Bladeren bron

fix formula doc (#3388)

* fix formula doc

* replace regular mode with normal mode
liuhongen1234567 9 maanden geleden
bovenliggende
commit
17a7973e11
69 gewijzigde bestanden met toevoegingen van 169 en 257 verwijderingen
  1. 1 1
      docs/module_usage/tutorials/cv_modules/3d_bev_detection.en.md
  2. 1 1
      docs/module_usage/tutorials/cv_modules/anomaly_detection.en.md
  3. 2 2
      docs/module_usage/tutorials/cv_modules/face_detection.en.md
  4. 1 1
      docs/module_usage/tutorials/cv_modules/face_feature.en.md
  5. 2 2
      docs/module_usage/tutorials/cv_modules/human_detection.en.md
  6. 2 2
      docs/module_usage/tutorials/cv_modules/human_keypoint_detection.en.md
  7. 2 2
      docs/module_usage/tutorials/cv_modules/image_classification.en.md
  8. 2 2
      docs/module_usage/tutorials/cv_modules/image_feature.en.md
  9. 2 2
      docs/module_usage/tutorials/cv_modules/image_multilabel_classification.en.md
  10. 2 2
      docs/module_usage/tutorials/cv_modules/instance_segmentation.en.md
  11. 2 2
      docs/module_usage/tutorials/cv_modules/mainbody_detection.en.md
  12. 2 2
      docs/module_usage/tutorials/cv_modules/object_detection.en.md
  13. 1 1
      docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.en.md
  14. 1 1
      docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.en.md
  15. 1 1
      docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.en.md
  16. 2 2
      docs/module_usage/tutorials/cv_modules/rotated_object_detection.en.md
  17. 2 2
      docs/module_usage/tutorials/cv_modules/semantic_segmentation.en.md
  18. 2 2
      docs/module_usage/tutorials/cv_modules/small_object_detection.en.md
  19. 2 2
      docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md
  20. 1 1
      docs/module_usage/tutorials/cv_modules/vehicle_detection.en.md
  21. 1 1
      docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.en.md
  22. 1 1
      docs/module_usage/tutorials/ocr_modules/formula_recognition.en.md
  23. 2 2
      docs/module_usage/tutorials/ocr_modules/layout_detection.en.md
  24. 2 2
      docs/module_usage/tutorials/ocr_modules/seal_text_detection.en.md
  25. 1 1
      docs/module_usage/tutorials/ocr_modules/table_cells_detection.en.md
  26. 1 1
      docs/module_usage/tutorials/ocr_modules/table_classification.en.md
  27. 2 2
      docs/module_usage/tutorials/ocr_modules/table_structure_recognition.en.md
  28. 1 1
      docs/module_usage/tutorials/ocr_modules/text_detection.en.md
  29. 2 2
      docs/module_usage/tutorials/ocr_modules/text_image_unwarping.en.md
  30. 1 1
      docs/module_usage/tutorials/ocr_modules/text_recognition.en.md
  31. 2 2
      docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.en.md
  32. 2 2
      docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.en.md
  33. 2 2
      docs/module_usage/tutorials/time_series_modules/time_series_classification.en.md
  34. 2 2
      docs/module_usage/tutorials/time_series_modules/time_series_forecasting.en.md
  35. 1 1
      docs/module_usage/tutorials/video_modules/video_classification.en.md
  36. 1 1
      docs/module_usage/tutorials/video_modules/video_detection.en.md
  37. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.en.md
  38. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.en.md
  39. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.en.md
  40. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.en.md
  41. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.en.md
  42. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/image_classification.en.md
  43. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md
  44. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md
  45. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/object_detection.en.md
  46. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_detection.en.md
  47. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_segmentation.en.md
  48. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.en.md
  49. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.en.md
  50. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.en.md
  51. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.en.md
  52. 1 1
      docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.en.md
  53. 1 1
      docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.en.md
  54. 1 1
      docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.en.md
  55. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/OCR.en.md
  56. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.en.md
  57. 39 81
      docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.en.md
  58. 39 85
      docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md
  59. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.en.md
  60. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.en.md
  61. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md
  62. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.en.md
  63. 1 1
      docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.en.md
  64. 1 1
      docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.en.md
  65. 1 1
      docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md
  66. 1 1
      docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.en.md
  67. 1 1
      docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.en.md
  68. 4 4
      docs/pipeline_usage/tutorials/video_pipelines/video_classification.en.md
  69. 1 1
      docs/pipeline_usage/tutorials/video_pipelines/video_detection.en.md

+ 1 - 1
docs/module_usage/tutorials/cv_modules/3d_bev_detection.en.md

@@ -39,7 +39,7 @@ The 3D multimodal fusion detection module is a key component in the fields of co
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 1 - 1
docs/module_usage/tutorials/cv_modules/anomaly_detection.en.md

@@ -42,7 +42,7 @@ Unsupervised anomaly detection is a technology that automatically identifies and
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration  <a id="quick"> </a>

