_vit_base_patch16_224.yaml](../../paddlex/configs/image_classification/CLIP_vit_base_patch16_224.yaml)|
+|CLIP_vit_large_patch14_224|88.1|51.1284|1131.28|1.04 G|[CLIP_vit_large_patch14_224.yaml](../../paddlex/configs/image_classification/CLIP_vit_large_patch14_224.yaml)|
+|ConvNeXt_base_224|83.84|12.8473|1513.87|313.9 M|[ConvNeXt_base_224.yaml](../../paddlex/configs/image_classification/ConvNeXt_base_224.yaml)|
+|ConvNeXt_base_384|84.90|31.7607|3967.05|313.9 M|[ConvNeXt_base_384.yaml](../../paddlex/configs/image_classification/ConvNeXt_base_384.yaml)|
+|ConvNeXt_large_224|84.26|26.8103|2463.56|700.7 M|[ConvNeXt_large_224.yaml](../../paddlex/configs/image_classification/ConvNeXt_large_224.yaml)|
+|ConvNeXt_large_384|85.27|66.4058|6598.92|700.7 M|[ConvNeXt_large_384.yaml](../../paddlex/configs/image_classification/ConvNeXt_large_384.yaml)|
+|ConvNeXt_small|83.13|9.74075|1127.6|178.0 M|[ConvNeXt_small.yaml](../../paddlex/configs/image_classification/ConvNeXt_small.yaml)|
+|ConvNeXt_tiny|82.03|5.48923|672.559|101.4 M|[ConvNeXt_tiny.yaml](../../paddlex/configs/image_classification/ConvNeXt_tiny.yaml)|
+|FasterNet-L|83.5|23.4415|-|357.1 M|[FasterNet-L.yaml](../../paddlex/configs/image_classification/FasterNet-L.yaml)|
+|FasterNet-M|83.0|21.8936|-|204.6 M|[FasterNet-M.yaml](../../paddlex/configs/image_classification/FasterNet-M.yaml)|
+|FasterNet-S|81.3|13.0409|-|119.3 M|[FasterNet-S.yaml](../../paddlex/configs/image_classification/FasterNet-S.yaml)|
+|FasterNet-T0|71.9|12.2432|-|15.1 M|[FasterNet-T0.yaml](../../paddlex/configs/image_classification/FasterNet-T0.yaml)|
+|FasterNet-T1|75.9|11.3562|-|29.2 M|[FasterNet-T1.yaml](../../paddlex/configs/image_classification/FasterNet-T1.yaml)|
+|FasterNet-T2|79.1|10.703|-|57.4 M|[FasterNet-T2.yaml](../../paddlex/configs/image_classification/FasterNet-T2.yaml)|
+|MobileNetV1_x0_5|63.5|1.86754|7.48297|4.8 M|[MobileNetV1_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV1_x0_5.yaml)|
+|MobileNetV1_x0_25|51.4|1.83478|4.83674|1.8 M|[MobileNetV1_x0_25.yaml](../../paddlex/configs/image_classification/MobileNetV1_x0_25.yaml)|
+|MobileNetV1_x0_75|68.8|2.57903|10.6343|9.3 M|[MobileNetV1_x0_75.yaml](../../paddlex/configs/image_classification/MobileNetV1_x0_75.yaml)|
+|MobileNetV1_x1_0|71.0|2.78781|13.98|15.2 M|[MobileNetV1_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV1_x1_0.yaml)|
+|MobileNetV2_x0_5|65.0|4.94234|11.1629|7.1 M|[MobileNetV2_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV2_x0_5.yaml)|
+|MobileNetV2_x0_25|53.2|4.50856|9.40991|5.5 M|[MobileNetV2_x0_25.yaml](../../paddlex/configs/image_classification/MobileNetV2_x0_25.yaml)|
+|MobileNetV2_x1_0|72.2|6.12159|16.0442|12.6 M|[MobileNetV2_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV2_x1_0.yaml)|
+|MobileNetV2_x1_5|74.1|6.28385|22.5129|25.0 M|[MobileNetV2_x1_5.yaml](../../paddlex/configs/image_classification/MobileNetV2_x1_5.yaml)|
+|MobileNetV2_x2_0|75.2|6.12888|30.8612|41.2 M|[MobileNetV2_x2_0.yaml](../../paddlex/configs/image_classification/MobileNetV2_x2_0.yaml)|
+|MobileNetV3_large_x0_5|69.2|6.31302|14.5588|9.6 M|[MobileNetV3_large_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x0_5.yaml)|
+|MobileNetV3_large_x0_35|64.3|5.76207|13.9041|7.5 M|[MobileNetV3_large_x0_35.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x0_35.yaml)|
+|MobileNetV3_large_x0_75|73.1|8.41737|16.9506|14.0 M|[MobileNetV3_large_x0_75.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x0_75.yaml)|
+|MobileNetV3_large_x1_0|75.3|8.64112|19.1614|19.5 M|[MobileNetV3_large_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x1_0.yaml)|
+|MobileNetV3_large_x1_25|76.4|8.73358|22.1296|26.5 M|[MobileNetV3_large_x1_25.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x1_25.yaml)|
+|MobileNetV3_small_x0_5|59.2|5.16721|11.2688|6.8 M|[MobileNetV3_small_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x0_5.yaml)|
+|MobileNetV3_small_x0_35|53.0|5.22053|11.0055|6.0 M|[MobileNetV3_small_x0_35.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x0_35.yaml)|
+|MobileNetV3_small_x0_75|66.0|5.39831|12.8313|8.5 M|[MobileNetV3_small_x0_75.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x0_75.yaml)|
+|MobileNetV3_small_x1_0|68.2|6.00993|12.9598|10.5 M|[MobileNetV3_small_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x1_0.yaml)|
+|MobileNetV3_small_x1_25|70.7|6.9589|14.3995|13.0 M|[MobileNetV3_small_x1_25.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x1_25.yaml)|
+|MobileNetV4_conv_large|83.4|12.5485|51.6453|125.2 M|[MobileNetV4_conv_large.yaml](../../paddlex/configs/image_classification/MobileNetV4_conv_large.yaml)|
+|MobileNetV4_conv_medium|79.9|9.65509|26.6157|37.6 M|[MobileNetV4_conv_medium.yaml](../../paddlex/configs/image_classification/MobileNetV4_conv_medium.yaml)|
+|MobileNetV4_conv_small|74.6|5.24172|11.0893|14.7 M|[MobileNetV4_conv_small.yaml](../../paddlex/configs/image_classification/MobileNetV4_conv_small.yaml)|
+|MobileNetV4_hybrid_large|83.8|20.0726|213.769|145.1 M|[MobileNetV4_hybrid_large.yaml](../../paddlex/configs/image_classification/MobileNetV4_hybrid_large.yaml)|
+|MobileNetV4_hybrid_medium|80.5|19.7543|62.2624|42.9 M|[MobileNetV4_hybrid_medium.yaml](../../paddlex/configs/image_classification/MobileNetV4_hybrid_medium.yaml)|
+|PP-HGNet_base|85.0|14.2969|327.114|249.4 M|[PP-HGNet_base.yaml](../../paddlex/configs/image_classification/PP-HGNet_base.yaml)|
+|PP-HGNet_small|81.51|5.50661|119.041|86.5 M|[PP-HGNet_small.yaml](../../paddlex/configs/image_classification/PP-HGNet_small.yaml)|
+|PP-HGNet_tiny|79.83|5.22006|69.396|52.4 M|[PP-HGNet_tiny.yaml](../../paddlex/configs/image_classification/PP-HGNet_tiny.yaml)|
+|PP-HGNetV2-B0|77.77|6.53694|23.352|21.4 M|[PP-HGNetV2-B0.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B0.yaml)|
+|PP-HGNetV2-B1|79.18|6.56034|27.3099|22.6 M|[PP-HGNetV2-B1.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B1.yaml)|
+|PP-HGNetV2-B2|81.74|9.60494|43.1219|39.9 M|[PP-HGNetV2-B2.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B2.yaml)|
+|PP-HGNetV2-B3|82.98|11.0042|55.1367|57.9 M|[PP-HGNetV2-B3.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B3.yaml)|
+|PP-HGNetV2-B4|83.57|9.66407|54.2462|70.4 M|[PP-HGNetV2-B4.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B4.yaml)|
+|PP-HGNetV2-B5|84.75|15.7091|115.926|140.8 M|[PP-HGNetV2-B5.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B5.yaml)|
+|PP-HGNetV2-B6|86.30|21.226|255.279|268.4 M|[PP-HGNetV2-B6.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B6.yaml)|
+|PP-LCNet_x0_5|63.14|3.67722|6.66857|6.7 M|[PP-LCNet_x0_5.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_5.yaml)|
+|PP-LCNet_x0_25|51.86|2.65341|5.81357|5.5 M|[PP-LCNet_x0_25.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_25.yaml)|
+|PP-LCNet_x0_35|58.09|2.7212|6.28944|5.9 M|[PP-LCNet_x0_35.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_35.yaml)|
+|PP-LCNet_x0_75|68.18|3.91032|8.06953|8.4 M|[PP-LCNet_x0_75.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_75.yaml)|
+|PP-LCNet_x1_0|71.32|3.84845|9.23735|10.5 M|[PP-LCNet_x1_0.yaml](../../paddlex/configs/image_classification/PP-LCNet_x1_0.yaml)|
+|PP-LCNet_x1_5|73.71|3.97666|12.3457|16.0 M|[PP-LCNet_x1_5.yaml](../../paddlex/configs/image_classification/PP-LCNet_x1_5.yaml)|
+|PP-LCNet_x2_0|75.18|4.07556|16.2752|23.2 M|[PP-LCNet_x2_0.yaml](../../paddlex/configs/image_classification/PP-LCNet_x2_0.yaml)|
+|PP-LCNet_x2_5|76.60|4.06028|21.5063|32.1 M|[PP-LCNet_x2_5.yaml](../../paddlex/configs/image_classification/PP-LCNet_x2_5.yaml)|
+|PP-LCNetV2_base|77.05|5.23428|19.6005|23.7 M|[PP-LCNetV2_base.yaml](../../paddlex/configs/image_classification/PP-LCNetV2_base.yaml)|
+|PP-LCNetV2_large |78.51|6.78335|30.4378|37.3 M|[PP-LCNetV2_large.yaml](../../paddlex/configs/image_classification/PP-LCNetV2_large.yaml)|
+|PP-LCNetV2_small|73.97|3.89762|13.0273|14.6 M|[PP-LCNetV2_small.yaml](../../paddlex/configs/image_classification/PP-LCNetV2_small.yaml)|
+|ResNet18_vd|72.3|3.53048|31.3014|41.5 M|[ResNet18_vd.yaml](../../paddlex/configs/image_classification/ResNet18_vd.yaml)|
+|ResNet18|71.0|2.4868|27.4601|41.5 M|[ResNet18.yaml](../../paddlex/configs/image_classification/ResNet18.yaml)|
+|ResNet34_vd|76.0|5.60675|56.0653|77.3 M|[ResNet34_vd.yaml](../../paddlex/configs/image_classification/ResNet34_vd.yaml)|
+|ResNet34|74.6|4.16902|51.925|77.3 M|[ResNet34.yaml](../../paddlex/configs/image_classification/ResNet34.yaml)|
+|ResNet50_vd|79.1|10.1885|68.446|90.8 M|[ResNet50_vd.yaml](../../paddlex/configs/image_classification/ResNet50_vd.yaml)|
+|ResNet50|76.5|9.62383|64.8135|90.8 M|[ResNet50.yaml](../../paddlex/configs/image_classification/ResNet50.yaml)|
+|ResNet101_vd|80.2|20.0563|124.85|158.4 M|[ResNet101_vd.yaml](../../paddlex/configs/image_classification/ResNet101_vd.yaml)|
+|ResNet101|77.6|19.2297|121.006|158.7 M|[ResNet101.yaml](../../paddlex/configs/image_classification/ResNet101.yaml)|
+|ResNet152_vd|80.6|29.6439|181.678|214.3 M|[ResNet152_vd.yaml](../../paddlex/configs/image_classification/ResNet152_vd.yaml)|
+|ResNet152|78.3|30.0461|177.707|214.2 M|[ResNet152.yaml](../../paddlex/configs/image_classification/ResNet152.yaml)|
+|ResNet200_vd|80.9|39.1628|235.185|266.0 M|[ResNet200_vd.yaml](../../paddlex/configs/image_classification/ResNet200_vd.yaml)|
+|StarNet-S1|73.6|9.895|23.0465|11.2 M|[StarNet-S1.yaml](../../paddlex/configs/image_classification/StarNet-S1.yaml)|
+|StarNet-S2|74.8|7.91279|21.9571|14.3 M|[StarNet-S2.yaml](../../paddlex/configs/image_classification/StarNet-S2.yaml)|
+|StarNet-S3|77.0|10.7531|30.7656|22.2 M|[StarNet-S3.yaml](../../paddlex/configs/image_classification/StarNet-S3.yaml)|
+|StarNet-S4|79.0|15.2868|43.2497|28.9 M|[StarNet-S4.yaml](../../paddlex/configs/image_classification/StarNet-S4.yaml)|
+|SwinTransformer_base_patch4_window7_224|83.37|16.9848|383.83|310.5 M|[SwinTransformer_base_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_base_patch4_window7_224.yaml)|
+|SwinTransformer_base_patch4_window12_384|84.17|37.2855|1178.63|311.4 M|[SwinTransformer_base_patch4_window12_384.yaml](../../paddlex/configs/image_classification/SwinTransformer_base_patch4_window12_384.yaml)|
+|SwinTransformer_large_patch4_window7_224|86.19|27.5498|689.729|694.8 M|[SwinTransformer_large_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_large_patch4_window7_224.yaml)|
+|SwinTransformer_large_patch4_window12_384|87.06|74.1768|2105.22|696.1 M|[SwinTransformer_large_patch4_window12_384.yaml](../../paddlex/configs/image_classification/SwinTransformer_large_patch4_window12_384.yaml)|
+|SwinTransformer_small_patch4_window7_224|83.21|16.3982|285.56|175.6 M|[SwinTransformer_small_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_small_patch4_window7_224.yaml)|
+|SwinTransformer_tiny_patch4_window7_224|81.10|8.54846|156.306|100.1 M|[SwinTransformer_tiny_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_tiny_patch4_window7_224.yaml)|
 
