[Docs] Add note on benchmark data (#4390)

* Add note on benchmark data

* Fix order

docs/module_usage/tutorials/cv_modules/3d_bev_detection.en.md

@@ -9,6 +9,8 @@ The 3D multimodal fusion detection module is a key component in the fields of co
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/3d_bev_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

docs/module_usage/tutorials/cv_modules/anomaly_detection.en.md

@@ -9,6 +9,7 @@ Unsupervised anomaly detection is a technology that automatically identifies and
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/anomaly_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/face_detection.en.md

@@ -9,6 +9,7 @@ Face detection is a fundamental task in object detection, aiming to automaticall
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/face_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/cv_modules/face_feature.en.md

@@ -9,6 +9,8 @@ Face feature models typically take standardized face images processed through de
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/cv_modules/face_feature.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/human_detection.en.md

@@ -9,6 +9,7 @@ Human detection is a subtask of object detection, which utilizes computer vision
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/human_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

docs/module_usage/tutorials/cv_modules/human_keypoint_detection.en.md

@@ -11,6 +11,8 @@ Keypoint detection algorithms mainly include two approaches: Top-Down and Bottom
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
   <tr>
     <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/human_keypoint_detection.md

@@ -11,6 +11,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
   <tr>
     <th >模型</th><th>模型下载链接</th>

docs/module_usage/tutorials/cv_modules/image_classification.en.md

@@ -9,6 +9,7 @@ The image classification module is a crucial component in computer vision system
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/image_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/image_feature.en.md

@@ -9,6 +9,7 @@ The image feature module is one of the important tasks in computer vision, prima
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/image_feature.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/image_multilabel_classification.en.md

@@ -9,6 +9,7 @@ The image multi-label classification module is a crucial component in computer v
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/image_multilabel_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/instance_segmentation.en.md

@@ -9,6 +9,8 @@ The instance segmentation module is a crucial component in computer vision syste
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/instance_segmentation.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

docs/module_usage/tutorials/cv_modules/mainbody_detection.en.md

@@ -9,6 +9,7 @@ Mainbody detection is a fundamental task in object detection, aiming to identify
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/mainbody_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/object_detection.en.md

@@ -9,6 +9,8 @@ The object detection module is a crucial component in computer vision systems, r
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/object_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.en.md

@@ -9,6 +9,8 @@ Open-vocabulary object detection is an advanced object detection technology aime
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.en.md

@@ -9,6 +9,8 @@ Open-vocabulary segmentation is an image segmentation task that aims to segment
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.en.md

@@ -9,6 +9,7 @@ Pedestrian attribute recognition is a crucial component in computer vision syste
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/rotated_object_detection.en.md

@@ -9,6 +9,8 @@ Rotated object detection is a derivative of the object detection module, specifi
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/rotated_object_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

docs/module_usage/tutorials/cv_modules/semantic_segmentation.en.md

@@ -9,6 +9,8 @@ Semantic segmentation is a technique in computer vision that classifies each pix
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/cv_modules/semantic_segmentation.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/cv_modules/small_object_detection.en.md

@@ -9,6 +9,8 @@ Small object detection typically refers to accurately detecting and locating sma
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/cv_modules/small_object_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md

@@ -9,6 +9,7 @@ Vehicle attribute recognition is a crucial component in computer vision systems.
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/cv_modules/vehicle_detection.en.md

@@ -9,6 +9,7 @@ Vehicle detection is a subtask of object detection, specifically referring to th
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/cv_modules/vehicle_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

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

@@ -9,6 +9,7 @@ The document image orientation classification module is aim to distinguish the o
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <thead>

docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

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

@@ -9,6 +9,7 @@ The formula recognition module is a crucial component of OCR (Optical Character
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/ocr_modules/formula_recognition.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

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

@@ -9,6 +9,8 @@ The core task of structure analysis is to parse and segment the content of input
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 * <b>The layout detection model includes 20 common categories: document title, paragraph title, text, page number, abstract, table, references, footnotes, header, footer, algorithm, formula, formula number, image, table, seal, figure_table title, chart, and sidebar text and lists of references</b>
 <table>
 <thead>

docs/module_usage/tutorials/ocr_modules/layout_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 * <b>版面检测模型，包含20个常见的类别：文档标题、段落标题、文本、页码、摘要、目录、参考文献、脚注、页眉、页脚、算法、公式、公式编号、图像、表格、图和表标题（图标题、表格标题和图表标题）、印章、图表、侧栏文本和参考文献内容</b>
 <table>
 <thead>

