[Feat] Support textline_orientation for chatocr and unify naming of text line orientation (#15337)

* Support textline_orientation for chatocr and unify naming of textline orientation

* Unify description

* Update documentation

* Fix serving doc

Author: Bobholamovic

docs/version3.x/module_usage/text_line_orientation_classification.en.md renamed to docs/version3.x/module_usage/textline_orientation_classification.en.md

@@ -92,8 +92,8 @@ The text line orientation classification module primarily distinguishes the orie
 You can quickly experience the functionality with a single command:
 
 ```bash
-paddleocr text_line_orientation_classification -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/textline_rot180_demo.jpg
-```
+paddleocr textline_orientation_classification -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/textline_rot180_demo.jpg
+```  
 
 You can also integrate the text line orientation classification model into your project. Run the following code after downloading the [example image](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/textline_rot180_demo.jpg) to your local machine. 
 

docs/version3.x/module_usage/text_line_orientation_classification.md renamed to docs/version3.x/module_usage/textline_orientation_classification.md

@@ -96,7 +96,7 @@ comments: true
 使用一行命令即可快速体验：
 
 ```bash
-paddleocr text_line_orientation_classification -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/textline_rot180_demo.jpg
+paddleocr textline_orientation_classification -i https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/textline_rot180_demo.jpg
 ```
 
 您也可以将文本行方向分类模块中的模型推理集成到您的项目中。运行以下代码前，请您下载[示例图片](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/textline_rot180_demo.jpg)到本地。

docs/version3.x/pipeline_usage/OCR.en.md

@@ -16,7 +16,7 @@ The general OCR pipeline is used to solve text recognition tasks by extracting t
 
 - [Document Image Orientation Classification Module](../module_usage/doc_img_orientation_classification.md) (Optional)
 - [Text Image Unwarping Module](../module_usage/text_image_unwarping.md) (Optional)
-- [Text Line Orientation Classification Module](../module_usage/text_line_orientation_classification.md) (Optional)
+- [Text Line Orientation Classification Module](../module_usage/textline_orientation_classification.md) (Optional)
 - [Text Detection Module](../module_usage/text_detection.md)
 - [Text Recognition Module](../module_usage/text_recognition.md)
 
@@ -592,19 +592,19 @@ paddleocr ocr -i ./general_ocr_002.png --ocr_version PP-OCRv4
 <td></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_model_name</code></td>
+<td><code>textline_orientation_model_name</code></td>
 <td>Name of the text line orientation model. If not set, the pipeline default model will be used.</td>
 <td><code>str</code></td>
 <td></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_model_dir</code></td>
+<td><code>textline_orientation_model_dir</code></td>
 <td>Directory path of the text line orientation model. If not set, the official model will be downloaded.</td>
 <td><code>str</code></td>
 <td></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_batch_size</code></td>
+<td><code>textline_orientation_batch_size</code></td>
 <td>Batch size for the text line orientation model. If not set, the default batch size will be <code>1</code>.</td>
 <td><code>int</code></td>
 <td></td>
@@ -794,13 +794,13 @@ Any floating-point number greater than <code>0</code>. If not set, the pipeline'
 </tr>
 <tr>
 <td><code>cls_model_dir</code></td>
-<td>Deprecated. Please refer <code>text_line_orientation_model_dir</code> , they cannot be specified simultaneously with the new parameters.</td>
+<td>Deprecated. Please refer <code>textline_orientation_model_dir</code> , they cannot be specified simultaneously with the new parameters.</td>
 <td><code>str</code></td>
 <td></td>
 </tr>
 <tr>
 <td><code>cls_batch_num</code></td>
-<td>Deprecated. Please refer <code>text_line_orientation_batch_size</code> , they cannot be specified simultaneously with the new parameters.</td>