+ 2 - 2
docs/module_usage/tutorials/cv_modules/face_detection.en.md

@@ -70,7 +70,7 @@ Face detection is a fundamental task in object detection, aiming to automaticall
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -479,4 +479,4 @@ The face detection module can be integrated into PaddleX pipelines such as [<b>F
 
 The weights you produce can be directly integrated into the face detection module. You can refer to the Python example code in [Quick Integration](#quick), simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/cv_modules/face_feature.en.md

@@ -56,7 +56,7 @@ Face feature models typically take standardized face images processed through de
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 2 - 2
docs/module_usage/tutorials/cv_modules/human_detection.en.md

@@ -52,7 +52,7 @@ Human detection is a subtask of object detection, which utilizes computer vision
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -448,4 +448,4 @@ The pedestrian detection module can be integrated into PaddleX pipelines such as
 
 The weights you produce can be directly integrated into the pedestrian detection module. You can refer to the Python example code in [Quick Integration](#iii-quick-integration). Simply replace the model with the path to your trained model to complete the integration.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/human_keypoint_detection.en.md

@@ -56,7 +56,7 @@ Keypoint detection algorithms mainly include two approaches: Top-Down and Bottom
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -436,4 +436,4 @@ The human keypoint detection module can be integrated into the PaddleX pipeline
 
 The weights you produced can be directly integrated into the face feature module. You can refer to the Python example code in [Quick Integration](#III.-Quick-Integration) and only need to replace the model with the path to the model you trained.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/image_classification.en.md

@@ -691,7 +691,7 @@ The image classification module is a crucial component in computer vision system
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>
@@ -1058,4 +1058,4 @@ The image classification module can be integrated into the [General Image Classi
 
 The weights you produce can be directly integrated into the image classification module. You can refer to the Python example code in <a href="#lable">Quick Integration</a>  and simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/image_feature.en.md

@@ -56,7 +56,7 @@ The image feature module is one of the important tasks in computer vision, prima
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -469,4 +469,4 @@ The image feature module can be integrated into the <b>General Image Recognition
 
 The weights you produce can be directly integrated into the image feature 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.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/image_multilabel_classification.en.md

@@ -80,7 +80,7 @@ The image multi-label classification module is a crucial component in computer v
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -499,4 +499,4 @@ The image multi-label classification module can be integrated into the [General
 
 The weights you produce can be directly integrated into the image multi-label classification 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.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/instance_segmentation.en.md

@@ -173,7 +173,7 @@ The instance segmentation module is a crucial component in computer vision syste
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>
@@ -598,4 +598,4 @@ The instance segmentation module can be integrated into the [General Instance Se
 2.<b>Module Integration</b>
 The weights you produce can be directly integrated into the instance segmentation module. Refer to the Python example code in <a href="#lable">Quick Integration</a> , and simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/mainbody_detection.en.md

@@ -44,7 +44,7 @@ Mainbody detection is a fundamental task in object detection, aiming to identify
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration  <a id="quick"> </a>
@@ -440,4 +440,4 @@ The main body detection module can be integrated into PaddleX pipelines such as
 
 The weights you produce can be directly integrated into the main body detection module. You can refer to the Python example code in [Quick Integration](#quick), simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/object_detection.en.md

@@ -361,7 +361,7 @@ The object detection module is a crucial component in computer vision systems, r
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>
@@ -816,4 +816,4 @@ The object detection module can be integrated into the [General Object Detection
 
 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.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.en.md

@@ -43,7 +43,7 @@ Open-vocabulary object detection is an advanced object detection technology aime
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 1 - 1
docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.en.md

@@ -44,7 +44,7 @@ Open-vocabulary segmentation is an image segmentation task that aims to segment
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 1 - 1
docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.en.md

@@ -46,7 +46,7 @@ Pedestrian attribute recognition is a crucial component in computer vision syste
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## <span id="lable">III. Quick Integration</span>

+ 2 - 2
docs/module_usage/tutorials/cv_modules/rotated_object_detection.en.md

@@ -41,7 +41,7 @@ Rotated object detection is a derivative of the object detection module, specifi
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -473,4 +473,4 @@ The model can be directly integrated into the PaddleX pipelines or directly into
 
 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.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/semantic_segmentation.en.md

@@ -220,7 +220,7 @@ Semantic segmentation is a technique in computer vision that classifies each pix
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>
@@ -663,4 +663,4 @@ The document semantic segmentation module can be integrated into PaddleX pipelin
 
 The weights you produce can be directly integrated into the semantic segmentation module. You can refer to the Python sample code in [Quick Integration](#iii-quick-integration) and just replace the model with the path to the model you trained.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/small_object_detection.en.md

@@ -59,7 +59,7 @@ Small object detection typically refers to accurately detecting and locating sma
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -488,4 +488,4 @@ The small object detection module can be integrated into the [Small Object Detec
 
 The weights you produce can be directly integrated into the small object detection module. You can refer to the Python example code in [Quick Integration](#quick), simply replacing the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md