 **注：以上精度指标为 **[ImageNet-1k](https://www.image-net.org/index.php)** 验证集 Top1 Acc。**
 
-## 图像多标签分类模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|CLIP_vit_base_patch16_448_ML|89.15|-|-|325.6 M|
-|PP-HGNetV2-B0_ML|80.98|-|-|39.6 M|
-|PP-HGNetV2-B4_ML|87.96|-|-|88.5 M|
-|PP-HGNetV2-B6_ML|91.25|-|-|286.5 M|
-|PP-LCNet_x1_0_ML|77.96|-|-|29.4 M|
-|ResNet50_ML|83.50|-|-|108.9 M|
+## [图像多标签分类模块](../module_usage/tutorials/cv_modules/ml_classification.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|CLIP_vit_base_patch16_448_ML|89.15|-|-|325.6 M|[CLIP_vit_base_patch16_448_ML.yaml](../../paddlex/configs/multilabel_classification/CLIP_vit_base_patch16_448_ML.yaml)|
+|PP-HGNetV2-B0_ML|80.98|-|-|39.6 M|[PP-HGNetV2-B0_ML.yaml](../../paddlex/configs/multilabel_classification/PP-HGNetV2-B0_ML.yaml)|
+|PP-HGNetV2-B4_ML|87.96|-|-|88.5 M|[PP-HGNetV2-B4_ML.yaml](../../paddlex/configs/multilabel_classification/PP-HGNetV2-B4_ML.yaml)|
+|PP-HGNetV2-B6_ML|91.25|-|-|286.5 M|[PP-HGNetV2-B6_ML.yaml](../../paddlex/configs/multilabel_classification/PP-HGNetV2-B6_ML.yaml)|
+|PP-LCNet_x1_0_ML|77.96|-|-|29.4 M|[PP-LCNet_x1_0_ML.yaml](../../paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml)|
+|ResNet50_ML|83.50|-|-|108.9 M|[ResNet50_ML.yaml](../../paddlex/configs/multilabel_classification/ResNet50_ML.yaml)|
 
 **注：以上精度指标为 [COCO2017](https://cocodataset.org/#home) 的多标签分类任务mAP。**
 
-## 行人属性模块
-|模型名称|mA（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-LCNet_x1_0_pedestrian_attribute|92.2|3.84845|9.23735|6.7 M  |
+## [行人属性模块](../module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.md)
+|模型名称|mA（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-LCNet_x1_0_pedestrian_attribute|92.2|3.84845|9.23735|6.7 M  |[PP-LCNet_x1_0_pedestrian_attribute.yaml](../../paddlex/configs/pedestrian_attribute/PP-LCNet_x1_0_pedestrian_attribute.yaml)|
 
 **注：以上精度指标为 PaddleX 内部自建数据集mA。**
 
-## 车辆属性模块
-|模型名称|mA（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-LCNet_x1_0_vehicle_attribute|91.7|3.84845|9.23735|6.7 M|
+## [车辆属性模块](../module_usage/tutorials/cv_modules/vehicle_attribute_recognition.md)
+|模型名称|mA（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-LCNet_x1_0_vehicle_attribute|91.7|3.84845|9.23735|6.7 M|[PP-LCNet_x1_0_vehicle_attribute.yaml](../../paddlex/configs/vehicle_attribute/PP-LCNet_x1_0_vehicle_attribute.yaml)|
 
 **注：以上精度指标为 VeRi 数据集 mA。**
 
-## 图像特征模块
-|模型名称|recall@1（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-ShiTuV2_rec|84.2|5.23428|19.6005|16.3 M|
-|PP-ShiTuV2_rec_CLIP_vit_base|88.69|13.1957|285.493|306.6 M|
-|PP-ShiTuV2_rec_CLIP_vit_large|91.03|51.1284|1131.28|1.05 G|
+## [图像特征模块](../module_usage/tutorials/cv_modules/image_feature.md)
+|模型名称|recall@1（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-ShiTuV2_rec|84.2|5.23428|19.6005|16.3 M|[PP-ShiTuV2_rec.yaml](../../paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml)|
+|PP-ShiTuV2_rec_CLIP_vit_base|88.69|13.1957|285.493|306.6 M|[PP-ShiTuV2_rec_CLIP_vit_base.yaml](../../paddlex/configs/general_recognition/PP-ShiTuV2_rec_CLIP_vit_base.yaml)|
+|PP-ShiTuV2_rec_CLIP_vit_large|91.03|51.1284|1131.28|1.05 G|[PP-ShiTuV2_rec_CLIP_vit_large.yaml](../../paddlex/configs/general_recognition/PP-ShiTuV2_rec_CLIP_vit_large.yaml)|
 
 **注：以上精度指标为 AliProducts recall@1。**
 
-## 文档方向分类模块
-|模型名称|Top-1 Acc（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-LCNet_x1_0_doc_ori|99.26|3.84845|9.23735|7.1 M|
+## [文档方向分类模块](../module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md)
+|模型名称|Top-1 Acc（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-LCNet_x1_0_doc_ori|99.26|3.84845|9.23735|7.1 M|[PP-LCNet_x1_0_doc_ori.yaml](../../paddlex/configs/doc_text_orientation/PP-LCNet_x1_0_doc_ori.yaml)|
 
 **注：以上精度指标为 PaddleX 内部自建数据集 Top-1 Acc 。**
 
-## 主体检测模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-ShiTuV2_det|41.5|33.7426|537.003|27.6 M|
+## [主体检测模块](../module_usage/tutorials/cv_modules/mainbody_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-ShiTuV2_det|41.5|33.7426|537.003|27.6 M|[PP-ShiTuV2_det.yaml](../../paddlex/configs/mainbody_detection/PP-ShiTuV2_det.yaml)|
 
 **注：以上精度指标为 [PaddleClas主体检测数据集](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.5/docs/zh_CN/training/PP-ShiTu/mainbody_detection.md) mAP(0.5:0.95)。**
 
-## 目标检测模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|Cascade-FasterRCNN-ResNet50-FPN|41.1|-|-|245.4 M|
-|Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN|45.0|-|-|246.2 M|
-|CenterNet-DLA-34|37.6|-|-|75.4 M|
-|CenterNet-ResNet50|38.9|-|-|319.7 M|
-|DETR-R50|42.3|59.2132|5334.52|159.3 M|
-|FasterRCNN-ResNet34-FPN|37.8|-|-|137.5 M|
-|FasterRCNN-ResNet50-FPN|38.4|-|-|148.1 M|
-|FasterRCNN-ResNet50-vd-FPN|39.5|-|-|148.1 M|
-|FasterRCNN-ResNet50-vd-SSLDv2-FPN|41.4|-|-|148.1 M|
-|FasterRCNN-ResNet50|36.7|-|-|120.2 M|
-|FasterRCNN-ResNet101-FPN|41.4|-|-|216.3 M|
-|FasterRCNN-ResNet101|39.0|-|-|188.1 M|
-|FasterRCNN-ResNeXt101-vd-FPN|43.4|-|-|360.6 M|
-|FasterRCNN-Swin-Tiny-FPN|42.6|-|-|159.8 M|
-|FCOS-ResNet50|39.6|103.367|3424.91|124.2 M|
-|PicoDet-L|42.6|16.6715|169.904|20.9 M|
-|PicoDet-M|37.5|16.2311|71.7257|16.8 M|
-|PicoDet-S|29.1|14.097|37.6563|4.4 M |
-|PicoDet-XS|26.2|13.8102|48.3139|5.7M |
-|PP-YOLOE_plus-L|52.9|33.5644|814.825|185.3 M|
-|PP-YOLOE_plus-M|49.8|19.843|449.261|83.2 M|
-|PP-YOLOE_plus-S|43.7|16.8884|223.059|28.3 M|
-|PP-YOLOE_plus-X|54.7|57.8995|1439.93|349.4 M|
-|RT-DETR-H|56.3|114.814|3933.39|435.8 M|
-|RT-DETR-L|53.0|34.5252|1454.27|113.7 M|
-|RT-DETR-R18|46.5|19.89|784.824|70.7 M|
-|RT-DETR-R50|53.1|41.9327|1625.95|149.1 M|
-|RT-DETR-X|54.8|61.8042|2246.64|232.9 M|
-|YOLOv3-DarkNet53|39.1|40.1055|883.041|219.7 M|
-|YOLOv3-MobileNetV3|31.4|18.6692|267.214|83.8 M|
-|YOLOv3-ResNet50_vd_DCN|40.6|31.6276|856.047|163.0 M|
-|YOLOX-L|50.1|185.691|1250.58|192.5 M|
-|YOLOX-M|46.9|123.324|688.071|90.0 M|
-|YOLOX-N|26.1|79.1665|155.59|3.4M|
-|YOLOX-S|40.4|184.828|474.446|32.0 M|
-|YOLOX-T|32.9|102.748|212.52|18.1 M|
-|YOLOX-X|51.8|227.361|2067.84|351.5 M|
+## [目标检测模块](../module_usage/tutorials/cv_modules/object_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|Cascade-FasterRCNN-ResNet50-FPN|41.1|-|-|245.4 M|[Cascade-FasterRCNN-ResNet50-FPN.yaml](../../paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-FPN.yaml)|
+|Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN|45.0|-|-|246.2 M|[Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|CenterNet-DLA-34|37.6|-|-|75.4 M|[CenterNet-DLA-34.yaml](../../paddlex/configs/object_detection/CenterNet-DLA-34.yaml)|
+|CenterNet-ResNet50|38.9|-|-|319.7 M|[CenterNet-ResNet50.yaml](../../paddlex/configs/object_detection/CenterNet-ResNet50.yaml)|
+|DETR-R50|42.3|59.2132|5334.52|159.3 M|[DETR-R50.yaml](../../paddlex/configs/object_detection/DETR-R50.yaml)|
+|FasterRCNN-ResNet34-FPN|37.8|-|-|137.5 M|[FasterRCNN-ResNet34-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet34-FPN.yaml)|
+|FasterRCNN-ResNet50-FPN|38.4|-|-|148.1 M|[FasterRCNN-ResNet50-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50-FPN.yaml)|
+|FasterRCNN-ResNet50-vd-FPN|39.5|-|-|148.1 M|[FasterRCNN-ResNet50-vd-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-FPN.yaml)|
+|FasterRCNN-ResNet50-vd-SSLDv2-FPN|41.4|-|-|148.1 M|[FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|FasterRCNN-ResNet50|36.7|-|-|120.2 M|[FasterRCNN-ResNet50.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50.yaml)|
+|FasterRCNN-ResNet101-FPN|41.4|-|-|216.3 M|[FasterRCNN-ResNet101-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet101-FPN.yaml)|
+|FasterRCNN-ResNet101|39.0|-|-|188.1 M|[FasterRCNN-ResNet101.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet101.yaml)|
+|FasterRCNN-ResNeXt101-vd-FPN|43.4|-|-|360.6 M|[FasterRCNN-ResNeXt101-vd-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNeXt101-vd-FPN.yaml)|
+|FasterRCNN-Swin-Tiny-FPN|42.6|-|-|159.8 M|[FasterRCNN-Swin-Tiny-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-Swin-Tiny-FPN.yaml)|
+|FCOS-ResNet50|39.6|103.367|3424.91|124.2 M|[FCOS-ResNet50.yaml](../../paddlex/configs/object_detection/FCOS-ResNet50.yaml)|
+|PicoDet-L|42.6|16.6715|169.904|20.9 M|[PicoDet-L.yaml](../../paddlex/configs/object_detection/PicoDet-L.yaml)|
+|PicoDet-M|37.5|16.2311|71.7257|16.8 M|[PicoDet-M.yaml](../../paddlex/configs/object_detection/PicoDet-M.yaml)|
+|PicoDet-S|29.1|14.097|37.6563|4.4 M |[PicoDet-S.yaml](../../paddlex/configs/object_detection/PicoDet-S.yaml)|
+|PicoDet-XS|26.2|13.8102|48.3139|5.7M |[PicoDet-XS.yaml](../../paddlex/configs/object_detection/PicoDet-XS.yaml)|
+|PP-YOLOE_plus-L|52.9|33.5644|814.825|185.3 M|[PP-YOLOE_plus-L.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-L.yaml)|
+|PP-YOLOE_plus-M|49.8|19.843|449.261|83.2 M|[PP-YOLOE_plus-M.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-M.yaml)|
+|PP-YOLOE_plus-S|43.7|16.8884|223.059|28.3 M|[PP-YOLOE_plus-S.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-S.yaml)|
+|PP-YOLOE_plus-X|54.7|57.8995|1439.93|349.4 M|[PP-YOLOE_plus-X.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-X.yaml)|
+|RT-DETR-H|56.3|114.814|3933.39|435.8 M|[RT-DETR-H.yaml](../../paddlex/configs/object_detection/RT-DETR-H.yaml)|
+|RT-DETR-L|53.0|34.5252|1454.27|113.7 M|[RT-DETR-L.yaml](../../paddlex/configs/object_detection/RT-DETR-L.yaml)|
+|RT-DETR-R18|46.5|19.89|784.824|70.7 M|[RT-DETR-R18.yaml](../../paddlex/configs/object_detection/RT-DETR-R18.yaml)|
+|RT-DETR-R50|53.1|41.9327|1625.95|149.1 M|[RT-DETR-R50.yaml](../../paddlex/configs/object_detection/RT-DETR-R50.yaml)|
+|RT-DETR-X|54.8|61.8042|2246.64|232.9 M|[RT-DETR-X.yaml](../../paddlex/configs/object_detection/RT-DETR-X.yaml)|
+|YOLOv3-DarkNet53|39.1|40.1055|883.041|219.7 M|[YOLOv3-DarkNet53.yaml](../../paddlex/configs/object_detection/YOLOv3-DarkNet53.yaml)|
+|YOLOv3-MobileNetV3|31.4|18.6692|267.214|83.8 M|[YOLOv3-MobileNetV3.yaml](../../paddlex/configs/object_detection/YOLOv3-MobileNetV3.yaml)|
+|YOLOv3-ResNet50_vd_DCN|40.6|31.6276|856.047|163.0 M|[YOLOv3-ResNet50_vd_DCN.yaml](../../paddlex/configs/object_detection/YOLOv3-ResNet50_vd_DCN.yaml)|
+|YOLOX-L|50.1|185.691|1250.58|192.5 M|[YOLOX-L.yaml](../../paddlex/configs/object_detection/YOLOX-L.yaml)|
+|YOLOX-M|46.9|123.324|688.071|90.0 M|[YOLOX-M.yaml](../../paddlex/configs/object_detection/YOLOX-M.yaml)|
+|YOLOX-N|26.1|79.1665|155.59|3.4M|[YOLOX-N.yaml](../../paddlex/configs/object_detection/YOLOX-N.yaml)|
+|YOLOX-S|40.4|184.828|474.446|32.0 M|[YOLOX-S.yaml](../../paddlex/configs/object_detection/YOLOX-S.yaml)|
+|YOLOX-T|32.9|102.748|212.52|18.1 M|[YOLOX-T.yaml](../../paddlex/configs/object_detection/YOLOX-T.yaml)|
+|YOLOX-X|51.8|227.361|2067.84|351.5 M|[YOLOX-X.yaml](../../paddlex/configs/object_detection/YOLOX-X.yaml)|
 
 **注：以上精度指标为 **[COCO2017](https://cocodataset.org/#home)** 验证集 mAP(0.5:0.95)。**
 
-## 小目标检测模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-YOLOE_plus_SOD-S|25.1|65.4608|324.37|77.3 M|
-|PP-YOLOE_plus_SOD-L|31.9|57.1448|1006.98|325.0 M|
-|PP-YOLOE_plus_SOD-largesize-L|42.7|458.521|11172.7|340.5 M|
+## [小目标检测模块](../module_usage/tutorials/cv_modules/small_object_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-YOLOE_plus_SOD-S|25.1|65.4608|324.37|77.3 M|[PP-YOLOE_plus_SOD-S.yaml](../../paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-S.yaml)|
+|PP-YOLOE_plus_SOD-L|31.9|57.1448|1006.98|325.0 M|[PP-YOLOE_plus_SOD-L.yaml](../../paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-L.yaml)|
+|PP-YOLOE_plus_SOD-largesize-L|42.7|458.521|11172.7|340.5 M|[PP-YOLOE_plus_SOD-largesize-L.yaml](../../paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-largesize-L.yaml)|
 