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

@@ -9,6 +9,7 @@ The seal text detection module typically outputs multi-point bounding boxes arou
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <thead>

docs/module_usage/tutorials/ocr_modules/seal_text_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

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

@@ -9,6 +9,8 @@ The table cell detection module is a key component of table recognition tasks, r
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/ocr_modules/table_cells_detection.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

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

@@ -9,6 +9,8 @@ The table classification module is a key component of a computer vision system,
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/ocr_modules/table_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

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

@@ -9,6 +9,7 @@ Table structure recognition is a crucial component in table recognition systems,
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <table>
 <tr>

docs/module_usage/tutorials/ocr_modules/table_structure_recognition.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

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

@@ -8,6 +8,9 @@ comments: true
 The text detection module is a crucial component in OCR (Optical Character Recognition) systems, responsible for locating and marking regions containing text within images. The performance of this module directly impacts the accuracy and efficiency of the entire OCR system. The text detection module typically outputs bounding boxes for text regions, which are then passed on to the text recognition module for further processing.
 
 ## II. Supported Models
+
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/ocr_modules/text_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

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

@@ -9,6 +9,8 @@ The primary purpose of Text Image Unwarping is to perform geometric transformati
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/ocr_modules/text_image_unwarping.md

@@ -9,7 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
-
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

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

@@ -9,6 +9,8 @@ The text recognition module is the core component of an OCR (Optical Character R
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/ocr_modules/text_recognition.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

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

@@ -9,6 +9,8 @@ The text line orientation classification module primarily distinguishes the orie
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/speech_modules/multilingual_speech_recognition.en.md

@@ -9,6 +9,8 @@ Speech recognition is an advanced tool that can automatically convert human-spok
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 ### Whisper Model
 Demo Link | Training Data | Size | Descriptions | CER | Model
 :-----------: | :-----:| :-------: | :-----: | :-----: |:---------:|

docs/module_usage/tutorials/speech_modules/multilingual_speech_recognition.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 ### Whisper Model
 <table>
   <tr>

docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.en.md

@@ -9,6 +9,8 @@ Time series anomaly detection focuses on identifying abnormal points or periods
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/time_series_modules/time_series_classification.en.md

@@ -9,6 +9,8 @@ Time series classification involves identifying and categorizing different patte
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/time_series_modules/time_series_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <thead>

docs/module_usage/tutorials/time_series_modules/time_series_forecasting.en.md

@@ -9,6 +9,8 @@ Time series forecasting aims to predict the possible values or states at a futur
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/time_series_modules/time_series_forecasting.md

@@ -9,6 +9,8 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <thead>
 <tr>

docs/module_usage/tutorials/video_modules/video_classification.en.md

@@ -9,6 +9,8 @@ The Video Classification Module is a crucial component in a computer vision syst
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/video_modules/video_classification.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/video_modules/video_detection.en.md

@@ -11,6 +11,8 @@ The output of the video detection module includes bounding boxes and class label
 
 ## II. List of Supported Models
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/video_modules/video_detection.md

@@ -10,6 +10,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/vlm_modules/chart_parsing.en.md

@@ -11,6 +11,8 @@ Multimodal chart parsing is a cutting-edge technology in the OCR field, focusing
 
 ## II. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/module_usage/tutorials/vlm_modules/chart_parsing.md

@@ -11,6 +11,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/module_usage/tutorials/vlm_modules/doc_vlm.en.md

@@ -6,6 +6,8 @@ The document visual-language model is a cutting-edge multimodal processing techn
 
 ## 2. Supported Model List
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Download Link</th>

docs/module_usage/tutorials/vlm_modules/doc_vlm.md

@@ -9,6 +9,7 @@ comments: true
 
 ## 二、支持模型列表
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
 
 <table>
 <tr>

docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.en.md

@@ -16,6 +16,8 @@ Please note that the 3D multi-modal fusion detection pipeline currently does not
 