@@ -46,7 +46,7 @@ Vehicle attribute recognition is a crucial component in computer vision systems.
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -459,4 +459,4 @@ The vehicle attribute recognition module can be integrated into the [Vehicle Att
 
 The weights you produce can be directly integrated into the vehicle attribute recognition module. Refer to the Python example code in  <a href="#lable">Quick Integration</a>  and simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/cv_modules/vehicle_detection.en.md

@@ -49,7 +49,7 @@ Vehicle detection is a subtask of object detection, specifically referring to th
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 1 - 1
docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.en.md

@@ -46,7 +46,7 @@ The document image orientation classification module is aim to distinguish the o
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 1 - 1
docs/module_usage/tutorials/ocr_modules/formula_recognition.en.md

@@ -65,7 +65,7 @@ The formula recognition module is a crucial component of OCR (Optical Character
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 2 - 2
docs/module_usage/tutorials/ocr_modules/layout_detection.en.md

@@ -196,7 +196,7 @@ The core task of structure analysis is to parse and segment the content of input
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>
@@ -626,4 +626,4 @@ The structure analysis module can be integrated into PaddleX pipelines such as t
 1. <b>Module Integration</b>
 The weights you produce can be directly integrated into the layout area localization module. You can refer to the Python example code in the [Quick Integration](#quick) section, simply replacing the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/ocr_modules/seal_text_detection.en.md

@@ -54,7 +54,7 @@ The seal text detection module typically outputs multi-point bounding boxes arou
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -602,4 +602,4 @@ The document Seal Text Detection module can be integrated into PaddleX pipelines
 
 The weights you produce can be directly integrated into the Seal Text Detection module. You can refer to the Python sample code in [Quick Integration](#iii-quick-integration) and just replace the model with the path to the model you trained.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/ocr_modules/table_cells_detection.en.md

@@ -47,7 +47,7 @@ The table cell detection module is a key component of table recognition tasks, r
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 1 - 1
docs/module_usage/tutorials/ocr_modules/table_classification.en.md

@@ -39,7 +39,7 @@ The table classification module is a key component of a computer vision system,
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 2 - 2
docs/module_usage/tutorials/ocr_modules/table_structure_recognition.en.md

@@ -65,7 +65,7 @@ SLANet_plus is an enhanced version of SLANet, a table structure recognition mode
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 
@@ -418,4 +418,4 @@ The table structure recognition module can be integrated into PaddleX pipelines
 
 The model weights you produce can be directly integrated into the table structure recognition 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.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/ocr_modules/text_detection.en.md

@@ -52,7 +52,7 @@ The text detection module is a crucial component in OCR (Optical Character Recog
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration

+ 2 - 2
docs/module_usage/tutorials/ocr_modules/text_image_unwarping.en.md

@@ -41,7 +41,7 @@ The primary purpose of Text Image Unwarping is to perform geometric transformati
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -231,4 +231,4 @@ For more information on using PaddleX's single-model inference API, refer to the
 ## IV. Custom Development
 The current module temporarily does not support fine-tuning training and only supports inference integration. Fine-tuning training for this module is planned to be supported in the future.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/ocr_modules/text_recognition.en.md

@@ -280,7 +280,7 @@ The ultra-lightweight cyrillic alphabet recognition model trained based on the P
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 2 - 2
docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.en.md

@@ -45,7 +45,7 @@ The text line orientation classification module primarily distinguishes the orie
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -433,4 +433,4 @@ The text line orientation classification module can be integrated into the [Docu
 
 The weights you produce can be directly integrated into the text line orientation classification module. You can refer to the Python example code in [Quick Integration](##Quick-Integration) and only need to replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.en.md

@@ -69,7 +69,7 @@ Time series anomaly detection focuses on identifying abnormal points or periods
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -505,4 +505,4 @@ The time series prediction module can be integrated into PaddleX pipelines such
 
 The weights you produce can be directly integrated into the time series anomaly detection module. Refer to the Python example code in [Quick Integration](#iii-quick-integration), simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/time_series_modules/time_series_classification.en.md

@@ -41,7 +41,7 @@ Time series classification involves identifying and categorizing different patte
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -487,4 +487,4 @@ The time series prediction module can be integrated into PaddleX pipelines such
 
 The weights you produce can be directly integrated into the time series classification module. Refer to the Python example code in [Quick Integration](#iii-quick-integration) (Note: This section header is in Chinese and should be translated or removed for consistency), simply replace the model with the path to your trained model.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 2 - 2
docs/module_usage/tutorials/time_series_modules/time_series_forecasting.en.md

@@ -71,7 +71,7 @@ Time series forecasting aims to predict the possible values or states at a futur
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## III. Quick Integration
@@ -551,4 +551,4 @@ The Time Series Forecasting module can be integrated into PaddleX pipelines such
 
 The weights you produce can be directly integrated into the Time Series Forecasting module. You can refer to the Python sample code in [Quick Integration](#iii-quick-integration) and just replace the model with the path to the model you trained.
 
-You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).
+You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the [PaddleX High-Performance Inference Guide](../../../pipeline_deploy/high_performance_inference.en.md).