 **注：以上精度指标为 **[VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset)** 验证集 mAP(0.5:0.95)。**
 
-## 行人检测模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-YOLOE-L_human|48.0|32.7754|777.691|196.1 M|
-|PP-YOLOE-S_human|42.5|15.0118|179.317|28.8 M|
+## [行人检测模块](../module_usage/tutorials/cv_modules/human_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-YOLOE-L_human|48.0|32.7754|777.691|196.1 M|[PP-YOLOE-L_human.yaml](../../paddlex/configs/human_detection/PP-YOLOE-L_human.yaml)|
+|PP-YOLOE-S_human|42.5|15.0118|179.317|28.8 M|[PP-YOLOE-S_human.yaml](../../paddlex/configs/human_detection/PP-YOLOE-S_human.yaml)|
 
 **注：以上精度指标为 **[CrowdHuman](https://bj.bcebos.com/v1/paddledet/data/crowdhuman.zip)** 验证集 mAP(0.5:0.95)。**
 
-## 车辆检测模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-YOLOE-L_vehicle|63.9|32.5619|775.633|196.1 M|
-|PP-YOLOE-S_vehicle|61.3|15.3787|178.441|28.8 M|
+## [车辆检测模块](../module_usage/tutorials/cv_modules/vehicle_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-YOLOE-L_vehicle|63.9|32.5619|775.633|196.1 M|[PP-YOLOE-L_vehicle.yaml](../../paddlex/configs/vehicle_detection/PP-YOLOE-L_vehicle.yaml)|
+|PP-YOLOE-S_vehicle|61.3|15.3787|178.441|28.8 M|[PP-YOLOE-S_vehicle.yaml](../../paddlex/configs/vehicle_detection/PP-YOLOE-S_vehicle.yaml)|
 
 **注：以上精度指标为 **[PPVehicle](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppvehicle)** 验证集 mAP(0.5:0.95)。**
 
-## 人脸检测模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PicoDet_LCNet_x2_5_face|35.8|33.7426|537.003|27.7 M|
+## [人脸检测模块](../module_usage/tutorials/cv_modules/face_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PicoDet_LCNet_x2_5_face|35.8|33.7426|537.003|27.7 M|[PicoDet_LCNet_x2_5_face.yaml](../../paddlex/configs/face_detection/PicoDet_LCNet_x2_5_face.yaml)|
 
 **注：以上精度指标为 **[wider_face](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppvehicle)** 评估集 mAP(0.5:0.95)。**
 
-## 异常检测模块
-|模型名称|Avg（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|STFPM|96.2|-|-|21.5 M|
+## [异常检测模块](../module_usage/tutorials/cv_modules/anomaly_detection.md)
+|模型名称|Avg（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|STFPM|96.2|-|-|21.5 M|[STFPM.yaml](../../paddlex/configs/anomaly_detection/STFPM.yaml)|
 
 **注：以上精度指标为 **[MVTec AD](https://www.mvtec.com/company/research/datasets/mvtec-ad)** 验证集 平均异常分数。**
 
-## 语义分割模块
-|模型名称|mloU（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|Deeplabv3_Plus-R50 |80.36|61.0531|1513.58|94.9 M|
-|Deeplabv3_Plus-R101|81.10|100.026|2460.71|162.5 M|
-|Deeplabv3-R50|79.90|82.2631|1735.83|138.3 M|
-|Deeplabv3-R101|80.85|121.492|2685.51|205.9 M|
-|OCRNet_HRNet-W18|80.67|48.2335|906.385|43.1 M|
-|OCRNet_HRNet-W48|82.15|78.9976|2226.95|249.8 M|
-|PP-LiteSeg-T|73.10|7.6827|138.683|28.5 M|
-|PP-LiteSeg-B|75.25|-|-|47.0 M|
-|SegFormer-B0 (slice)|76.73|11.1946|268.929|13.2 M|
-|SegFormer-B1 (slice)|78.35|17.9998|403.393|48.5 M|
-|SegFormer-B2 (slice)|81.60|48.0371|1248.52|96.9 M|
-|SegFormer-B3 (slice)|82.47|64.341|1666.35|167.3 M|
-|SegFormer-B4 (slice)|82.38|82.4336|1995.42|226.7 M|
-|SegFormer-B5 (slice)|82.58|97.3717|2420.19|229.7 M|
+## [语义分割模块](../module_usage/tutorials/cv_modules/semantic_segmentation.md)
+|模型名称|mloU（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|Deeplabv3_Plus-R50 |80.36|61.0531|1513.58|94.9 M|[Deeplabv3_Plus-R50.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3_Plus-R50.yaml)|
+|Deeplabv3_Plus-R101|81.10|100.026|2460.71|162.5 M|[Deeplabv3_Plus-R101.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3_Plus-R101.yaml)|
+|Deeplabv3-R50|79.90|82.2631|1735.83|138.3 M|[Deeplabv3-R50.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3-R50.yaml)|
+|Deeplabv3-R101|80.85|121.492|2685.51|205.9 M|[Deeplabv3-R101.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3-R101.yaml)|
+|OCRNet_HRNet-W18|80.67|48.2335|906.385|43.1 M|[OCRNet_HRNet-W18.yaml](../../paddlex/configs/semantic_segmentation/OCRNet_HRNet-W18.yaml)|
+|OCRNet_HRNet-W48|82.15|78.9976|2226.95|249.8 M|[OCRNet_HRNet-W48.yaml](../../paddlex/configs/semantic_segmentation/OCRNet_HRNet-W48.yaml)|
+|PP-LiteSeg-T|73.10|7.6827|138.683|28.5 M|[PP-LiteSeg-T.yaml](../../paddlex/configs/semantic_segmentation/PP-LiteSeg-T.yaml)|
+|PP-LiteSeg-B|75.25|-|-|47.0 M|[PP-LiteSeg-B.yaml](../../paddlex/configs/semantic_segmentation/PP-LiteSeg-B.yaml)|
+|SegFormer-B0 (slice)|76.73|11.1946|268.929|13.2 M|[SegFormer-B0.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B0.yaml)|
+|SegFormer-B1 (slice)|78.35|17.9998|403.393|48.5 M|[SegFormer-B1.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B1.yaml)|
+|SegFormer-B2 (slice)|81.60|48.0371|1248.52|96.9 M|[SegFormer-B2.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B2.yaml)|
+|SegFormer-B3 (slice)|82.47|64.341|1666.35|167.3 M|[SegFormer-B3.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B3.yaml)|
+|SegFormer-B4 (slice)|82.38|82.4336|1995.42|226.7 M|[SegFormer-B4.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B4.yaml)|
+|SegFormer-B5 (slice)|82.58|97.3717|2420.19|229.7 M|[SegFormer-B5.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B5.yaml)|
 
 **注：以上精度指标为 **[Cityscapes](https://www.cityscapes-dataset.com/)** 数据集 mloU。**
 
-|模型名称|mloU（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|SeaFormer_base(slice)|40.92|24.4073|397.574|30.8 M|
-|SeaFormer_large (slice)|43.66|27.8123|550.464|49.8 M|
-|SeaFormer_small (slice)|38.73|19.2295|358.343|14.3 M|
-|SeaFormer_tiny (slice)|34.58|13.9496|330.132|6.1M |
+|模型名称|mloU（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|SeaFormer_base(slice)|40.92|24.4073|397.574|30.8 M|[SeaFormer_base.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_base.yaml)|
+|SeaFormer_large (slice)|43.66|27.8123|550.464|49.8 M|[SeaFormer_large.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_large.yaml)|
+|SeaFormer_small (slice)|38.73|19.2295|358.343|14.3 M|[SeaFormer_small.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_small.yaml)|
+|SeaFormer_tiny (slice)|34.58|13.9496|330.132|6.1M |[SeaFormer_tiny.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_tiny.yaml)|
 
 **注：以上精度指标为 **[ADE20k](https://groups.csail.mit.edu/vision/datasets/ADE20K/)** 数据集, slice 表示对输入图像进行了切图操作。**
 
-## 实例分割模块
-|模型名称|Mask AP|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|Mask-RT-DETR-H|50.6|132.693|4896.17|449.9 M|
-|Mask-RT-DETR-L|45.7|46.5059|2575.92|113.6 M|
-|Mask-RT-DETR-M|42.7|36.8329|-|66.6 M|
-|Mask-RT-DETR-S|41.0|33.5007|-|51.8 M|
-|Mask-RT-DETR-X|47.5|75.755|3358.04|237.5 M|
-|Cascade-MaskRCNN-ResNet50-FPN|36.3|-|-|254.8 M|
-|Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN|39.1|-|-|254.7 M|
-|MaskRCNN-ResNet50-FPN|35.6|-|-|157.5 M|
-|MaskRCNN-ResNet50-vd-FPN|36.4|-|-|157.5 M|
-|MaskRCNN-ResNet50-vd-SSLDv2-FPN|38.2|-|-|157.2 M|
-|MaskRCNN-ResNet50|32.8|-|-|127.8 M|
-|MaskRCNN-ResNet101-FPN|36.6|-|-|225.4 M|
-|MaskRCNN-ResNet101-vd-FPN|38.1|-|-|225.1 M|
-|MaskRCNN-ResNeXt101-vd-FPN|39.5|-|-|370.0 M|
-|PP-YOLOE_seg-S|32.5|-|-|31.5 M|
+## [实例分割模块](../module_usage/tutorials/cv_modules/instance_segmentation.md)
+|模型名称|Mask AP|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|Mask-RT-DETR-H|50.6|132.693|4896.17|449.9 M|[Mask-RT-DETR-H.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-H.yaml)|
+|Mask-RT-DETR-L|45.7|46.5059|2575.92|113.6 M|[Mask-RT-DETR-L.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml)|
+|Mask-RT-DETR-M|42.7|36.8329|-|66.6 M|[Mask-RT-DETR-M.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-M.yaml)|
+|Mask-RT-DETR-S|41.0|33.5007|-|51.8 M|[Mask-RT-DETR-S.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-S.yaml)|
+|Mask-RT-DETR-X|47.5|75.755|3358.04|237.5 M|[Mask-RT-DETR-X.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-X.yaml)|
+|Cascade-MaskRCNN-ResNet50-FPN|36.3|-|-|254.8 M|[Cascade-MaskRCNN-ResNet50-FPN.yaml](../../paddlex/configs/instance_segmentation/Cascade-MaskRCNN-ResNet50-FPN.yaml)|
+|Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN|39.1|-|-|254.7 M|[Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/instance_segmentation/Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|MaskRCNN-ResNet50-FPN|35.6|-|-|157.5 M|[MaskRCNN-ResNet50-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50-FPN.yaml)|
+|MaskRCNN-ResNet50-vd-FPN|36.4|-|-|157.5 M|[MaskRCNN-ResNet50-vd-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50-vd-FPN.yaml)|
+|MaskRCNN-ResNet50-vd-SSLDv2-FPN|38.2|-|-|157.2 M|[MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|MaskRCNN-ResNet50|32.8|-|-|127.8 M|[MaskRCNN-ResNet50.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50.yaml)|
+|MaskRCNN-ResNet101-FPN|36.6|-|-|225.4 M|[MaskRCNN-ResNet101-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet101-FPN.yaml)|
+|MaskRCNN-ResNet101-vd-FPN|38.1|-|-|225.1 M|[MaskRCNN-ResNet101-vd-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet101-vd-FPN.yaml)|
+|MaskRCNN-ResNeXt101-vd-FPN|39.5|-|-|370.0 M|[MaskRCNN-ResNeXt101-vd-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNeXt101-vd-FPN.yaml)|
+|PP-YOLOE_seg-S|32.5|-|-|31.5 M|[PP-YOLOE_seg-S.yaml](../../paddlex/configs/instance_segmentation/PP-YOLOE_seg-S.yaml)|
 
 **注：以上精度指标为 **[COCO2017](https://cocodataset.org/#home)** 验证集 Mask AP(0.5:0.95)。**
 
-## 文本检测模块
-|模型名称|检测Hmean（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-OCRv4_mobile_det |77.79|10.6923|120.177|4.2 M|
-|PP-OCRv4_server_det |82.69|83.3501|2434.01|100.1M|
+## [文本检测模块](../module_usage/tutorials/ocr_modules/text_detection.md)
+|模型名称|检测Hmean（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-OCRv4_mobile_det |77.79|10.6923|120.177|4.2 M|[PP-OCRv4_mobile_det.yaml](../../paddlex/configs/text_detection/PP-OCRv4_mobile_det.yaml)|
+|PP-OCRv4_server_det |82.69|83.3501|2434.01|100.1M|[PP-OCRv4_server_det.yaml](../../paddlex/configs/text_detection/PP-OCRv4_server_det.yaml)|
 
 **注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中检测包含 500 张图片。**
 
-## 印章文本检测模块
-|模型名称|检测Hmean（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-OCRv4_mobile_seal_det|96.47|10.5878|131.813|4.7M |
-|PP-OCRv4_server_seal_det|98.21|84.341|2425.06|108.3 M|
+## [印章文本检测模块](../module_usage/tutorials/ocr_modules/seal_text_detection.md)
+|模型名称|检测Hmean（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-OCRv4_mobile_seal_det|96.47|10.5878|131.813|4.7M |[PP-OCRv4_mobile_seal_det.yaml](../../paddlex/configs/text_detection_seal/PP-OCRv4_mobile_seal_det.yaml)|
+|PP-OCRv4_server_seal_det|98.21|84.341|2425.06|108.3 M|[PP-OCRv4_server_seal_det.yaml](../../paddlex/configs/text_detection_seal/PP-OCRv4_server_seal_det.yaml)|
 
 **注：以上精度指标的评估集是 PaddleX 自建的印章数据集，包含500印章图像。**
 
-## 文本识别模块
-|模型名称|识别Avg Accuracy(%)|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PP-OCRv4_mobile_rec |78.20|7.95018|46.7868|10.6 M|
-|PP-OCRv4_server_rec |79.20|7.19439|140.179|71.2 M|
+## [文本识别模块](../module_usage/tutorials/ocr_modules/text_recognition.md)
+|模型名称|识别Avg Accuracy(%)|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PP-OCRv4_mobile_rec |78.20|7.95018|46.7868|10.6 M|[PP-OCRv4_mobile_rec.yaml](../../paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml)|
+|PP-OCRv4_server_rec |79.20|7.19439|140.179|71.2 M|[PP-OCRv4_server_rec.yaml](../../paddlex/configs/text_recognition/PP-OCRv4_server_rec.yaml)|
 
 **注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中文本识别包含 1.1w 张图片。**
 
-|模型名称|识别Avg Accuracy(%)|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|ch_SVTRv2_rec|68.81|8.36801|165.706|73.9 M|
+|模型名称|识别Avg Accuracy(%)|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|ch_SVTRv2_rec|68.81|8.36801|165.706|73.9 M|[ch_SVTRv2_rec.yaml](../../paddlex/configs/text_recognition/ch_SVTRv2_rec.yaml)|
 