+<td>Deprecated. Please refer <code>textline_orientation_batch_size</code> , they cannot be specified simultaneously with the new parameters.</td>
 <td><code>int</code></td>
 <td></td>
 </tr>
@@ -975,19 +975,19 @@ In the above Python script, the following steps are performed:
  <td><code>None</code></td>
  </tr>
  <tr>
- <td><code>text_line_orientation_model_name</code></td>
+ <td><code>textline_orientation_model_name</code></td>
  <td>Name of the text line orientation model. If set to <code>None</code>, the pipeline's default model will be used.</td>
  <td><code>str</code></td>
  <td><code>None</code></td>
  </tr>
  <tr>
- <td><code>text_line_orientation_model_dir</code></td>
+ <td><code>textline_orientation_model_dir</code></td>
  <td>Directory path of the text line orientation model. If set to <code>None</code>, the official model will be downloaded.</td>
  <td><code>str</code></td>
  <td><code>None</code></td>
  </tr>
  <tr>
- <td><code>text_line_orientation_batch_size</code></td>
+ <td><code>textline_orientation_batch_size</code></td>
  <td>Batch size for the text line orientation model. If set to <code>None</code>, the default batch size will be <code>1</code>.</td>
  <td><code>int</code></td>
  <td><code>None</code></td>

docs/version3.x/pipeline_usage/OCR.md

@@ -16,7 +16,7 @@ OCR（光学字符识别，Optical Character Recognition）是一种将图像中
 
 - [文档图像方向分类模块](../module_usage/doc_img_orientation_classification.md) （可选）
 - [文本图像矫正模块](../module_usage/text_image_unwarping.md) （可选）
-- [文本行方向分类模块](../module_usage/text_line_orientation_classification.md) （可选）
+- [文本行方向分类模块](../module_usage/textline_orientation_classification.md) （可选）
 - [文本检测模块](../module_usage/text_detection.md)
 - [文本识别模块](../module_usage/text_recognition.md)
 
@@ -592,19 +592,19 @@ paddleocr ocr -i ./general_ocr_002.png --ocr_version PP-OCRv4
 <td></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_model_name</code></td>
+<td><code>textline_orientation_model_name</code></td>
 <td>文本行方向模型的名称。如果不设置，将会使用产线默认模型。</td>
 <td><code>str</code></td>
 <td></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_model_dir</code></td>
+<td><code>textline_orientation_model_dir</code></td>
 <td>文本行方向模型的目录路径。如果不设置，将会下载官方模型。</td>
 <td><code>str</code></td>
 <td></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_batch_size</code></td>
+<td><code>textline_orientation_batch_size</code></td>
 <td>文本行方向模型的批处理大小。如果不设置，将默认设置批处理大小为<code>1</code>。</td>
 <td><code>int</code></td>
 <td></td>
@@ -792,13 +792,13 @@ paddleocr ocr -i ./general_ocr_002.png --ocr_version PP-OCRv4
 </tr>
 <tr>
 <td><code>cls_model_dir</code></td>
-<td>已废弃，请参考<code>text_line_orientation_model_dir</code>，且与新的参数不能同时指定。</td>
+<td>已废弃，请参考<code>textline_orientation_model_dir</code>，且与新的参数不能同时指定。</td>
 <td><code>str</code></td>
 <td></td>
 </tr>
 <tr>
 <td><code>cls_batch_num</code></td>
-<td>已废弃，请参考<code>text_line_orientation_batch_size</code>，且与新的参数不能同时指定。</td>
+<td>已废弃，请参考<code>textline_orientation_batch_size</code>，且与新的参数不能同时指定。</td>
 <td><code>int</code></td>
 <td></td>
 </tr>
@@ -973,19 +973,19 @@ for res in result:
 <td><code>None</code></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_model_name</code></td>
+<td><code>textline_orientation_model_name</code></td>
 <td>文本行方向模型的名称。如果设置为<code>None</code>，将会使用产线默认模型。</td>
 <td><code>str</code></td>
 <td><code>None</code></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_model_dir</code></td>
+<td><code>textline_orientation_model_dir</code></td>
 <td>文本行方向模型的目录路径。如果设置为<code>None</code>，将会下载官方模型。</td>
 <td><code>str</code></td>
 <td><code>None</code></td>
 </tr>
 <tr>
-<td><code>text_line_orientation_batch_size</code></td>
+<td><code>textline_orientation_batch_size</code></td>
 <td>文本行方向模型的批处理大小。如果设置为<code>None</code>，将默认设置批处理大小为<code>1</code>。</td>
 <td><code>int</code></td>
 <td><code>None</code></td>

docs/version3.x/pipeline_usage/PP-ChatOCRv4.en.md