+ 1 - 1
docs/module_usage/tutorials/video_modules/video_classification.en.md

@@ -53,7 +53,7 @@ PP-TSM is a video classification model developed by Baidu PaddlePaddle's Vision
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 </details>
 

+ 1 - 1
docs/module_usage/tutorials/video_modules/video_detection.en.md

@@ -43,7 +43,7 @@ YOWO is a single-stage network with two branches. One branch extracts spatial fe
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## <span id="lable">III. Quick Integration</span>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.en.md

@@ -45,7 +45,7 @@ BEVFusion is a multi-modal 3D object detection model that fuses surround camera
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.en.md

@@ -111,7 +111,7 @@ The face recognition pipeline is an end-to-end system dedicated to solving face
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.en.md

@@ -86,7 +86,7 @@ PP-ShiTuV2 is a practical general image recognition system mainly composed of th
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.en.md

@@ -91,7 +91,7 @@ PaddleX's Human Keypoint Detection Pipeline is a Top-Down solution consisting of
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.en.md

@@ -42,7 +42,7 @@ This pipeline integrates the high-precision anomaly detection model STFPM, which
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/image_classification.en.md

@@ -698,7 +698,7 @@ Image classification is a technique that assigns images to predefined categories
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md

@@ -66,7 +66,7 @@ Image multi-label classification is a technique that assigns multiple relevant c
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md

@@ -173,7 +173,7 @@ Instance segmentation is a computer vision task that not only identifies the obj
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/object_detection.en.md

@@ -360,7 +360,7 @@ Object detection aims to identify the categories and locations of multiple objec
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_detection.en.md

@@ -48,7 +48,7 @@ Open vocabulary object detection is an advanced object detection technology that
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_segmentation.en.md

@@ -50,7 +50,7 @@ Open vocabulary segmentation is an image segmentation task that aims to segment
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.en.md

@@ -79,7 +79,7 @@ Pedestrian attribute recognition is a key function in computer vision systems, u
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.en.md

@@ -47,7 +47,7 @@ Rotated object detection is a variant of the object detection module, specifical
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.en.md

@@ -206,7 +206,7 @@ Semantic segmentation is a computer vision technique that aims to assign each pi
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.en.md

@@ -58,7 +58,7 @@ Small object detection is a specialized technique for identifying tiny objects w
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.en.md

@@ -76,7 +76,7 @@ Vehicle attribute recognition is a crucial component in computer vision systems.
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.en.md

@@ -322,7 +322,7 @@ The RepSVTR text recognition model is a mobile-oriented text recognition model b
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.en.md

@@ -396,7 +396,7 @@ The RepSVTR text recognition model is a mobile-oriented text recognition model b
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/OCR.en.md

@@ -410,7 +410,7 @@ The ultra-lightweight cyrillic alphabet recognition model trained based on the P
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.en.md

@@ -73,7 +73,7 @@ The document image preprocessing pipeline integrates two major functions: docume
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 39 - 81
docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.en.md

@@ -100,32 +100,12 @@ The formula recognition pipeline is designed to solve formula recognition tasks
 </tbody>
 </table>
 
-> ❗ The above list includes the <b>3 core models</b> that are key supported by the text recognition module. The module actually supports a total of <b>11 full models</b>, including several predefined models with different categories. The complete model list is as follows:
+> ❗ The above list includes the <b>3 core models</b> that are key supported by the text recognition module. The module actually supports a total of <b>6 full models</b>, including several predefined models with different categories. The complete model list is as follows:
 
 <details><summary> 👉 Details of Model List</summary>
-<table>
-<thead>
-<tr>
-<th>Model</th><th>Model Download Link</th>
-<th>mAP(0.5) (%)</th>
-<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
-<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
-<th>Model Storage Size (M)</th>
-<th>Introduction</th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Training Model</a></td>
-<td>97.5</td>
-<td>8.02 / 3.09</td>
-<td>23.70 / 20.41</td>
-<td>7.4 M</td>
-<td>A high-efficiency layout area localization model trained on a self-built dataset using PicoDet-1x, capable of detecting table regions.</td>
-</tr>
-</tbody></table>
 