 <b>The 3D multi-modal fusion detection pipeline includes a 3D multi-modal fusion detection module</b>，which contains <b>a BEVFusion model</b>. We provide benchmark data for this model:
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <p><b>3D Multi-modal Fusion Detection Module:</b></p>
 <table>
 <tr>

docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.md

@@ -16,6 +16,8 @@ BEVFusion 是一种多模态 3D 目标检测模型，通过将环视摄像头图
 
 <b>3D多模态融合检测产线中包含了3D多模态融合检测模块</b>，模块中包含了一个<b>BEVFusion模型</b>，我们提供了该模型的 benchmark 数据：
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <p><b>3D多模态融合检测模块：</b></p>
 <table>
 <tr>

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

@@ -12,6 +12,7 @@ The face recognition pipeline is an end-to-end system dedicated to solving face
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/pipelines/face_recognition/02.jpg"/>
 <b>The face recognition pipeline includes a face detection module and a face feature module</b>, with several models in each module. Which models to use can be selected based on the benchmark data below. <b>If you prioritize model accuracy, choose models with higher accuracy; if you prioritize inference speed, choose models with faster inference; if you prioritize model size, choose models with smaller storage requirements</b>.
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <p><b>Face Detection Module</b>:</p>
 <table>

docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.md

@@ -12,6 +12,8 @@ comments: true
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/pipelines/face_recognition/02.jpg"/>
 <b>人脸识别产线中包含了人脸检测模块和人脸特征模块</b>，每个模块中包含了若干模型，具体使用哪些模型，您可以根据下边的 benchmark 数据来选择。<b>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</b>。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <p><b>人脸检测模块：</b></p>
 <table>
 <thead>

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

@@ -13,6 +13,7 @@ PP-ShiTuV2 is a practical general image recognition system mainly composed of th
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/pipelines/general_image_recognition/pp_shitu_v2.jpg"/>
 <b>The General Image Recognition Pipeline includes the mainbody detection module and the image feature module</b>, with several models to choose. You can select the model to use based on the benchmark data below. <b>If you prioritize model precision, choose a model with higher precision. If you prioritize inference speed, choose a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage size</b>.
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
 
 <b>Mainbody Detection Module:</b>
 <table>

docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.md

@@ -13,6 +13,8 @@ PP-ShiTuV2 是一个实用的通用图像识别系统，主要由主体检测、
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/pipelines/general_image_recognition/pp_shitu_v2.jpg"/>
 <b>通用图像识别产线中包含了主体检测模块和图像特征模块</b>，有若干模型可供选择，您可以根据下边的 benchmark 数据来选择使用的模型。<b>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</b>。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 
 <b>主体检测模块：</b>
 <table>

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

@@ -12,6 +12,8 @@ PaddleX's Human Keypoint Detection Pipeline is a Top-Down solution consisting of
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/pipelines/human_keypoint_detection/01.jpg"/>
 <b>The Human Keypoint Detection Pipeline includes pedestrian detection and human keypoint detection modules</b>, with several models available. You can choose the model based on the benchmark data below. <b>If you prioritize model accuracy, choose a model with higher accuracy; if you prioritize inference speed, choose a model with faster inference speed; if you prioritize storage size, choose a model with a smaller storage size</b>.
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <details><summary> 👉Model List Details</summary>
 <b>Pedestrian Detection Module:</b>
 <table>

docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.md

@@ -9,6 +9,8 @@ PaddleX 的人体关键点检测产线是一个 Top-Down 方案，由行人检
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/refs/heads/main/images/pipelines/human_keypoint_detection/01.jpg"/>
 <b>人体关键点检测产线中包含了行人检测模块和人体关键点检测模块</b>，有若干模型可供选择，您可以根据下边的 benchmark 数据来选择使用的模型。<b>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</b>。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <details><summary> 👉模型列表详情</summary>
 <b>行人检测模块：</b>
 <table>

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

@@ -12,6 +12,8 @@ This pipeline integrates the high-precision anomaly detection model STFPM, which
 
 <b>The image anomaly detection pipeline includes an unsupervised anomaly detection module, with the following model benchmarks</b>:
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md

@@ -13,6 +13,8 @@ comments: true
 
 <b>图像异常检测</b><b>产线中包含图像异常检测模块</b>，包含的模型如下。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <thead>
 <tr>

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

@@ -9,6 +9,9 @@ Image classification is a technique that assigns images to predefined categories
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_classification/01.png"/>
 <b>The General Image Classification Pipeline includes an image classification module. If you prioritize model accuracy, choose a model with higher accuracy. If you prioritize inference speed, select a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage size.</b>
+
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md