 **注：以上精度指标的评估集是 [PaddleOCR算法模型挑战赛 - 赛题一：OCR端到端识别任务](https://aistudio.baidu.com/competition/detail/1131/0/introduction)A榜。**
 
-|模型名称|识别Avg Accuracy(%)|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|ch_RepSVTR_rec|65.07|10.5047|51.5647|22.1 M|
+|模型名称|识别Avg Accuracy(%)|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|ch_RepSVTR_rec|65.07|10.5047|51.5647|22.1 M|[ch_RepSVTR_rec.yaml](../../paddlex/configs/text_recognition/ch_RepSVTR_rec.yaml)|
 
 **注：以上精度指标的评估集是 [PaddleOCR算法模型挑战赛 - 赛题一：OCR端到端识别任务](https://aistudio.baidu.com/competition/detail/1131/0/introduction)B榜。**
 
-## 公式识别模块
-|模型名称|BLEU score|normed edit distance|ExpRate （%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|-|-|
-|LaTeX_OCR_rec|0.8821|0.0823|40.01|-|-|89.7 M|
+## [公式识别模块](../module_usage/tutorials/ocr_modules/formula_recognition.md)
+|模型名称|BLEU score|normed edit distance|ExpRate （%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|-|-|
+|LaTeX_OCR_rec|0.8821|0.0823|40.01|-|-|89.7 M|[LaTeX_OCR_rec.yaml](../../paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml)|
 
 **注：以上精度指标测量自 [LaTeX-OCR公式识别测试集](https://drive.google.com/drive/folders/13CA4vAmOmD_I_dSbvLp-Lf0s6KiaNfuO)。**
 
-## 表格结构识别模块
-|模型名称|精度（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|SLANet|59.52|522.536|1845.37|6.9 M |
-|SLANet_plus|63.69|522.536|1845.37|6.9 M |
+## [表格结构识别模块](../module_usage/tutorials/ocr_modules/table_structure_recognition.md)
+|模型名称|精度（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|SLANet|59.52|522.536|1845.37|6.9 M |[SLANet.yaml](../../paddlex/configs/table_recognition/SLANet.yaml)|
+|SLANet_plus|63.69|522.536|1845.37|6.9 M |[SLANet_plus.yaml](../../paddlex/configs/table_recognition/SLANet_plus.yaml)|
 
 **注：以上精度指标测量自 ****PaddleX内部自建英文表格识别数据集****。**
 
-## 图像矫正模块
-|模型名称|MS-SSIM （%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|UVDoc|54.40|-|-|30.3 M|
+## [图像矫正模块](../module_usage/tutorials/ocr_modules/text_image_unwarping.md)
+|模型名称|MS-SSIM （%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|UVDoc|54.40|-|-|30.3 M|[UVDoc.yaml](../../paddlex/configs/image_unwarping/UVDoc.yaml)|
 
 **注：以上精度指标测量自 ****PaddleX自建的图像矫正数据集****。**
 
-## 版面区域分析模块
-|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|
-|-|-|-|-|-|
-|PicoDet_layout_1x|86.8|13.036|91.2634|7.4 M |
-|PicoDet-L_layout_3cls|89.3|15.7425|159.771|22.6 M|
-|RT-DETR-H_layout_3cls|95.9|114.644|3832.62|470.1 M|
-|RT-DETR-H_layout_17cls|92.6|115.126|3827.25|470.2 M|
+## [版面区域检测模块](../module_usage/tutorials/ocr_modules/layout_detection.md)
+|模型名称|mAP（%）|GPU推理耗时（ms）|CPU推理耗时（ms）|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|PicoDet_layout_1x|86.8|13.036|91.2634|7.4 M |[PicoDet_layout_1x.yaml](../../paddlex/configs/structure_analysis/PicoDet_layout_1x.yaml)|
+|PicoDet-L_layout_3cls|89.3|15.7425|159.771|22.6 M|[PicoDet-L_layout_3cls.yaml](../../paddlex/configs/structure_analysis/PicoDet-L_layout_3cls.yaml)|
+|RT-DETR-H_layout_3cls|95.9|114.644|3832.62|470.1 M|[RT-DETR-H_layout_3cls.yaml](../../paddlex/configs/structure_analysis/RT-DETR-H_layout_3cls.yaml)|
+|RT-DETR-H_layout_17cls|92.6|115.126|3827.25|470.2 M|[RT-DETR-H_layout_17cls.yaml](../../paddlex/configs/structure_analysis/RT-DETR-H_layout_17cls.yaml)|
 
-**注：以上精度指标的评估集是 ****PaddleX 自建的版面区域分析数据集****，包含 1w 张图片。**
+**注：以上精度指标的评估集是 ****PaddleX 自建的版面区域检测数据集****，包含 1w 张图片。**
 
-## 时序预测模块
-|模型名称|mse|mae|模型存储大小|
-|-|-|-|-|
-|DLinear|0.382|0.394|72 K|
-|NLinear|0.386|0.392|40 K |
-|Nonstationary|0.600|0.515|55.5 M|
-|PatchTST|0.385|0.397|2.0 M |
-|RLinear|0.384|0.392|40 K|
-|TiDE|0.405|0.412|31.7 M|
-|TimesNet|0.417|0.431|4.9 M|
+## [时序预测模块](../module_usage/tutorials/time_series_modules/time_series_forecasting.md)
+|模型名称|mse|mae|模型存储大小|yaml 文件|
+|-|-|-|-|-|
+|DLinear|0.382|0.394|72 K|[DLinear.yaml](../../paddlex/configs/ts_forecast/DLinear.yaml)|
+|NLinear|0.386|0.392|40 K |[NLinear.yaml](../../paddlex/configs/ts_forecast/NLinear.yaml)|
+|Nonstationary|0.600|0.515|55.5 M|[Nonstationary.yaml](../../paddlex/configs/ts_forecast/Nonstationary.yaml)|
+|PatchTST|0.385|0.397|2.0 M |[PatchTST.yaml](../../paddlex/configs/ts_forecast/PatchTST.yaml)|
+|RLinear|0.384|0.392|40 K|[RLinear.yaml](../../paddlex/configs/ts_forecast/RLinear.yaml)|
+|TiDE|0.405|0.412|31.7 M|[TiDE.yaml](../../paddlex/configs/ts_forecast/TiDE.yaml)|
+|TimesNet|0.417|0.431|4.9 M|[TimesNet.yaml](../../paddlex/configs/ts_forecast/TimesNet.yaml)|
 
 **注：以上精度指标测量自 **[ETTH1](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Etth1.tar)** 数据集 ****（在测试集test.csv上的评测结果）****。**
 
-## 时序异常检测模块
-|模型名称|precison|recall|f1_score|模型存储大小|
-|-|-|-|-|-|
-|AutoEncoder_ad|99.36|84.36|91.25|52 K |
-|DLinear_ad|98.98|93.96|96.41|112 K|
-|Nonstationary_ad|98.55|88.95|93.51|1.8 M |
-|PatchTST_ad|98.78|90.70|94.57|320 K |
-|TimesNet_ad|98.37|94.80|96.56|1.3 M |
+## [时序异常检测模块](../module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md)
+|模型名称|precison|recall|f1_score|模型存储大小|yaml 文件|
+|-|-|-|-|-|-|
+|AutoEncoder_ad|99.36|84.36|91.25|52 K |[AutoEncoder_ad.yaml](../../paddlex/configs/ts_anomaly_detection/AutoEncoder_ad.yaml)|
+|DLinear_ad|98.98|93.96|96.41|112 K|[DLinear_ad.yaml](../../paddlex/configs/ts_anomaly_detection/DLinear_ad.yaml)|
+|Nonstationary_ad|98.55|88.95|93.51|1.8 M |[Nonstationary_ad.yaml](../../paddlex/configs/ts_anomaly_detection/Nonstationary_ad.yaml)|
+|PatchTST_ad|98.78|90.70|94.57|320 K |[PatchTST_ad.yaml](../../paddlex/configs/ts_anomaly_detection/PatchTST_ad.yaml)|
+|TimesNet_ad|98.37|94.80|96.56|1.3 M |[TimesNet_ad.yaml](../../paddlex/configs/ts_anomaly_detection/TimesNet_ad.yaml)|
 
 **注：以上精度指标测量自 **[PSM](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ts_anomaly_examples.tar)** 数据集。**
 
-## 时序分类模块
-|模型名称|acc(%)|模型存储大小|
-|-|-|-|
-|TimesNet_cls|87.5|792 K|
+## [时序分类模块](../module_usage/tutorials/time_series_modules/time_series_classification.md)
+|模型名称|acc(%)|模型存储大小|yaml 文件|
+|-|-|-|-|
+|TimesNet_cls|87.5|792 K|[TimesNet_cls.yaml](../../paddlex/configs/ts_classification/TimesNet_cls.yaml)|
 
 **注：以上精度指标测量自 [UWaveGestureLibrary](https://paddlets.bj.bcebos.com/classification/UWaveGestureLibrary_TEST.csv)数据集。**
 
->**注：以上所有模型 GPU 推理耗时基于 NVIDIA Tesla T4 机器，精度类型为 FP32， CPU 推理速度基于 Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz，线程数为8，精度类型为 FP32。**
+>**注：以上所有模型 GPU 推理耗时基于 NVIDIA Tesla T4 机器，精度类型为 FP32， CPU 推理速度基于 Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz，线程数为8，精度类型为 FP32。**

docs/support_list/models_list_en.md

@@ -4,374 +4,374 @@
 
 PaddleX incorporates multiple pipelines, each containing several modules, and each module includes various models. You can choose which models to use based on the benchmark data below. If you prioritize model accuracy, select models with higher accuracy. If you prioritize inference speed, choose models with faster inference. If you prioritize model storage size, select models with smaller storage sizes.
 