-* <b>3-Class Layout Detection Model, including Table, Image, and Stamp</b>
+
+* <b>17-Class Area Detection Model, including 17 common layout categories: Paragraph Title, Image, Text, Number, Abstract, Content, Figure Caption, Formula, Table, Table Caption, References, Document Title, Footnote, Header, Algorithm, Footer, and Stamp</b>
 <table>
 <thead>
 <tr>
@@ -139,55 +119,34 @@ The formula recognition pipeline is designed to solve formula recognition tasks
 </thead>
 <tbody>
 <tr>
-<td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">Training Model</a></td>
-<td>88.2</td>
-<td>8.99 / 2.22</td>
-<td>16.11 / 8.73</td>
+<td>PicoDet-S_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_layout_17cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_17cls_pretrained.pdparams">Training Model</a></td>
+<td>87.4</td>
+<td>9.11 / 2.12</td>
+<td>15.42 / 9.12</td>
 <td>4.8</td>
 <td>A high-efficiency layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-S.</td>
 </tr>
 <tr>
-<td>PicoDet-L_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_layout_3cls_pretrained.pdparams">Training Model</a></td>
+<td>PicoDet-L_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_layout_17cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_layout_17cls_pretrained.pdparams">Training Model</a></td>
 <td>89.0</td>
-<td>13.05 / 4.50</td>
-<td>41.30 / 41.30</td>
+<td>13.50 / 4.69</td>
+<td>43.32 / 43.32</td>
 <td>22.6</td>
 <td>A balanced efficiency and precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-L.</td>
 </tr>
 <tr>
-<td>RT-DETR-H_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-H_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-H_layout_3cls_pretrained.pdparams">Training Model</a></td>
-<td>95.8</td>
-<td>114.93 / 27.71</td>
-<td>947.56 / 947.56</td>
-<td>470.1</td>
+<td>RT-DETR-H_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-H_layout_17cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-H_layout_17cls_pretrained.pdparams">Training Model</a></td>
+<td>98.3</td>
+<td>115.29 / 104.09</td>
+<td>995.27 / 995.27</td>
+<td>470.2</td>
 <td>A high-precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using RT-DETR-H.</td>
 </tr>
-</tbody></table>
+</tbody>
+</table>
 
-* <b>5-Class English Document Area Detection Model, including Text, Title, Table, Image, and List</b>
-<table>
-<thead>
-<tr>
-<th>Model</th><th>Model Download Link</th>
-<th>mAP(0.5) (%)</th>
-<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
-<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
-<th>Model Storage Size (M)</th>
-<th>Introduction</th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td>PicoDet_layout_1x</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet_layout_1x_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_pretrained.pdparams">Training Model</a></td>
-<td>97.8</td>
-<td>9.03 / 3.10</td>
-<td>25.82 / 20.70</td>
-<td>7.4</td>
-<td>A high-efficiency English document layout area localization model trained on the PubLayNet dataset using PicoDet-1x.</td>
-</tr>
-</tbody></table>
 
-* <b>17-Class Area Detection Model, including 17 common layout categories: Paragraph Title, Image, Text, Number, Abstract, Content, Figure Caption, Formula, Table, Table Caption, References, Document Title, Footnote, Header, Algorithm, Footer, and Stamp</b>
+* <b>Layout detection model, including 23 common categories: document title, paragraph title, text, page number, abstract, table of contents, references, footnotes, header, footer, algorithm, formula, formula number, image, chart title, table, table title, seal, chart title, chart, header image, footer image, sidebar text</b>
 <table>
 <thead>
 <tr>
@@ -201,31 +160,33 @@ The formula recognition pipeline is designed to solve formula recognition tasks
 </thead>
 <tbody>
 <tr>
-<td>PicoDet-S_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_layout_17cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_17cls_pretrained.pdparams">Training Model</a></td>
-<td>87.4</td>
-<td>9.11 / 2.12</td>
-<td>15.42 / 9.12</td>
-<td>4.8</td>
-<td>A high-efficiency layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-S.</td>
+<td>PP-DocLayout-L</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-DocLayout-L_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-L_pretrained.pdparams">Training Model</a></td>
+<td>90.4</td>
+<td>34.6244 / 10.3945</td>
+<td>510.57 / -</td>
+<td>123.76 M</td>
+<td>A high-precision layout area localization model trained on a self-built dataset containing Chinese and English papers, magazines, contracts, books, exams, and research reports using RT-DETR-L.</td>
 </tr>
 <tr>
-<td>PicoDet-L_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_layout_17cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_layout_17cls_pretrained.pdparams">Training Model</a></td>
-<td>89.0</td>
-<td>13.50 / 4.69</td>
-<td>43.32 / 43.32</td>
-<td>22.6</td>
-<td>A balanced efficiency and precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using PicoDet-L.</td>
+<td>PP-DocLayout-M</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-DocLayout-M_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-M_pretrained.pdparams">Training Model</a></td>
+<td>75.2</td>
+<td>13.3259 / 4.8685</td>
+<td>44.0680 / 44.0680</td>
+<td>22.578</td>
+<td>A layout area localization model with balanced precision and efficiency, trained on a self-built dataset containing Chinese and English papers, magazines, contracts, books, exams, and research reports using PicoDet-L.</td>
 </tr>
 <tr>
-<td>RT-DETR-H_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-H_layout_17cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-H_layout_17cls_pretrained.pdparams">Training Model</a></td>
-<td>98.3</td>
-<td>115.29 / 104.09</td>
-<td>995.27 / 995.27</td>
-<td>470.2</td>
-<td>A high-precision layout area localization model trained on a self-built dataset of Chinese and English papers, magazines, and research reports using RT-DETR-H.</td>
+<td>PP-DocLayout-S</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-DocLayout-S_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-S_pretrained.pdparams">Training Model</a></td>
+<td>70.9</td>
+<td>8.3008 / 2.3794</td>
+<td>10.0623 / 9.9296</td>
+<td>4.834</td>
+<td>A high-efficiency layout area localization model trained on a self-built dataset containing Chinese and English papers, magazines, contracts, books, exams, and research reports using PicoDet-S.</td>
 </tr>
 </tbody>
 </table>
+
+
 </details>
 