@@ -10,6 +10,8 @@ comments: true
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_classification/01.png"/>
 <b>通用图像分类产线中包含了图像分类模块，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</b>。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

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

@@ -11,6 +11,8 @@ Image multi-label classification is a technique that assigns multiple relevant c
 
 <b>The General Image Multi-Label Classification Pipeline includes a module for image multi-label classification. If you prioritize model accuracy, choose a model with higher accuracy. If you prioritize inference speed, choose a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage size.</b>
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <thead>
 <tr>

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -11,6 +11,8 @@ comments: true
 
 <b>通用图像多标签分类产线中包含了图像多标签分类模块，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</b>。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <thead>
 <tr>

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

@@ -9,6 +9,9 @@ Instance segmentation is a computer vision task that not only identifies the obj
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/instance_segmentation/01.png"/>
 <b>The General Instance Segmentation Pipeline includes a</b> <b>Object Detection</b> <b>module. If you prioritize model precision, choose a model with higher precision. If you prioritize inference speed, choose a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage size.</b>
+
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md

@@ -11,6 +11,9 @@ comments: true
 <b>通用实例分割产线中包含了实例分割模块，该模块都包含多个模型，您可以根据下方的基准测试数据选择使用的模型</b>。
 
 <b>如果您更注重模型的精度，请选择精度较高的模型；如果您更在意模型的推理速度，请选择推理速度较快的模型；如果您关注模型的存储大小，请选择存储体积较小的模型。</b>
+
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <p><b>通用图像实例分割模块（可选）：</b></p>
 <table>
 <tr>

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

@@ -8,6 +8,9 @@ comments: true
 Object detection aims to identify the categories and locations of multiple objects in images or videos by generating bounding boxes to mark these objects. Unlike simple image classification, object detection not only requires recognizing what objects are present in an image, such as people, cars, and animals, but also accurately determining the specific position of each object within the image, typically represented by rectangular boxes. This technology is widely used in autonomous driving, surveillance systems, smart photo albums, and other fields, relying on deep learning models (e.g., YOLO, Faster R-CNN) that can efficiently extract features and perform real-time detection, significantly enhancing the computer's ability to understand image content.
 
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/object_detection/01.png"/>
+
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <table>
 <tr>
 <th>Model</th><th>Model Download Link</th>

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md

@@ -10,6 +10,8 @@ comments: true
 <img src="https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/object_detection/01.png"/>
 <b>通用</b><b>目标检测</b><b>产线中包含了</b><b>目标检测</b><b>模块，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</b>。
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <table>
 <tr>
 <th>模型</th><th>模型下载链接</th>

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

@@ -13,6 +13,8 @@ Open vocabulary object detection is an advanced object detection technology that
 
 <b>If you prioritize model accuracy, choose a model with higher accuracy; if you prioritize inference speed, choose a model with faster inference speed; if you prioritize storage size, choose a model with a smaller storage size.</b>
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <p><b>General Image Open Vocabulary Detection Module (Optional):</b></p>
 
 <table>

docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_detection.md

@@ -13,6 +13,8 @@ comments: true
 
 <b>如果您更注重模型的精度，请选择精度较高的模型；如果您更在意模型的推理速度，请选择推理速度较快的模型；如果您关注模型的存储大小，请选择存储体积较小的模型。</b>
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <p><b>通用图像开放词汇检测模块（可选）：</b></p>
 
 <table>

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

@@ -13,6 +13,8 @@ Open vocabulary segmentation is an image segmentation task that aims to segment
 
 <b>If you prioritize model accuracy, choose a model with higher accuracy; if you prioritize inference speed, choose a model with faster inference speed; if you prioritize storage size, choose a model with a smaller storage size.</b>
 
+> The inference time only includes the model inference time and does not include the time for pre- or post-processing.
+
 <p><b>General Image Open Vocabulary Segmentation Module (Optional):</b></p>
 
 <table>

docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_segmentation.md

@@ -13,6 +13,8 @@ comments: true
 
 <b>如果您更注重模型的精度，请选择精度较高的模型；如果您更在意模型的推理速度，请选择推理速度较快的模型；如果您关注模型的存储大小，请选择存储体积较小的模型。</b>
 
+> 推理耗时仅包含模型推理耗时，不包含前后处理耗时。
+
 <p><b>通用图像开放词汇分割模块（可选）：</b></p>
 
 <table>