-## Image Classification Module
-| Model Name | Top-1 Acc (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |
-|-|-|-|-|-|
-|CLIP_vit_base_patch16_224|85.36|13.1957|285.493|306.5 M|
-|CLIP_vit_large_patch14_224|88.1|51.1284|1131.28|1.04 G|
-|ConvNeXt_base_224|83.84|12.8473|1513.87|313.9 M|
-|ConvNeXt_base_384|84.90|31.7607|3967.05|313.9 M|
-|ConvNeXt_large_224|84.26|26.8103|2463.56|700.7 M|
-|ConvNeXt_large_384|85.27|66.4058|6598.92|700.7 M|
-|ConvNeXt_small|83.13|9.74075|1127.6|178.0 M|
-|ConvNeXt_tiny|82.03|5.48923|672.559|101.4 M|
-|FasterNet-L|83.5|23.4415|-|357.1 M|
-|FasterNet-M|83.0|21.8936|-|204.6 M|
-|FasterNet-S|81.3|13.0409|-|119.3 M|
-|FasterNet-T0|71.9|12.2432|-|15.1 M|
-|FasterNet-T1|75.9|11.3562|-|29.2 M|
-|FasterNet-T2|79.1|10.703|-|57.4 M|
-|MobileNetV1_x0_5|63.5|1.86754|7.48297|4.8 M|
-|MobileNetV1_x0_25|51.4|1.83478|4.83674|1.8 M|
-|MobileNetV1_x0_75|68.8|2.57903|10.6343|9.3 M|
-|MobileNetV1_x1_0|71.0|2.78781|13.98|15.2 M|
-|MobileNetV2_x0_5|65.0|4.94234|11.1629|7.1 M|
-|MobileNetV2_x0_25|53.2|4.50856|9.40991|5.5 M|
-|MobileNetV2_x1_0|72.2|6.12159|16.0442|12.6 M|
-|MobileNetV2_x1_5|74.1|6.28385|22.5129|25.0 M|
-|MobileNetV2_x2_0|75.2|6.12888|30.8612|41.2 M|
-|MobileNetV3_large_x0_5|69.2|6.31302|14.5588|9.6 M|
-|MobileNetV3_large_x0_35|64.3|5.76207|13.9041|7.5 M|
-|MobileNetV3_large_x0_75|73.1|8.41737|16.9506|14.0 M|
-|MobileNetV3_large_x1_0|75.3|8.64112|19.1614|19.5 M|
-|MobileNetV3_large_x1_25|76.4|8.73358|22.1296|26.5 M|
-|MobileNetV3_small_x0_5|59.2|5.16721|11.2688|6.8 M|
-|MobileNetV3_small_x0_35|53.0|5.22053|11.0055|6.0 M|
-|MobileNetV3_small_x0_75|66.0|5.39831|12.8313|8.5 M|
-|MobileNetV3_small_x1_0|68.2|6.00993|12.9598|10.5 M|
-|MobileNetV3_small_x1_25|70.7|6.9589|14.3995|13.0 M|
-|MobileNetV4_conv_large|83.4|12.5485|51.6453|125.2 M|
-|MobileNetV4_conv_medium|79.9|9.65509|26.6157|37.6 M|
-|MobileNetV4_conv_small|74.6|5.24172|11.0893|14.7 M|
-|MobileNetV4_hybrid_large|83.8|20.0726|213.769|145.1 M|
-|MobileNetV4_hybrid_medium|80.5|19.7543|62.2624|42.9 M|
-|PP-HGNet_base|85.0|14.2969|327.114|249.4 M|
-|PP-HGNet_small|81.51|5.50661|119.041|86.5 M|
-|PP-HGNet_tiny|79.83|5.22006|69.396|52.4 M|
-|PP-HGNetV2-B0|77.77|6.53694|23.352|21.4 M|
-|PP-HGNetV2-B1|79.18|6.56034|27.3099|22.6 M|
-|PP-HGNetV2-B2|81.74|9.60494|43.1219|39.9 M|
-|PP-HGNetV2-B3|82.98|11.0042|55.1367|57.9 M|
-|PP-HGNetV2-B4|83.57|9.66407|54.2462|70.4 M|
-|PP-HGNetV2-B5|84.75|15.7091|115.926|140.8 M|
-|PP-HGNetV2-B6|86.30|21.226|255.279|268.4 M|
-|PP-LCNet_x0_5|63.14|3.67722|6.66857|6.7 M|
-|PP-LCNet_x0_25|51.86|2.65341|5.81357|5.5 M|
-|PP-LCNet_x0_35|58.09|2.7212|6.28944|5.9 M|
-|PP-LCNet_x0_75|68.18|3.91032|8.06953|8.4 M|
-|PP-LCNet_x1_0|71.32|3.84845|9.23735|10.5 M|
-|PP-LCNet_x1_5|73.71|3.97666|12.3457|16.0 M|
-|PP-LCNet_x2_0|75.18|4.07556|16.2752|23.2 M|
-|PP-LCNet_x2_5|76.60|4.06028|21.5063|32.1 M|
-|PP-LCNetV2_base|77.05|5.23428|19.6005|23.7 M|
-|PP-LCNetV2_large |78.51|6.78335|30.4378|37.3 M|
-|PP-LCNetV2_small|73.97|3.89762|13.0273|14.6 M|
-|ResNet18_vd|72.3|3.53048|31.3014|41.5 M|
-|ResNet18|71.0|2.4868|27.4601|41.5 M|
-|ResNet34_vd|76.0|5.60675|56.0653|77.3 M|
-|ResNet34|74.6|4.16902|51.925|77.3 M|
-|ResNet50_vd|79.1|10.1885|68.446|90.8 M|
-|ResNet50|76.5|9.62383|64.8135|90.8 M|
-|ResNet101_vd|80.2|20.0563|124.85|158.4 M|
-|ResNet101|77.6|19.2297|121.006|158.7 M|
-|ResNet152_vd|80.6|29.6439|181.678|214.3 M|
-|ResNet152|78.3|30.0461|177.707|214.2 M|
-|ResNet200_vd|80.9|39.1628|235.185|266.0 M|
-|StarNet-S1|73.6|9.895|23.0465|11.2 M|
-|StarNet-S2|74.8|7.91279|21.9571|14.3 M|
-|StarNet-S3|77.0|10.7531|30.7656|22.2 M|
-|StarNet-S4|79.0|15.2868|43.2497|28.9 M|
-|SwinTransformer_base_patch4_window7_224|83.37|16.9848|383.83|310.5 M|
-|SwinTransformer_base_patch4_window12_384|84.17|37.2855|1178.63|311.4 M|
-|SwinTransformer_large_patch4_window7_224|86.19|27.5498|689.729|694.8 M|
-|SwinTransformer_large_patch4_window12_384|87.06|74.1768|2105.22|696.1 M|
-|SwinTransformer_small_patch4_window7_224|83.21|16.3982|285.56|175.6 M|
-|SwinTransformer_tiny_patch4_window7_224|81.10|8.54846|156.306|100.1 M|
+## [Image Classification Module](../module_usage/tutorials/cv_modules/image_classification_en.md)
+| Model Name | Top-1 Acc (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |YAML File|
+|-|-|-|-|-|-|
+|CLIP_vit_base_patch16_224|85.36|13.1957|285.493|306.5 M|[CLIP_vit_base_patch16_224.yaml](../../paddlex/configs/image_classification/CLIP_vit_base_patch16_224.yaml)|
+|CLIP_vit_large_patch14_224|88.1|51.1284|1131.28|1.04 G|[CLIP_vit_large_patch14_224.yaml](../../paddlex/configs/image_classification/CLIP_vit_large_patch14_224.yaml)|
+|ConvNeXt_base_224|83.84|12.8473|1513.87|313.9 M|[ConvNeXt_base_224.yaml](../../paddlex/configs/image_classification/ConvNeXt_base_224.yaml)|
+|ConvNeXt_base_384|84.90|31.7607|3967.05|313.9 M|[ConvNeXt_base_384.yaml](../../paddlex/configs/image_classification/ConvNeXt_base_384.yaml)|
+|ConvNeXt_large_224|84.26|26.8103|2463.56|700.7 M|[ConvNeXt_large_224.yaml](../../paddlex/configs/image_classification/ConvNeXt_large_224.yaml)|
+|ConvNeXt_large_384|85.27|66.4058|6598.92|700.7 M|[ConvNeXt_large_384.yaml](../../paddlex/configs/image_classification/ConvNeXt_large_384.yaml)|
+|ConvNeXt_small|83.13|9.74075|1127.6|178.0 M|[ConvNeXt_small.yaml](../../paddlex/configs/image_classification/ConvNeXt_small.yaml)|
+|ConvNeXt_tiny|82.03|5.48923|672.559|101.4 M|[ConvNeXt_tiny.yaml](../../paddlex/configs/image_classification/ConvNeXt_tiny.yaml)|
+|FasterNet-L|83.5|23.4415|-|357.1 M|[FasterNet-L.yaml](../../paddlex/configs/image_classification/FasterNet-L.yaml)|
+|FasterNet-M|83.0|21.8936|-|204.6 M|[FasterNet-M.yaml](../../paddlex/configs/image_classification/FasterNet-M.yaml)|
+|FasterNet-S|81.3|13.0409|-|119.3 M|[FasterNet-S.yaml](../../paddlex/configs/image_classification/FasterNet-S.yaml)|
+|FasterNet-T0|71.9|12.2432|-|15.1 M|[FasterNet-T0.yaml](../../paddlex/configs/image_classification/FasterNet-T0.yaml)|
+|FasterNet-T1|75.9|11.3562|-|29.2 M|[FasterNet-T1.yaml](../../paddlex/configs/image_classification/FasterNet-T1.yaml)|
+|FasterNet-T2|79.1|10.703|-|57.4 M|[FasterNet-T2.yaml](../../paddlex/configs/image_classification/FasterNet-T2.yaml)|
+|MobileNetV1_x0_5|63.5|1.86754|7.48297|4.8 M|[MobileNetV1_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV1_x0_5.yaml)|
+|MobileNetV1_x0_25|51.4|1.83478|4.83674|1.8 M|[MobileNetV1_x0_25.yaml](../../paddlex/configs/image_classification/MobileNetV1_x0_25.yaml)|
+|MobileNetV1_x0_75|68.8|2.57903|10.6343|9.3 M|[MobileNetV1_x0_75.yaml](../../paddlex/configs/image_classification/MobileNetV1_x0_75.yaml)|
+|MobileNetV1_x1_0|71.0|2.78781|13.98|15.2 M|[MobileNetV1_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV1_x1_0.yaml)|
+|MobileNetV2_x0_5|65.0|4.94234|11.1629|7.1 M|[MobileNetV2_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV2_x0_5.yaml)|
+|MobileNetV2_x0_25|53.2|4.50856|9.40991|5.5 M|[MobileNetV2_x0_25.yaml](../../paddlex/configs/image_classification/MobileNetV2_x0_25.yaml)|
+|MobileNetV2_x1_0|72.2|6.12159|16.0442|12.6 M|[MobileNetV2_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV2_x1_0.yaml)|
+|MobileNetV2_x1_5|74.1|6.28385|22.5129|25.0 M|[MobileNetV2_x1_5.yaml](../../paddlex/configs/image_classification/MobileNetV2_x1_5.yaml)|
+|MobileNetV2_x2_0|75.2|6.12888|30.8612|41.2 M|[MobileNetV2_x2_0.yaml](../../paddlex/configs/image_classification/MobileNetV2_x2_0.yaml)|
+|MobileNetV3_large_x0_5|69.2|6.31302|14.5588|9.6 M|[MobileNetV3_large_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x0_5.yaml)|
+|MobileNetV3_large_x0_35|64.3|5.76207|13.9041|7.5 M|[MobileNetV3_large_x0_35.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x0_35.yaml)|
+|MobileNetV3_large_x0_75|73.1|8.41737|16.9506|14.0 M|[MobileNetV3_large_x0_75.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x0_75.yaml)|
+|MobileNetV3_large_x1_0|75.3|8.64112|19.1614|19.5 M|[MobileNetV3_large_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x1_0.yaml)|
+|MobileNetV3_large_x1_25|76.4|8.73358|22.1296|26.5 M|[MobileNetV3_large_x1_25.yaml](../../paddlex/configs/image_classification/MobileNetV3_large_x1_25.yaml)|
+|MobileNetV3_small_x0_5|59.2|5.16721|11.2688|6.8 M|[MobileNetV3_small_x0_5.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x0_5.yaml)|
+|MobileNetV3_small_x0_35|53.0|5.22053|11.0055|6.0 M|[MobileNetV3_small_x0_35.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x0_35.yaml)|
+|MobileNetV3_small_x0_75|66.0|5.39831|12.8313|8.5 M|[MobileNetV3_small_x0_75.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x0_75.yaml)|
+|MobileNetV3_small_x1_0|68.2|6.00993|12.9598|10.5 M|[MobileNetV3_small_x1_0.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x1_0.yaml)|
+|MobileNetV3_small_x1_25|70.7|6.9589|14.3995|13.0 M|[MobileNetV3_small_x1_25.yaml](../../paddlex/configs/image_classification/MobileNetV3_small_x1_25.yaml)|
+|MobileNetV4_conv_large|83.4|12.5485|51.6453|125.2 M|[MobileNetV4_conv_large.yaml](../../paddlex/configs/image_classification/MobileNetV4_conv_large.yaml)|
+|MobileNetV4_conv_medium|79.9|9.65509|26.6157|37.6 M|[MobileNetV4_conv_medium.yaml](../../paddlex/configs/image_classification/MobileNetV4_conv_medium.yaml)|
+|MobileNetV4_conv_small|74.6|5.24172|11.0893|14.7 M|[MobileNetV4_conv_small.yaml](../../paddlex/configs/image_classification/MobileNetV4_conv_small.yaml)|
+|MobileNetV4_hybrid_large|83.8|20.0726|213.769|145.1 M|[MobileNetV4_hybrid_large.yaml](../../paddlex/configs/image_classification/MobileNetV4_hybrid_large.yaml)|
+|MobileNetV4_hybrid_medium|80.5|19.7543|62.2624|42.9 M|[MobileNetV4_hybrid_medium.yaml](../../paddlex/configs/image_classification/MobileNetV4_hybrid_medium.yaml)|
+|PP-HGNet_base|85.0|14.2969|327.114|249.4 M|[PP-HGNet_base.yaml](../../paddlex/configs/image_classification/PP-HGNet_base.yaml)|
+|PP-HGNet_small|81.51|5.50661|119.041|86.5 M|[PP-HGNet_small.yaml](../../paddlex/configs/image_classification/PP-HGNet_small.yaml)|
+|PP-HGNet_tiny|79.83|5.22006|69.396|52.4 M|[PP-HGNet_tiny.yaml](../../paddlex/configs/image_classification/PP-HGNet_tiny.yaml)|
+|PP-HGNetV2-B0|77.77|6.53694|23.352|21.4 M|[PP-HGNetV2-B0.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B0.yaml)|
+|PP-HGNetV2-B1|79.18|6.56034|27.3099|22.6 M|[PP-HGNetV2-B1.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B1.yaml)|
+|PP-HGNetV2-B2|81.74|9.60494|43.1219|39.9 M|[PP-HGNetV2-B2.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B2.yaml)|
+|PP-HGNetV2-B3|82.98|11.0042|55.1367|57.9 M|[PP-HGNetV2-B3.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B3.yaml)|
+|PP-HGNetV2-B4|83.57|9.66407|54.2462|70.4 M|[PP-HGNetV2-B4.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B4.yaml)|
+|PP-HGNetV2-B5|84.75|15.7091|115.926|140.8 M|[PP-HGNetV2-B5.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B5.yaml)|
+|PP-HGNetV2-B6|86.30|21.226|255.279|268.4 M|[PP-HGNetV2-B6.yaml](../../paddlex/configs/image_classification/PP-HGNetV2-B6.yaml)|
+|PP-LCNet_x0_5|63.14|3.67722|6.66857|6.7 M|[PP-LCNet_x0_5.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_5.yaml)|
+|PP-LCNet_x0_25|51.86|2.65341|5.81357|5.5 M|[PP-LCNet_x0_25.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_25.yaml)|
+|PP-LCNet_x0_35|58.09|2.7212|6.28944|5.9 M|[PP-LCNet_x0_35.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_35.yaml)|
+|PP-LCNet_x0_75|68.18|3.91032|8.06953|8.4 M|[PP-LCNet_x0_75.yaml](../../paddlex/configs/image_classification/PP-LCNet_x0_75.yaml)|
+|PP-LCNet_x1_0|71.32|3.84845|9.23735|10.5 M|[PP-LCNet_x1_0.yaml](../../paddlex/configs/image_classification/PP-LCNet_x1_0.yaml)|
+|PP-LCNet_x1_5|73.71|3.97666|12.3457|16.0 M|[PP-LCNet_x1_5.yaml](../../paddlex/configs/image_classification/PP-LCNet_x1_5.yaml)|
+|PP-LCNet_x2_0|75.18|4.07556|16.2752|23.2 M|[PP-LCNet_x2_0.yaml](../../paddlex/configs/image_classification/PP-LCNet_x2_0.yaml)|
+|PP-LCNet_x2_5|76.60|4.06028|21.5063|32.1 M|[PP-LCNet_x2_5.yaml](../../paddlex/configs/image_classification/PP-LCNet_x2_5.yaml)|
+|PP-LCNetV2_base|77.05|5.23428|19.6005|23.7 M|[PP-LCNetV2_base.yaml](../../paddlex/configs/image_classification/PP-LCNetV2_base.yaml)|
+|PP-LCNetV2_large |78.51|6.78335|30.4378|37.3 M|[PP-LCNetV2_large.yaml](../../paddlex/configs/image_classification/PP-LCNetV2_large.yaml)|
+|PP-LCNetV2_small|73.97|3.89762|13.0273|14.6 M|[PP-LCNetV2_small.yaml](../../paddlex/configs/image_classification/PP-LCNetV2_small.yaml)|
+|ResNet18_vd|72.3|3.53048|31.3014|41.5 M|[ResNet18_vd.yaml](../../paddlex/configs/image_classification/ResNet18_vd.yaml)|
+|ResNet18|71.0|2.4868|27.4601|41.5 M|[ResNet18.yaml](../../paddlex/configs/image_classification/ResNet18.yaml)|
+|ResNet34_vd|76.0|5.60675|56.0653|77.3 M|[ResNet34_vd.yaml](../../paddlex/configs/image_classification/ResNet34_vd.yaml)|
+|ResNet34|74.6|4.16902|51.925|77.3 M|[ResNet34.yaml](../../paddlex/configs/image_classification/ResNet34.yaml)|
+|ResNet50_vd|79.1|10.1885|68.446|90.8 M|[ResNet50_vd.yaml](../../paddlex/configs/image_classification/ResNet50_vd.yaml)|
+|ResNet50|76.5|9.62383|64.8135|90.8 M|[ResNet50.yaml](../../paddlex/configs/image_classification/ResNet50.yaml)|
+|ResNet101_vd|80.2|20.0563|124.85|158.4 M|[ResNet101_vd.yaml](../../paddlex/configs/image_classification/ResNet101_vd.yaml)|
+|ResNet101|77.6|19.2297|121.006|158.7 M|[ResNet101.yaml](../../paddlex/configs/image_classification/ResNet101.yaml)|
+|ResNet152_vd|80.6|29.6439|181.678|214.3 M|[ResNet152_vd.yaml](../../paddlex/configs/image_classification/ResNet152_vd.yaml)|
+|ResNet152|78.3|30.0461|177.707|214.2 M|[ResNet152.yaml](../../paddlex/configs/image_classification/ResNet152.yaml)|
+|ResNet200_vd|80.9|39.1628|235.185|266.0 M|[ResNet200_vd.yaml](../../paddlex/configs/image_classification/ResNet200_vd.yaml)|
+|StarNet-S1|73.6|9.895|23.0465|11.2 M|[StarNet-S1.yaml](../../paddlex/configs/image_classification/StarNet-S1.yaml)|
+|StarNet-S2|74.8|7.91279|21.9571|14.3 M|[StarNet-S2.yaml](../../paddlex/configs/image_classification/StarNet-S2.yaml)|
+|StarNet-S3|77.0|10.7531|30.7656|22.2 M|[StarNet-S3.yaml](../../paddlex/configs/image_classification/StarNet-S3.yaml)|
+|StarNet-S4|79.0|15.2868|43.2497|28.9 M|[StarNet-S4.yaml](../../paddlex/configs/image_classification/StarNet-S4.yaml)|
+|SwinTransformer_base_patch4_window7_224|83.37|16.9848|383.83|310.5 M|[SwinTransformer_base_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_base_patch4_window7_224.yaml)|
+|SwinTransformer_base_patch4_window12_384|84.17|37.2855|1178.63|311.4 M|[SwinTransformer_base_patch4_window12_384.yaml](../../paddlex/configs/image_classification/SwinTransformer_base_patch4_window12_384.yaml)|
+|SwinTransformer_large_patch4_window7_224|86.19|27.5498|689.729|694.8 M|[SwinTransformer_large_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_large_patch4_window7_224.yaml)|
+|SwinTransformer_large_patch4_window12_384|87.06|74.1768|2105.22|696.1 M|[SwinTransformer_large_patch4_window12_384.yaml](../../paddlex/configs/image_classification/SwinTransformer_large_patch4_window12_384.yaml)|
+|SwinTransformer_small_patch4_window7_224|83.21|16.3982|285.56|175.6 M|[SwinTransformer_small_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_small_patch4_window7_224.yaml)|
+|SwinTransformer_tiny_patch4_window7_224|81.10|8.54846|156.306|100.1 M|[SwinTransformer_tiny_patch4_window7_224.yaml](../../paddlex/configs/image_classification/SwinTransformer_tiny_patch4_window7_224.yaml)|
 