 <p><b>Formula Recognition Module </b></p>
@@ -274,9 +235,6 @@ The formula recognition pipeline is designed to solve formula recognition tasks
     - Document Image Orientation Classification Module: A self-built dataset using PaddleX, covering multiple scenarios such as ID cards and documents, containing 1000 images.
     - Text Image Rectification Module: [DocUNet](https://www3.cs.stonybrook.edu/~cvl/docunet.html).
     - Layout Region Detection Module: A self-built layout region detection dataset using PaddleOCR, including 500 images of common document types such as Chinese and English papers, magazines, contracts, books, exam papers, and research reports.
-    - Table Layout Detection Model: A self-built table region detection dataset using PaddleOCR, containing 7835 images of paper documents with tables in both Chinese and English.
-    - 3-Class Layout Detection Model: A self-built layout region detection dataset using PaddleOCR, including 1154 images of common document types such as Chinese and English papers, magazines, and research reports.
-    - 5-Class English Document Region Detection Model: The evaluation dataset from [PubLayNet](https://developer.ibm.com/exchanges/data/all/publaynet), containing 11245 images of English documents.
     - 17-Class Region Detection Model: A self-built layout region detection dataset using PaddleOCR, including 892 images of common document types such as Chinese and English papers, magazines, and research reports.
     - Formula Recognition Module: A self-built formula recognition test set using PaddleX.
   - **Hardware Configuration**:
@@ -288,7 +246,7 @@ The formula recognition pipeline is designed to solve formula recognition tasks
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 

+ 39 - 85
docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -99,34 +99,11 @@ comments: true
 </tbody>
 </table>
 
->❗ 以上列出的是文本识别模块重点支持的<b>3个核心模型</b>,该模块总共支持<b>11个全量模型</b>,包含多个预定义了不同类别的模型,完整的模型列表如下:
+>❗ 以上列出的是文本识别模块重点支持的<b>3个核心模型</b>,该模块总共支持<b>6个全量模型</b>,包含多个预定义了不同类别的模型,完整的模型列表如下:
 
 <details><summary> 👉模型列表详情</summary>
 
-* <b>表格版面检测模型</b>
-<table>
-<thead>
-<tr>
-<th>模型</th><th>模型下载链接</th>
-<th>mAP(0.5)(%)</th>
-<th>GPU推理耗时(ms)</th>
-<th>CPU推理耗时 (ms)</th>
-<th>模型存储大小(M)</th>
-<th>介绍</th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td>
-<td>97.5</td>
-<td>12.623</td>
-<td>90.8934</td>
-<td>7.4 M</td>
-<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型,可定位表格这1类区域</td>
-</tr>
-</tbody></table>
-
-* <b>3类版面检测模型,包含表格、图像、印章</b>
+* <b>17类区域检测模型,包含17个版面常见类别,分别是:段落标题、图片、文本、数字、摘要、内容、图表标题、公式、表格、表格标题、参考文献、文档标题、脚注、页眉、算法、页脚、印章</b>
 <table>
 <thead>
 <tr>
@@ -140,93 +117,73 @@ comments: true
 </thead>
 <tbody>
 <tr>
-<td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">训练模型</a></td>
-<td>88.2</td>
-<td>13.5</td>
-<td>45.8</td>
+<td>PicoDet-S_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_layout_17cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_17cls_pretrained.pdparams">训练模型</a></td>
+<td>87.4</td>
+<td>13.6</td>
+<td>46.2</td>
 <td>4.8</td>
 <td>基于PicoDet-S轻量模型在中英文论文、杂志和研报等场景上自建数据集训练的高效率版面区域定位模型</td>
 </tr>
 <tr>
-<td>PicoDet-L_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_layout_3cls_pretrained.pdparams">训练模型</a></td>
+<td>PicoDet-L_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_layout_17cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_layout_17cls_pretrained.pdparams">训练模型</a></td>
 <td>89.0</td>
-<td>15.7</td>
-<td>159.8</td>
+<td>17.2</td>
+<td>160.2</td>
 <td>22.6</td>
 <td>基于PicoDet-L在中英文论文、杂志和研报等场景上自建数据集训练的效率精度均衡版面区域定位模型</td>
 </tr>
 <tr>
-<td>RT-DETR-H_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-H_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-H_layout_3cls_pretrained.pdparams">训练模型</a></td>
-<td>95.8</td>
-<td>114.6</td>
-<td>3832.6</td>
-<td>470.1</td>
+<td>RT-DETR-H_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-H_layout_17cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-H_layout_17cls_pretrained.pdparams">训练模型</a></td>
+<td>98.3</td>
+<td>115.1</td>
+<td>3827.2</td>
+<td>470.2</td>
 <td>基于RT-DETR-H在中英文论文、杂志和研报等场景上自建数据集训练的高精度版面区域定位模型</td>
 </tr>
-</tbody></table>
+</tbody>
+</table>
 