 **Note: The above accuracy metrics are Top-1 Acc on the [ImageNet-1k](https://www.image-net.org/index.php) validation set.**
 
-## Image Multi-Label Classification Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |
-|-|-|-|-|-|
-|CLIP_vit_base_patch16_448_ML|89.15|-|-|325.6 M|
-|PP-HGNetV2-B0_ML|80.98|-|-|39.6 M|
-|PP-HGNetV2-B4_ML|87.96|-|-|88.5 M|
-|PP-HGNetV2-B6_ML|91.25|-|-|286.5 M|
-|PP-LCNet_x1_0_ML|77.96|-|-|29.4 M|
-|ResNet50_ML|83.50|-|-|108.9 M|
+## [Image Multi-Label Classification Module](../module_usage/tutorials/cv_modules/ml_classification_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |YAML File|
+|-|-|-|-|-|-|
+|CLIP_vit_base_patch16_448_ML|89.15|-|-|325.6 M|[CLIP_vit_base_patch16_448_ML.yaml](../../paddlex/configs/multilabel_classification/CLIP_vit_base_patch16_448_ML.yaml)|
+|PP-HGNetV2-B0_ML|80.98|-|-|39.6 M|[PP-HGNetV2-B0_ML.yaml](../../paddlex/configs/multilabel_classification/PP-HGNetV2-B0_ML.yaml)|
+|PP-HGNetV2-B4_ML|87.96|-|-|88.5 M|[PP-HGNetV2-B4_ML.yaml](../../paddlex/configs/multilabel_classification/PP-HGNetV2-B4_ML.yaml)|
+|PP-HGNetV2-B6_ML|91.25|-|-|286.5 M|[PP-HGNetV2-B6_ML.yaml](../../paddlex/configs/multilabel_classification/PP-HGNetV2-B6_ML.yaml)|
+|PP-LCNet_x1_0_ML|77.96|-|-|29.4 M|[PP-LCNet_x1_0_ML.yaml](../../paddlex/configs/multilabel_classification/PP-LCNet_x1_0_ML.yaml)|
+|ResNet50_ML|83.50|-|-|108.9 M|[ResNet50_ML.yaml](../../paddlex/configs/multilabel_classification/ResNet50_ML.yaml)|
 
 **Note: The above accuracy metrics are mAP for the multi-label classification task on [COCO2017](https://cocodataset.org/#home).**
 
-## Pedestrian Attribute Module
-| Model Name | mA (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size  |
-|-|-|-|-|-|
-|PP-LCNet_x1_0_pedestrian_attribute|92.2|3.84845|9.23735|6.7 M  |
+## [Pedestrian Attribute Module](../module_usage/tutorials/cv_modules/pedestrian_attribute_recognition_en.md)
+| Model Name | mA (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size  |YAML File|
+|-|-|-|-|-|-|
+|PP-LCNet_x1_0_pedestrian_attribute|92.2|3.84845|9.23735|6.7 M  |[PP-LCNet_x1_0_pedestrian_attribute.yaml](../../paddlex/configs/pedestrian_attribute/PP-LCNet_x1_0_pedestrian_attribute.yaml)|
 
 **Note: The above accuracy metrics are mA on PaddleX's internal self-built dataset.**
 
-## Vehicle Attribute Module
-| Model Name | mA (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |
-|-|-|-|-|-|
-|PP-LCNet_x1_0_vehicle_attribute|91.7|3.84845|9.23735|6.7 M|
+## [Vehicle Attribute Module](../module_usage/tutorials/cv_modules/vehicle_attribute_recognition_en.md)
+| Model Name | mA (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-LCNet_x1_0_vehicle_attribute|91.7|3.84845|9.23735|6.7 M|[PP-LCNet_x1_0_vehicle_attribute.yaml](../../paddlex/configs/vehicle_attribute/PP-LCNet_x1_0_vehicle_attribute.yaml)|
 
 **Note: The above accuracy metrics are mA on the VeRi dataset.**
 
-## Image Feature Module
-| Model Name | recall@1 (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |
-|-|-|-|-|-|
-|PP-ShiTuV2_rec|84.2|5.23428|19.6005|16.3 M|
-|PP-ShiTuV2_rec_CLIP_vit_base|88.69|13.1957|285.493|306.6 M|
-|PP-ShiTuV2_rec_CLIP_vit_large|91.03|51.1284|1131.28|1.05 G|
+## [Image Feature Module](../module_usage/tutorials/cv_modules/image_feature_en.md)
+| Model Name | recall@1 (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-ShiTuV2_rec|84.2|5.23428|19.6005|16.3 M|[PP-ShiTuV2_rec.yaml](../../paddlex/configs/general_recognition/PP-ShiTuV2_rec.yaml)|
+|PP-ShiTuV2_rec_CLIP_vit_base|88.69|13.1957|285.493|306.6 M|[PP-ShiTuV2_rec_CLIP_vit_base.yaml](../../paddlex/configs/general_recognition/PP-ShiTuV2_rec_CLIP_vit_base.yaml)|
+|PP-ShiTuV2_rec_CLIP_vit_large|91.03|51.1284|1131.28|1.05 G|[PP-ShiTuV2_rec_CLIP_vit_large.yaml](../../paddlex/configs/general_recognition/PP-ShiTuV2_rec_CLIP_vit_large.yaml)|
 
 **Note: The above accuracy metrics are recall@1 on AliProducts.**
 
 
-## Document Orientation Classification Module
-| Model Name | Top-1 Acc (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |
-|-|-|-|-|-|
-|PP-LCNet_x1_0_doc_ori|99.26|3.84845|9.23735|7.1 M|
+## [Document Orientation Classification Module](../module_usage/tutorials/ocr_modules/doc_img_orientation_classification_en.md)
+| Model Name | Top-1 Acc (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-LCNet_x1_0_doc_ori|99.26|3.84845|9.23735|7.1 M|[PP-LCNet_x1_0_doc_ori.yaml](../../paddlex/configs/doc_text_orientation/PP-LCNet_x1_0_doc_ori.yaml)|
 
 **Note: The above accuracy metrics are Top-1 Acc on PaddleX's internal self-built dataset.**
 
-## Main Body Detection Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size|
-|-|-|-|-|-|
-|PP-ShiTuV2_det|41.5|33.7426|537.003|27.6 M|
+## [Main Body Detection Module](../module_usage/tutorials/cv_modules/mainbody_detection_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size|YAML File|
+|-|-|-|-|-|-|
+|PP-ShiTuV2_det|41.5|33.7426|537.003|27.6 M|[PP-ShiTuV2_det.yaml](../../paddlex/configs/mainbody_detection/PP-ShiTuV2_det.yaml)|
 
 **Note: The above accuracy metrics are mAP(0.5:0.95) on the [PaddleClas main body detection dataset](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.5/docs/en/training/PP-ShiTu/mainbody_detection.md).**
 
-## Object Detection Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |
-|-|-|-|-|-|
-|Cascade-FasterRCNN-ResNet50-FPN|41.1|-|-|245.4 M|
-|Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN|45.0|-|-|246.2 M|
-|CenterNet-DLA-34|37.6|-|-|75.4 M|
-|CenterNet-ResNet50|38.9|-|-|319.7 M|
-|DETR-R50|42.3|59.2132|5334.52|159.3 M|
-|FasterRCNN-ResNet34-FPN|37.8|-|-|137.5 M|
-|FasterRCNN-ResNet50-FPN|38.4|-|-|148.1 M|
-|FasterRCNN-ResNet50-vd-FPN|39.5|-|-|148.1 M|
-|FasterRCNN-ResNet50-vd-SSLDv2-FPN|41.4|-|-|148.1 M|
-|FasterRCNN-ResNet50|36.7|-|-|120.2 M|
-|FasterRCNN-ResNet101-FPN|41.4|-|-|216.3 M|
-|FasterRCNN-ResNet101|39.0|-|-|188.1 M|
-|FasterRCNN-ResNeXt101-vd-FPN|43.4|-|-|360.6 M|
-|FasterRCNN-Swin-Tiny-FPN|42.6|-|-|159.8 M|
-|FCOS-ResNet50|39.6|103.367|3424.91|124.2 M|
-|PicoDet-L|42.6|16.6715|169.904|20.9 M|
-|PicoDet-M|37.5|16.2311|71.7257|16.8 M|
-|PicoDet-S|29.1|14.097|37.6563|4.4 M |
-|PicoDet-XS|26.2|13.8102|48.3139|5.7M |
-|PP-YOLOE_plus-L|52.9|33.5644|814.825|185.3 M|
-|PP-YOLOE_plus-M|49.8|19.843|449.261|83.2 M|
-|PP-YOLOE_plus-S|43.7|16.8884|223.059|28.3 M|
-|PP-YOLOE_plus-X|54.7|57.8995|1439.93|349.4 M|
-|RT-DETR-H|56.3|114.814|3933.39|435.8 M|
-|RT-DETR-L|53.0|34.5252|1454.27|113.7 M|
-|RT-DETR-R18|46.5|19.89|784.824|70.7 M|
-|RT-DETR-R50|53.1|41.9327|1625.95|149.1 M|
-|RT-DETR-X|54.8|61.8042|2246.64|232.9 M|
-|YOLOv3-DarkNet53|39.1|40.1055|883.041|219.7 M|
-|YOLOv3-MobileNetV3|31.4|18.6692|267.214|83.8 M|
-|YOLOv3-ResNet50_vd_DCN|40.6|31.6276|856.047|163.0 M|
-|YOLOX-L|50.1|185.691|1250.58|192.5 M|
-|YOLOX-M|46.9|123.324|688.071|90.0 M|
-|YOLOX-N|26.1|79.1665|155.59|3.4 M|
-|YOLOX-S|40.4|184.828|474.446|32.0 M|
-|YOLOX-T|32.9|102.748|212.52|18.1 M|
-|YOLOX-X|51.8|227.361|2067.84|351.5 M|
+## [Object Detection Module](../module_usage/tutorials/cv_modules/object_detection_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size |YAML File|
+|-|-|-|-|-|-|
+|Cascade-FasterRCNN-ResNet50-FPN|41.1|-|-|245.4 M|[Cascade-FasterRCNN-ResNet50-FPN.yaml](../../paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-FPN.yaml)|
+|Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN|45.0|-|-|246.2 M|[Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|CenterNet-DLA-34|37.6|-|-|75.4 M|[CenterNet-DLA-34.yaml](../../paddlex/configs/object_detection/CenterNet-DLA-34.yaml)|
+|CenterNet-ResNet50|38.9|-|-|319.7 M|[CenterNet-ResNet50.yaml](../../paddlex/configs/object_detection/CenterNet-ResNet50.yaml)|
+|DETR-R50|42.3|59.2132|5334.52|159.3 M|[DETR-R50.yaml](../../paddlex/configs/object_detection/DETR-R50.yaml)|
+|FasterRCNN-ResNet34-FPN|37.8|-|-|137.5 M|[FasterRCNN-ResNet34-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet34-FPN.yaml)|
+|FasterRCNN-ResNet50-FPN|38.4|-|-|148.1 M|[FasterRCNN-ResNet50-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50-FPN.yaml)|
+|FasterRCNN-ResNet50-vd-FPN|39.5|-|-|148.1 M|[FasterRCNN-ResNet50-vd-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-FPN.yaml)|
+|FasterRCNN-ResNet50-vd-SSLDv2-FPN|41.4|-|-|148.1 M|[FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|FasterRCNN-ResNet50|36.7|-|-|120.2 M|[FasterRCNN-ResNet50.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet50.yaml)|
+|FasterRCNN-ResNet101-FPN|41.4|-|-|216.3 M|[FasterRCNN-ResNet101-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet101-FPN.yaml)|
+|FasterRCNN-ResNet101|39.0|-|-|188.1 M|[FasterRCNN-ResNet101.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNet101.yaml)|
+|FasterRCNN-ResNeXt101-vd-FPN|43.4|-|-|360.6 M|[FasterRCNN-ResNeXt101-vd-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-ResNeXt101-vd-FPN.yaml)|
+|FasterRCNN-Swin-Tiny-FPN|42.6|-|-|159.8 M|[FasterRCNN-Swin-Tiny-FPN.yaml](../../paddlex/configs/object_detection/FasterRCNN-Swin-Tiny-FPN.yaml)|
+|FCOS-ResNet50|39.6|103.367|3424.91|124.2 M|[FCOS-ResNet50.yaml](../../paddlex/configs/object_detection/FCOS-ResNet50.yaml)|
+|PicoDet-L|42.6|16.6715|169.904|20.9 M|[PicoDet-L.yaml](../../paddlex/configs/object_detection/PicoDet-L.yaml)|
+|PicoDet-M|37.5|16.2311|71.7257|16.8 M|[PicoDet-M.yaml](../../paddlex/configs/object_detection/PicoDet-M.yaml)|
+|PicoDet-S|29.1|14.097|37.6563|4.4 M |[PicoDet-S.yaml](../../paddlex/configs/object_detection/PicoDet-S.yaml)|
+|PicoDet-XS|26.2|13.8102|48.3139|5.7M |[PicoDet-XS.yaml](../../paddlex/configs/object_detection/PicoDet-XS.yaml)|
+|PP-YOLOE_plus-L|52.9|33.5644|814.825|185.3 M|[PP-YOLOE_plus-L.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-L.yaml)|
+|PP-YOLOE_plus-M|49.8|19.843|449.261|83.2 M|[PP-YOLOE_plus-M.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-M.yaml)|
+|PP-YOLOE_plus-S|43.7|16.8884|223.059|28.3 M|[PP-YOLOE_plus-S.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-S.yaml)|
+|PP-YOLOE_plus-X|54.7|57.8995|1439.93|349.4 M|[PP-YOLOE_plus-X.yaml](../../paddlex/configs/object_detection/PP-YOLOE_plus-X.yaml)|
+|RT-DETR-H|56.3|114.814|3933.39|435.8 M|[RT-DETR-H.yaml](../../paddlex/configs/object_detection/RT-DETR-H.yaml)|
+|RT-DETR-L|53.0|34.5252|1454.27|113.7 M|[RT-DETR-L.yaml](../../paddlex/configs/object_detection/RT-DETR-L.yaml)|
+|RT-DETR-R18|46.5|19.89|784.824|70.7 M|[RT-DETR-R18.yaml](../../paddlex/configs/object_detection/RT-DETR-R18.yaml)|
+|RT-DETR-R50|53.1|41.9327|1625.95|149.1 M|[RT-DETR-R50.yaml](../../paddlex/configs/object_detection/RT-DETR-R50.yaml)|
+|RT-DETR-X|54.8|61.8042|2246.64|232.9 M|[RT-DETR-X.yaml](../../paddlex/configs/object_detection/RT-DETR-X.yaml)|
+|YOLOv3-DarkNet53|39.1|40.1055|883.041|219.7 M|[YOLOv3-DarkNet53.yaml](../../paddlex/configs/object_detection/YOLOv3-DarkNet53.yaml)|
+|YOLOv3-MobileNetV3|31.4|18.6692|267.214|83.8 M|[YOLOv3-MobileNetV3.yaml](../../paddlex/configs/object_detection/YOLOv3-MobileNetV3.yaml)|
+|YOLOv3-ResNet50_vd_DCN|40.6|31.6276|856.047|163.0 M|[YOLOv3-ResNet50_vd_DCN.yaml](../../paddlex/configs/object_detection/YOLOv3-ResNet50_vd_DCN.yaml)|
+|YOLOX-L|50.1|185.691|1250.58|192.5 M|[YOLOX-L.yaml](../../paddlex/configs/object_detection/YOLOX-L.yaml)|
+|YOLOX-M|46.9|123.324|688.071|90.0 M|[YOLOX-M.yaml](../../paddlex/configs/object_detection/YOLOX-M.yaml)|
+|YOLOX-N|26.1|79.1665|155.59|3.4 M|[YOLOX-N.yaml](../../paddlex/configs/object_detection/YOLOX-N.yaml)|
+|YOLOX-S|40.4|184.828|474.446|32.0 M|[YOLOX-S.yaml](../../paddlex/configs/object_detection/YOLOX-S.yaml)|
+|YOLOX-T|32.9|102.748|212.52|18.1 M|[YOLOX-T.yaml](../../paddlex/configs/object_detection/YOLOX-T.yaml)|
+|YOLOX-X|51.8|227.361|2067.84|351.5 M|[YOLOX-X.yaml](../../paddlex/configs/object_detection/YOLOX-X.yaml)|
 