-* <b>5类英文文档区域检测模型,包含文字、标题、表格、图片以及列表</b>
-<table>
-<thead>
-<tr>
-<th>模型</th><th>模型下载链接</th>
-<th>mAP(0.5)(%)</th>
-<th>GPU推理耗时(ms)</th>
-<th>CPU推理耗时 (ms)</th>
-<th>模型存储大小(M)</th>
-<th>介绍</th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td>PicoDet_layout_1x</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet_layout_1x_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_pretrained.pdparams">训练模型</a></td>
-<td>97.8</td>
-<td>13.0</td>
-<td>91.3</td>
-<td>7.4</td>
-<td>基于PicoDet-1x在PubLayNet数据集训练的高效率英文文档版面区域定位模型</td>
-</tr>
-</tbody></table>
 
-* <b>17类区域检测模型,包含17个版面常见类别,分别是:段落标题、图片、文本、数字、摘要、内容、图表标题、公式、表格、表格标题、参考文献、文档标题、脚注、页眉、算法、页脚、印章</b>
+* <b>版面检测模型,包含23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、图表标题、表格、表格标题、印章、图表标题、图表、页眉图像、页脚图像、侧栏文本</b>
 <table>
 <thead>
 <tr>
 <th>模型</th><th>模型下载链接</th>
 <th>mAP(0.5)(%)</th>
-<th>GPU推理耗时(ms)</th>
-<th>CPU推理耗时 (ms)</th>
+<th>GPU推理耗时(ms)<br/>[常规模式 / 高性能模式]</th>
+<th>CPU推理耗时(ms)<br/>[常规模式 / 高性能模式]</th>
 <th>模型存储大小(M)</th>
 <th>介绍</th>
 </tr>
 </thead>
 <tbody>
 <tr>
-<td>PicoDet-S_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_layout_17cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_17cls_pretrained.pdparams">训练模型</a></td>
-<td>87.4</td>
-<td>13.6</td>
-<td>46.2</td>
-<td>4.8</td>
-<td>基于PicoDet-S轻量模型在中英文论文、杂志和研报等场景上自建数据集训练的高效率版面区域定位模型</td>
+<td>PP-DocLayout-L</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-DocLayout-L_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-L_pretrained.pdparams">训练模型</a></td>
+<td>90.4</td>
+<td>34.6244 / 10.3945</td>
+<td>510.57 / -</td>
+<td>123.76 M</td>
+<td>基于RT-DETR-L在包含中英文论文、杂志、合同、书本、试卷和研报等场景的自建数据集训练的高精度版面区域定位模型</td>
 </tr>
 <tr>
-<td>PicoDet-L_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_layout_17cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_layout_17cls_pretrained.pdparams">训练模型</a></td>
-<td>89.0</td>
-<td>17.2</td>
-<td>160.2</td>
-<td>22.6</td>
-<td>基于PicoDet-L在中英文论文、杂志和研报等场景上自建数据集训练的效率精度均衡版面区域定位模型</td>
+<td>PP-DocLayout-M</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-DocLayout-M_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-M_pretrained.pdparams">训练模型</a></td>
+<td>75.2</td>
+<td>13.3259 / 4.8685</td>
+<td>44.0680 / 44.0680</td>
+<td>22.578</td>
+<td>基于PicoDet-L在包含中英文论文、杂志、合同、书本、试卷和研报等场景的自建数据集训练的精度效率平衡的版面区域定位模型</td>
 </tr>
 <tr>
-<td>RT-DETR-H_layout_17cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-H_layout_17cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-H_layout_17cls_pretrained.pdparams">训练模型</a></td>
-<td>98.3</td>
-<td>115.1</td>
-<td>3827.2</td>
-<td>470.2</td>
-<td>基于RT-DETR-H在中英文论文、杂志和研报等场景上自建数据集训练的高精度版面区域定位模型</td>
+<td>PP-DocLayout-S</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-DocLayout-S_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-DocLayout-S_pretrained.pdparams">训练模型</a></td>
+<td>70.9</td>
+<td>8.3008 / 2.3794</td>
+<td>10.0623 / 9.9296</td>
+<td>4.834</td>
+<td>基于PicoDet-S在中英文论文、杂志、合同、书本、试卷和研报等场景上自建数据集训练的高效率版面区域定位模型</td>
 </tr>
 </tbody>
 </table>
+
 </details>
 