 **Note: The above accuracy metrics are mAP(0.5:0.95) on the [COCO2017](https://cocodataset.org/#home) validation set.**
 
-## Small Object Detection Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size  |
-|-|-|-|-|-|
-|PP-YOLOE_plus_SOD-S|25.1|65.4608|324.37|77.3 M|
-|PP-YOLOE_plus_SOD-L|31.9|57.1448|1006.98|325.0 M|
-|PP-YOLOE_plus_SOD-largesize-L|42.7|458.521|11172.7|340.5 M|
+## [Small Object Detection Module](../module_usage/tutorials/cv_modules/small_object_detection_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size  |YAML File|
+|-|-|-|-|-|-|
+|PP-YOLOE_plus_SOD-S|25.1|65.4608|324.37|77.3 M|[PP-YOLOE_plus_SOD-S.yaml](../../paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-S.yaml)|
+|PP-YOLOE_plus_SOD-L|31.9|57.1448|1006.98|325.0 M|[PP-YOLOE_plus_SOD-L.yaml](../../paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-L.yaml)|
+|PP-YOLOE_plus_SOD-largesize-L|42.7|458.521|11172.7|340.5 M|[PP-YOLOE_plus_SOD-largesize-L.yaml](../../paddlex/configs/small_object_detection/PP-YOLOE_plus_SOD-largesize-L.yaml)|
 
 **Note: The above accuracy metrics are mAP(0.5:0.95) on the [VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset) validation set.**
 
-## Pedestrian Detection Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |
-|-|-|-|-|-|
-|PP-YOLOE-L_human|48.0|32.7754|777.691|196.1 M|
-|PP-YOLOE-S_human|42.5|15.0118|179.317|28.8 M|
+## [Pedestrian Detection Module](../module_usage/tutorials/cv_modules/human_detection_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-YOLOE-L_human|48.0|32.7754|777.691|196.1 M|[PP-YOLOE-L_human.yaml](../../paddlex/configs/human_detection/PP-YOLOE-L_human.yaml)|
+|PP-YOLOE-S_human|42.5|15.0118|179.317|28.8 M|[PP-YOLOE-S_human.yaml](../../paddlex/configs/human_detection/PP-YOLOE-S_human.yaml)|
 
 **Note: The above accuracy metrics are mAP(0.5:0.95) on the [CrowdHuman](https://bj.bcebos.com/v1/paddledet/data/crowdhuman.zip) validation set.**
 
 
-## Vehicle Detection Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |
-|-|-|-|-|-|
-|PP-YOLOE-L_vehicle|63.9|32.5619|775.633|196.1 M|
-|PP-YOLOE-S_vehicle|61.3|15.3787|178.441|28.8 M|
+## [Vehicle Detection Module](../module_usage/tutorials/cv_modules/vehicle_detection_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms) | Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-YOLOE-L_vehicle|63.9|32.5619|775.633|196.1 M|[PP-YOLOE-L_vehicle.yaml](../../paddlex/configs/vehicle_detection/PP-YOLOE-L_vehicle.yaml)|
+|PP-YOLOE-S_vehicle|61.3|15.3787|178.441|28.8 M|[PP-YOLOE-S_vehicle.yaml](../../paddlex/configs/vehicle_detection/PP-YOLOE-S_vehicle.yaml)|
 
 **Note: The above accuracy metrics are mAP(0.5:0.95) on the [PPVehicle](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppvehicle) validation set.**
 
-## Face Detection Module
-| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size  |
-|-|-|-|-|-|
-|PicoDet_LCNet_x2_5_face|35.8|33.7426|537.003|27.7 M|
+## [Face Detection Module](../module_usage/tutorials/cv_modules/face_detection_en.md)
+| Model Name | mAP (%) | GPU Inference Time (ms) | CPU Inference Time (ms)  | Model Size  |YAML File|
+|-|-|-|-|-|-|
+|PicoDet_LCNet_x2_5_face|35.8|33.7426|537.003|27.7 M|[PicoDet_LCNet_x2_5_face.yaml](../../paddlex/configs/face_detection/PicoDet_LCNet_x2_5_face.yaml)|
 
 **Note: The above accuracy metrics are evaluated on the **[wider_face](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppvehicle)** dataset using mAP(0.5:0.95).**
 
 
-## Abnormality Detection Module
-|Model Name|Avg (%)|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size |
-|-|-|-|-|-|
-|STFPM|96.2|-|-|21.5 M|
+## [Abnormality Detection Module](../module_usage/tutorials/cv_modules/anomaly_detection_en.md)
+|Model Name|Avg (%)|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size |YAML File|
+|-|-|-|-|-|-|
+|STFPM|96.2|-|-|21.5 M|[STFPM.yaml](../../paddlex/configs/anomaly_detection/STFPM.yaml)|
 
 **Note: The above accuracy metrics are evaluated on the **[MVTec AD](https://www.mvtec.com/company/research/datasets/mvtec-ad)** dataset using the average anomaly score.**
 
-## Semantic Segmentation Module
-|Model Name|mIoU (%)|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size|
-|-|-|-|-|-|
-|Deeplabv3_Plus-R50 |80.36|61.0531|1513.58|94.9 M|
-|Deeplabv3_Plus-R101|81.10|100.026|2460.71|162.5 M|
-|Deeplabv3-R50|79.90|82.2631|1735.83|138.3 M|
-|Deeplabv3-R101|80.85|121.492|2685.51|205.9 M|
-|OCRNet_HRNet-W18|80.67|48.2335|906.385|43.1 M|
-|OCRNet_HRNet-W48|82.15|78.9976|2226.95|249.8 M|
-|PP-LiteSeg-T|73.10|7.6827|138.683|28.5 M|
-|PP-LiteSeg-B|75.25|-|-|47.0 M|
-|SegFormer-B0 (slice)|76.73|11.1946|268.929|13.2 M|
-|SegFormer-B1 (slice)|78.35|17.9998|403.393|48.5 M|
-|SegFormer-B2 (slice)|81.60|48.0371|1248.52|96.9 M|
-|SegFormer-B3 (slice)|82.47|64.341|1666.35|167.3 M|
-|SegFormer-B4 (slice)|82.38|82.4336|1995.42|226.7 M|
-|SegFormer-B5 (slice)|82.58|97.3717|2420.19|229.7 M|
+## [Semantic Segmentation Module](../module_usage/tutorials/cv_modules/semantic_segmentation_en.md)
+|Model Name|mIoU (%)|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size|YAML File|
+|-|-|-|-|-|-|
+|Deeplabv3_Plus-R50 |80.36|61.0531|1513.58|94.9 M|[Deeplabv3_Plus-R50.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3_Plus-R50.yaml)|
+|Deeplabv3_Plus-R101|81.10|100.026|2460.71|162.5 M|[Deeplabv3_Plus-R101.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3_Plus-R101.yaml)|
+|Deeplabv3-R50|79.90|82.2631|1735.83|138.3 M|[Deeplabv3-R50.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3-R50.yaml)|
+|Deeplabv3-R101|80.85|121.492|2685.51|205.9 M|[Deeplabv3-R101.yaml](../../paddlex/configs/semantic_segmentation/Deeplabv3-R101.yaml)|
+|OCRNet_HRNet-W18|80.67|48.2335|906.385|43.1 M|[OCRNet_HRNet-W18.yaml](../../paddlex/configs/semantic_segmentation/OCRNet_HRNet-W18.yaml)|
+|OCRNet_HRNet-W48|82.15|78.9976|2226.95|249.8 M|[OCRNet_HRNet-W48.yaml](../../paddlex/configs/semantic_segmentation/OCRNet_HRNet-W48.yaml)|
+|PP-LiteSeg-T|73.10|7.6827|138.683|28.5 M|[PP-LiteSeg-T.yaml](../../paddlex/configs/semantic_segmentation/PP-LiteSeg-T.yaml)|
+|PP-LiteSeg-B|75.25|-|-|47.0 M|[PP-LiteSeg-B.yaml](../../paddlex/configs/semantic_segmentation/PP-LiteSeg-B.yaml)|
+|SegFormer-B0 (slice)|76.73|11.1946|268.929|13.2 M|[SegFormer-B0.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B0.yaml)|
+|SegFormer-B1 (slice)|78.35|17.9998|403.393|48.5 M|[SegFormer-B1.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B1.yaml)|
+|SegFormer-B2 (slice)|81.60|48.0371|1248.52|96.9 M|[SegFormer-B2.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B2.yaml)|
+|SegFormer-B3 (slice)|82.47|64.341|1666.35|167.3 M|[SegFormer-B3.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B3.yaml)|
+|SegFormer-B4 (slice)|82.38|82.4336|1995.42|226.7 M|[SegFormer-B4.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B4.yaml)|
+|SegFormer-B5 (slice)|82.58|97.3717|2420.19|229.7 M|[SegFormer-B5.yaml](../../paddlex/configs/semantic_segmentation/SegFormer-B5.yaml)|
 
 **Note: The above accuracy metrics are evaluated on the **[Cityscapes](https://www.cityscapes-dataset.com/)** dataset using mIoU.**
 
-|Model Name|mIoU (%)|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size|
-|-|-|-|-|-|
-|SeaFormer_base(slice)|40.92|24.4073|397.574|30.8 M|
-|SeaFormer_large (slice)|43.66|27.8123|550.464|49.8 M|
-|SeaFormer_small (slice)|38.73|19.2295|358.343|14.3 M|
-|SeaFormer_tiny (slice)|34.58|13.9496|330.132|6.1 M |
+|Model Name|mIoU (%)|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size|YAML File|
+|-|-|-|-|-|-|
+|SeaFormer_base(slice)|40.92|24.4073|397.574|30.8 M|[SeaFormer_base.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_base.yaml)|
+|SeaFormer_large (slice)|43.66|27.8123|550.464|49.8 M|[SeaFormer_large.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_large.yaml)|
+|SeaFormer_small (slice)|38.73|19.2295|358.343|14.3 M|[SeaFormer_small.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_small.yaml)|
+|SeaFormer_tiny (slice)|34.58|13.9496|330.132|6.1 M |[SeaFormer_tiny.yaml](../../paddlex/configs/semantic_segmentation/SeaFormer_tiny.yaml)|
 
 **Note: The above accuracy metrics are evaluated on the **[ADE20k](https://groups.csail.mit.edu/vision/datasets/ADE20K/)** dataset. "slice" indicates that the input image has been cropped.**
 
-## Instance Segmentation Module
-|Model Name|Mask AP|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size |
-|-|-|-|-|-|
-|Mask-RT-DETR-H|50.6|132.693|4896.17|449.9 M|
-|Mask-RT-DETR-L|45.7|46.5059|2575.92|113.6 M|
-|Mask-RT-DETR-M|42.7|36.8329|-|66.6 M|
-|Mask-RT-DETR-S|41.0|33.5007|-|51.8 M|
-|Mask-RT-DETR-X|47.5|75.755|3358.04|237.5 M|
-|Cascade-MaskRCNN-ResNet50-FPN|36.3|-|-|254.8 M|
-|Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN|39.1|-|-|254.7 M|
-|MaskRCNN-ResNet50-FPN|35.6|-|-|157.5 M|
-|MaskRCNN-ResNet50-vd-FPN|36.4|-|-|157.5 M|
-|MaskRCNN-ResNet50-vd-SSLDv2-FPN|38.2|-|-|157.2 M|
-|MaskRCNN-ResNet50|32.8|-|-|127.8 M|
-|MaskRCNN-ResNet101-FPN|36.6|-|-|225.4 M|
-|MaskRCNN-ResNet101-vd-FPN|38.1|-|-|225.1 M|
-|MaskRCNN-ResNeXt101-vd-FPN|39.5|-|-|370.0 M|
-|PP-YOLOE_seg-S|32.5|-|-|31.5 M|
+## [Instance Segmentation Module](../module_usage/tutorials/cv_modules/instance_segmentation_en.md)
+|Model Name|Mask AP|GPU Inference Time (ms)|CPU Inference Time (ms) |Model Size |YAML File|
+|-|-|-|-|-|-|
+|Mask-RT-DETR-H|50.6|132.693|4896.17|449.9 M|[Mask-RT-DETR-H.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-H.yaml)|
+|Mask-RT-DETR-L|45.7|46.5059|2575.92|113.6 M|[Mask-RT-DETR-L.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-L.yaml)|
+|Mask-RT-DETR-M|42.7|36.8329|-|66.6 M|[Mask-RT-DETR-M.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-M.yaml)|
+|Mask-RT-DETR-S|41.0|33.5007|-|51.8 M|[Mask-RT-DETR-S.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-S.yaml)|
+|Mask-RT-DETR-X|47.5|75.755|3358.04|237.5 M|[Mask-RT-DETR-X.yaml](../../paddlex/configs/instance_segmentation/Mask-RT-DETR-X.yaml)|
+|Cascade-MaskRCNN-ResNet50-FPN|36.3|-|-|254.8 M|[Cascade-MaskRCNN-ResNet50-FPN.yaml](../../paddlex/configs/instance_segmentation/Cascade-MaskRCNN-ResNet50-FPN.yaml)|
+|Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN|39.1|-|-|254.7 M|[Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/instance_segmentation/Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|MaskRCNN-ResNet50-FPN|35.6|-|-|157.5 M|[MaskRCNN-ResNet50-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50-FPN.yaml)|
+|MaskRCNN-ResNet50-vd-FPN|36.4|-|-|157.5 M|[MaskRCNN-ResNet50-vd-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50-vd-FPN.yaml)|
+|MaskRCNN-ResNet50-vd-SSLDv2-FPN|38.2|-|-|157.2 M|[MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+|MaskRCNN-ResNet50|32.8|-|-|127.8 M|[MaskRCNN-ResNet50.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet50.yaml)|
+|MaskRCNN-ResNet101-FPN|36.6|-|-|225.4 M|[MaskRCNN-ResNet101-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet101-FPN.yaml)|
+|MaskRCNN-ResNet101-vd-FPN|38.1|-|-|225.1 M|[MaskRCNN-ResNet101-vd-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNet101-vd-FPN.yaml)|
+|MaskRCNN-ResNeXt101-vd-FPN|39.5|-|-|370.0 M|[MaskRCNN-ResNeXt101-vd-FPN.yaml](../../paddlex/configs/instance_segmentation/MaskRCNN-ResNeXt101-vd-FPN.yaml)|
+|PP-YOLOE_seg-S|32.5|-|-|31.5 M|[PP-YOLOE_seg-S.yaml](../../paddlex/configs/instance_segmentation/PP-YOLOE_seg-S.yaml)|
 
 **Note: The above accuracy metrics are evaluated on the **[COCO2017](https://cocodataset.org/#home)** validation set using Mask AP(0.5:0.95).**
 
-## Text Detection Module
-|Model Name|Detection Hmean (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|
-|-|-|-|-|-|
-|PP-OCRv4_mobile_det |77.79|10.6923|120.177|4.2 M|
-|PP-OCRv4_server_det |82.69|83.3501|2434.01|100.1M|
+## [Text Detection Module](../module_usage/tutorials/ocr_modules/text_detection_en.md)
+|Model Name|Detection Hmean (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|YAML File|
+|-|-|-|-|-|-|
+|PP-OCRv4_mobile_det |77.79|10.6923|120.177|4.2 M|[PP-OCRv4_mobile_det.yaml](../../paddlex/configs/text_detection/PP-OCRv4_mobile_det.yaml)|
+|PP-OCRv4_server_det |82.69|83.3501|2434.01|100.1M|[PP-OCRv4_server_det.yaml](../../paddlex/configs/text_detection/PP-OCRv4_server_det.yaml)|
 
 **Note: The above accuracy metrics are evaluated on a self-built Chinese dataset by PaddleOCR, covering street scenes, web images, documents, and handwritten texts, with 500 images for detection.**
 
-## Seal Text Detection Module
-|Model Name|Detection Hmean (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |
-|-|-|-|-|-|
-|PP-OCRv4_mobile_seal_det|96.47|10.5878|131.813|4.7 M |
-|PP-OCRv4_server_seal_det|98.21|84.341|2425.06|108.3 M|
+## [Seal Text Detection Module](../module_usage/tutorials/ocr_modules/seal_text_detection_en.md)
+|Model Name|Detection Hmean (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-OCRv4_mobile_seal_det|96.47|10.5878|131.813|4.7 M |[PP-OCRv4_mobile_seal_det.yaml](../../paddlex/configs/text_detection_seal/PP-OCRv4_mobile_seal_det.yaml)|
+|PP-OCRv4_server_seal_det|98.21|84.341|2425.06|108.3 M|[PP-OCRv4_server_seal_det.yaml](../../paddlex/configs/text_detection_seal/PP-OCRv4_server_seal_det.yaml)|
 
 **Note: The above accuracy metrics are evaluated on a self-built seal dataset by PaddleX, containing 500 seal images.**
 
-## Text Recognition Module
-|Model Name|Recognition Avg Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |
-|-|-|-|-|-|
-|PP-OCRv4_mobile_rec |78.20|7.95018|46.7868|10.6 M|
-|PP-OCRv4_server_rec |79.20|7.19439|140.179|71.2 M|
+## [Text Recognition Module](../module_usage/tutorials/ocr_modules/text_recognition_en.md)
+|Model Name|Recognition Avg Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |YAML File|
+|-|-|-|-|-|-|
+|PP-OCRv4_mobile_rec |78.20|7.95018|46.7868|10.6 M|[PP-OCRv4_mobile_rec.yaml](../../paddlex/configs/text_recognition/PP-OCRv4_mobile_rec.yaml)|
+|PP-OCRv4_server_rec |79.20|7.19439|140.179|71.2 M|[PP-OCRv4_server_rec.yaml](../../paddlex/configs/text_recognition/PP-OCRv4_server_rec.yaml)|
 
 **Note: The above accuracy metrics are evaluated on a self-built Chinese dataset by PaddleOCR, covering street scenes, web images, documents, and handwritten texts, with 11,000 images for text recognition.**
 
-|Model Name|Recognition Avg Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |
-|-|-|-|-|-|
-|ch_SVTRv2_rec|68.81|8.36801|165.706|73.9 M|
+|Model Name|Recognition Avg Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |YAML File|
+|-|-|-|-|-|-|
+|ch_SVTRv2_rec|68.81|8.36801|165.706|73.9 M|[ch_SVTRv2_rec.yaml](../../paddlex/configs/text_recognition/ch_SVTRv2_rec.yaml)|
 
 **Note: The above accuracy metrics are evaluated on [PaddleOCR Algorithm Model Challenge - Task 1: OCR End-to-End Recognition](https://aistudio.baidu.com/competition/detail/1131/0/introduction) A-Rank.**
 
-|Model Name|Recognition Avg Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|
-|-|-|-|-|-|
-|ch_RepSVTR_rec|65.07|10.5047|51.5647|22.1 M|
+|Model Name|Recognition Avg Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|YAML File|
+|-|-|-|-|-|-|
+|ch_RepSVTR_rec|65.07|10.5047|51.5647|22.1 M|[ch_RepSVTR_rec.yaml](../../paddlex/configs/text_recognition/ch_RepSVTR_rec.yaml)|
 
 **Note: The above accuracy metrics are evaluated on [PaddleOCR Algorithm Model Challenge - Task 1: OCR End-to-End Recognition](https://aistudio.baidu.com/competition/detail/1131/0/introduction) B-Rank.**
 
-## Formula Recognition Module
-|Model Name|BLEU Score|Normed Edit Distance|ExpRate (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|
-|-|-|-|-|-|-|-|
-|LaTeX_OCR_rec|0.8821|0.0823|40.01|-|-|89.7 M|
+## [Formula Recognition Module](../module_usage/tutorials/ocr_modules/formula_recognition_en.md)
+|Model Name|BLEU Score|Normed Edit Distance|ExpRate (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|YAML File|
+|-|-|-|-|-|-|-|-|
+|LaTeX_OCR_rec|0.8821|0.0823|40.01|-|-|89.7 M|[LaTeX_OCR_rec.yaml](../../paddlex/configs/formula_recognition/LaTeX_OCR_rec.yaml)|
 
 **Note: The above accuracy metrics are measured on the [LaTeX-OCR formula recognition test set](https://drive.google.com/drive/folders/13CA4vAmOmD_I_dSbvLp-Lf0s6KiaNfuO).**
 
-## Table Structure Recognition Module
-|Model Name|Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |
-|-|-|-|-|-|
-|SLANet|59.52|522.536|1845.37|6.9 M |
-|SLANet_plus|63.69|522.536|1845.37|6.9 M |
- 
+## [Table Structure Recognition Module](../module_usage/tutorials/ocr_modules/table_structure_recognition_en.md)
+|Model Name|Accuracy (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size |YAML File|
+|-|-|-|-|-|-|
+|SLANet|59.52|522.536|1845.37|6.9 M |[SLANet.yaml](../../paddlex/configs/table_recognition/SLANet.yaml)|
+|SLANet_plus|63.69|522.536|1845.37|6.9 M |[SLANet_plus.yaml](../../paddlex/configs/table_recognition/SLANet_plus.yaml)|
+
 **Note: The above accuracy metrics are evaluated on a self-built English table recognition dataset by PaddleX.**
 
-## Image Rectification Module
-|Model Name|MS-SSIM (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|
-|-|-|-|-|-|
-|UVDoc|54.40|-|-|30.3 M|
+## [Image Rectification Module](../module_usage/tutorials/ocr_modules/text_image_unwarping_en.md)
+|Model Name|MS-SSIM (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|YAML File|
+|-|-|-|-|-|-|
+|UVDoc|54.40|-|-|30.3 M|[UVDoc.yaml](../../paddlex/configs/image_unwarping/UVDoc.yaml)|
 
 
 **Note: The above accuracy metrics are measured on a self-built image rectification dataset by PaddleX.**
 
-## Layout Analysis Module
-|Model Name|mAP (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|
-|-|-|-|-|-|
-|PicoDet_layout_1x|86.8|13.036|91.2634|7.4 M |
-|PicoDet-L_layout_3cls|89.3|15.7425|159.771|22.6 M|
-|RT-DETR-H_layout_3cls|95.9|114.644|3832.62|470.1 M|
-|RT-DETR-H_layout_17cls|92.6|115.126|3827.25|470.2 M|
+## [Layout Detection Module](../module_usage/tutorials/ocr_modules/layout_detection_en.md)
+|Model Name|mAP (%)|GPU Inference Time (ms)|CPU Inference Time (ms)|Model Size|YAML File|
+|-|-|-|-|-|-|
+|PicoDet_layout_1x|86.8|13.036|91.2634|7.4 M |[PicoDet_layout_1x.yaml](../../paddlex/configs/structure_analysis/PicoDet_layout_1x.yaml)|
+|PicoDet-L_layout_3cls|89.3|15.7425|159.771|22.6 M|[PicoDet-L_layout_3cls.yaml](../../paddlex/configs/structure_analysis/PicoDet-L_layout_3cls.yaml)|
+|RT-DETR-H_layout_3cls|95.9|114.644|3832.62|470.1 M|[RT-DETR-H_layout_3cls.yaml](../../paddlex/configs/structure_analysis/RT-DETR-H_layout_3cls.yaml)|
+|RT-DETR-H_layout_17cls|92.6|115.126|3827.25|470.2 M|[RT-DETR-H_layout_17cls.yaml](../../paddlex/configs/structure_analysis/RT-DETR-H_layout_17cls.yaml)|
 
-**Note: The evaluation set for the above accuracy metrics is the ****PaddleX self-built Layout Analysis Dataset****, containing 10,000 images.**
+**Note: The evaluation set for the above accuracy metrics is the ****PaddleX self-built Layout Detection Dataset****, containing 10,000 images.**
 
-## Time Series Forecasting Module
-|Model Name|mse|mae|Model Size|
-|-|-|-|-|
-|DLinear|0.382|0.394|72 K|
-|NLinear|0.386|0.392|40 K |
-|Nonstationary|0.600|0.515|55.5 M|
-|PatchTST|0.385|0.397|2.0 M |
-|RLinear|0.384|0.392|40 K|
-|TiDE|0.405|0.412|31.7 M|
-|TimesNet|0.417|0.431|4.9 M|
+## [Time Series Forecasting Module](../module_usage/tutorials/ts_modules/time_series_forecast_en.md)
+|Model Name|mse|mae|Model Size|YAML File|
+|-|-|-|-|-|
+|DLinear|0.382|0.394|72 K|[DLinear.yaml](../../paddlex/configs/ts_forecast/DLinear.yaml)|
+|NLinear|0.386|0.392|40 K |[NLinear.yaml](../../paddlex/configs/ts_forecast/NLinear.yaml)|
+|Nonstationary|0.600|0.515|55.5 M|[Nonstationary.yaml](../../paddlex/configs/ts_forecast/Nonstationary.yaml)|
+|PatchTST|0.385|0.397|2.0 M |[PatchTST.yaml](../../paddlex/configs/ts_forecast/PatchTST.yaml)|
+|RLinear|0.384|0.392|40 K|[RLinear.yaml](../../paddlex/configs/ts_forecast/RLinear.yaml)|
+|TiDE|0.405|0.412|31.7 M|[TiDE.yaml](../../paddlex/configs/ts_forecast/TiDE.yaml)|
+|TimesNet|0.417|0.431|4.9 M|[TimesNet.yaml](../../paddlex/configs/ts_forecast/TimesNet.yaml)|
 
 **Note: The above accuracy metrics are measured on the **[ETTH1](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Etth1.tar)** dataset ****(evaluation results on the test set test.csv)****.**
 
-## Time Series Anomaly Detection Module
-|Model Name|Precision|Recall|f1_score|Model Size|
-|-|-|-|-|-|
-|AutoEncoder_ad|99.36|84.36|91.25|52 K |
-|DLinear_ad|98.98|93.96|96.41|112 K|
-|Nonstationary_ad|98.55|88.95|93.51|1.8 M |
-|PatchTST_ad|98.78|90.70|94.57|320 K |
-|TimesNet_ad|98.37|94.80|96.56|1.3 M |
+## [Time Series Anomaly Detection Module](../module_usage/tutorials/ts_modules/time_series_anomaly_detection_en.md)
+|Model Name|Precision|Recall|f1_score|Model Size|YAML File|
+|-|-|-|-|-|-|
+|AutoEncoder_ad|99.36|84.36|91.25|52 K |[AutoEncoder_ad.yaml](../../paddlex/configs/ts_anomaly_detection/AutoEncoder_ad.yaml)|
+|DLinear_ad|98.98|93.96|96.41|112 K|[DLinear_ad.yaml](../../paddlex/configs/ts_anomaly_detection/DLinear_ad.yaml)|
+|Nonstationary_ad|98.55|88.95|93.51|1.8 M |[Nonstationary_ad.yaml](../../paddlex/configs/ts_anomaly_detection/Nonstationary_ad.yaml)|
+|PatchTST_ad|98.78|90.70|94.57|320 K |[PatchTST_ad.yaml](../../paddlex/configs/ts_anomaly_detection/PatchTST_ad.yaml)|
+|TimesNet_ad|98.37|94.80|96.56|1.3 M |[TimesNet_ad.yaml](../../paddlex/configs/ts_anomaly_detection/TimesNet_ad.yaml)|
 
 **Note: The above accuracy metrics are measured on the **[PSM](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ts_anomaly_examples.tar)** dataset.**
 
-## Time Series Classification Module
-|Model Name|acc (%)|Model Size|
-|-|-|-|
-|TimesNet_cls|87.5|792 K|
+## [Time Series Classification Module](../module_usage/tutorials/ts_modules/time_series_classification_en.md)
+|Model Name|acc (%)|Model Size|YAML File|
+|-|-|-|-|
+|TimesNet_cls|87.5|792 K|[TimesNet_cls.yaml](../../paddlex/configs/ts_classification/TimesNet_cls.yaml)|
 
 **Note: The above accuracy metrics are measured on the [UWaveGestureLibrary](https://paddlets.bj.bcebos.com/classification/UWaveGestureLibrary_TEST.csv) dataset.**
 
->**Note: All GPU inference times for the above models are based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.**
+>**Note: All GPU inference times for the above models are based on an NVIDIA Tesla T4 machine with FP32 precision. CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz with 8 threads and FP32 precision.**