 <p><b>公式识别模块:</b></p>
@@ -274,11 +231,8 @@ comments: true
 - **性能测试环境**
   - **测试数据集**:
     - 文档图像方向分类模型:PaddleX自建的数据集,覆盖证件和文档等多个场景,包含 1000 张图片。
-    - 文本图像矫正模型:<a href="https://www3.cs.stonybrook.edu/~cvl/docunet.html">DocUNet。
+    - 文本图像矫正模型:<a href="https://www3.cs.stonybrook.edu/~cvl/docunet.html">DocUNet</a>
     - 版面区域检测模型:PaddleOCR 自建的版面区域检测数据集,包含中英文论文、杂志、合同、书本、试卷和研报等常见的 500 张文档类型图片。
-    - 表格版面检测模型:PaddleOCR 自建的版面表格区域检测数据集,包含中英文 7835 张带有表格的论文文档类型图片。
-    - 3类版面检测模型:PaddleOCR 自建的版面区域检测数据集,包含中英文论文、杂志和研报等常见的 1154 张文档类型图片。
-    - 5类英文文档区域检测模型:[PubLayNet](https://developer.ibm.com/exchanges/data/all/publaynet) 的评估数据集,包含英文>文档的 11245 张文图片。
     - 17类区域检测模型:PaddleOCR 自建的版面区域检测数据集,包含中英文论文、杂志和研报等常见的 892 张文档类型图片。
     - 公式识别模型:PaddleX 内部自建公式识别测试集。
   - **硬件配置**:

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.en.md

@@ -393,7 +393,7 @@ The RepSVTR text recognition model is a mobile-oriented text recognition model b
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing_v2.en.md

@@ -591,7 +591,7 @@ SVTRv2 is a server-side text recognition model developed by the OpenOCR team fro
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md

@@ -485,7 +485,7 @@ SVTRv2 is a server text recognition model developed by the OpenOCR team of Fudan
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.en.md

@@ -173,7 +173,7 @@ SLANet_plus is an enhanced version of SLANet, a table structure recognition mode
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.en.md

@@ -427,7 +427,7 @@ SVTRv2 is a server-side text recognition model developed by the OpenOCR team fro
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>

+ 1 - 1
docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.en.md

@@ -73,7 +73,7 @@ Time series anomaly detection is a technique for identifying abnormal patterns o
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md

@@ -68,7 +68,7 @@ comments: true
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 

+ 1 - 1
docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.en.md

@@ -41,7 +41,7 @@ Time series classification is a technique that categorizes time-series data into
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 1 - 1
docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.en.md

@@ -79,7 +79,7 @@ Time series forecasting is a technique that utilizes historical data to predict
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start

+ 4 - 4
docs/pipeline_usage/tutorials/video_pipelines/video_classification.en.md

@@ -56,7 +56,7 @@ PP-TSM is a video classification model developed by Baidu PaddlePaddle's Vision
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 </details>
@@ -515,9 +515,9 @@ print(result["categories"])
 <details><summary>C++</summary>
 
 <pre><code class="language-cpp">#include &lt;iostream&gt;
-#include "cpp-httplib/httplib.h" // <url id="cun16s4432eblpu24trg" type="url" status="parsed" title="GitHub - Huiyicc/cpp-httplib: A C++ header-only HTTP/HTTPS server and client library" wc="15064">https://github.com/Huiyicc/cpp-httplib</url> 
-#include "nlohmann/json.hpp" // <url id="cun16s4432eblpu24ts0" type="url" status="parsed" title="GitHub - nlohmann/json: JSON for Modern C++" wc="80311">https://github.com/nlohmann/json</url> 
-#include "base64.hpp" // <url id="cun16s4432eblpu24tsg" type="url" status="parsed" title="GitHub - tobiaslocker/base64: A modern C++ base64 encoder / decoder" wc="2293">https://github.com/tobiaslocker/base64</url> 
+#include "cpp-httplib/httplib.h" // <url id="cun16s4432eblpu24trg" type="url" status="parsed" title="GitHub - Huiyicc/cpp-httplib: A C++ header-only HTTP/HTTPS server and client library" wc="15064">https://github.com/Huiyicc/cpp-httplib</url>
+#include "nlohmann/json.hpp" // <url id="cun16s4432eblpu24ts0" type="url" status="parsed" title="GitHub - nlohmann/json: JSON for Modern C++" wc="80311">https://github.com/nlohmann/json</url>
+#include "base64.hpp" // <url id="cun16s4432eblpu24tsg" type="url" status="parsed" title="GitHub - tobiaslocker/base64: A modern C++ base64 encoder / decoder" wc="2293">https://github.com/tobiaslocker/base64</url>
 
 int main() {
     httplib::Client client("localhost:8080");

+ 1 - 1
docs/pipeline_usage/tutorials/video_pipelines/video_detection.en.md

@@ -45,7 +45,7 @@ YOWO is a single-stage network with two branches. One branch extracts spatial fe
 
 | Mode        | GPU Configuration                        | CPU Configuration | Acceleration Technology Combination                   |
 |-------------|----------------------------------------|-------------------|---------------------------------------------------|
-| Regular Mode| FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
+| Normal Mode | FP32 Precision / No TRT Acceleration   | FP32 Precision / 8 Threads | PaddleInference                                 |
 | High-Performance Mode | Optimal combination of pre-selected precision types and acceleration strategies | FP32 Precision / 8 Threads | Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.) |
 
 ## 2. Quick Start