@@ -664,6 +664,12 @@ The name of the document orientation classification model. If not set, the defau
 <td></td>
 </tr>
 <tr>
+<td><code>use_textline_orientation</code></td>
+<td>Whether to load and use the text line orientation classification module. If not set, the parameter value initialized by the pipeline will be used by default, initialized as <code>True</code>.</td>
+<td><code>bool</code></td>
+<td></td>
+</tr>
+<tr>
 <td><code>use_seal_recognition</code></td>
 <td>Whether to load and use the seal recognition sub-pipeline. If not set, the parameter's value initialized during pipeline setup will be used, defaulting to <code>True</code>.</td>
 <td><code>bool</code></td>
@@ -1106,6 +1112,12 @@ The relevant parameter descriptions are as follows:
 <td><code>None</code></td>
 </tr>
 <tr>
+<td><code>use_textline_orientation</code></td>
+<td>Whether to load and use the text line orientation classification function. If set to<code>None</code>, the value initialized by the pipeline for this parameter will be used by default (initialized to <code>True</code>).</td>
+<td><code>bool</code></td>
+<td><code>None</code></td>
+</tr>
+<tr>
 <td><code>use_seal_recognition</code></td>
 <td>Whether to load and use the seal recognition sub-pipeline. If set to<code>None</code>, the value initialized by the pipeline for this parameter will be used by default (initialized to <code>True</code>).</td>
 <td><code>bool</code></td>
@@ -1418,7 +1430,13 @@ The relevant parameter descriptions are as follows:
 </tr>
 <tr>
 <td><code>use_doc_unwarping</code></td>
-<td>Whether to use the text image correction module during inference.</td>
+<td>Whether to use the document image unwarping module during inference.</td>
+<td><code>bool</code></td>
+<td><code>None</code></td>
+</tr>
+<tr>
+<td><code>use_textline_orientation</code></td>
+<td>Whether to use the text line orientation classification module during inference.</td>
 <td><code>bool</code></td>
 <td><code>None</code></td>
 </tr>

docs/version3.x/pipeline_usage/PP-ChatOCRv4.md

@@ -20,7 +20,7 @@ PP-ChatOCRv4 产线中包含<b>版面区域检测模块</b>、<b>表格结构识
 - [表格结构识别模块](../module_usage/table_structure_recognition.md)（可选）
 - [文本检测模块](../module_usage/text_detection.md)
 - [文本识别模块](../module_usage/text_recognition.md)
-- [文本行方向分类模块](../module_usage/text_line_orientation_classification.md)（可选）
+- [文本行方向分类模块](../module_usage/textline_orientation_classification.md)（可选）
 - [公式识别模块](../module_usage/formula_recognition.md)（可选）
 - [印章文本检测模块](../module_usage/seal_text_detection.md)（可选）
 
@@ -905,13 +905,19 @@ paddleocr pp_chatocrv4_doc -i vehicle_certificate-1.png -k 驾驶室准乘人数
 </tr>
 <tr>
 <td><code>use_doc_orientation_classify</code></td>
-<td>是否加载并使用文档方向分类功能。如果不设置，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
+<td>是否加载并使用文档方向分类模块。如果不设置，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
 <td><code>bool</code></td>
 <td></td>
 </tr>
 <tr>
 <td><code>use_doc_unwarping</code></td>
-<td>是否加载并使用文档去扭曲功能。如果不设置，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
+<td>是否加载并使用文档去扭曲模块。如果不设置，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
+<td><code>bool</code></td>
+<td></td>
+</tr>
+<tr>
+<td><code>use_textline_orientation</code></td>
+<td>是否加载并使用文本行方向分类模块。如果不设置，初始化为<code>True</code>。</td>
 <td><code>bool</code></td>
 <td></td>
 </tr>
@@ -1325,13 +1331,19 @@ PP-ChatOCRv4 预测的流程、API说明、产出说明如下：
 </tr>
 <tr>
 <td><code>use_doc_orientation_classify</code></td>
-<td>是否加载并使用文档方向分类功能。如果设置为<code>None</code>，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
+<td>是否加载并使用文档方向分类模块。如果设置为<code>None</code>，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
 <td><code>bool</code></td>
 <td><code>None</code></td>
 </tr>
 <tr>
 <td><code>use_doc_unwarping</code></td>
-<td>是否加载并使用文档去扭曲功能。如果设置为<code>None</code>，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
+<td>是否加载并使用文档去扭曲模块。如果设置为<code>None</code>，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
+<td><code>bool</code></td>
+<td><code>None</code></td>
+</tr>
+<tr>
+<td><code>use_textline_orientation</code></td>
+<td>是否加载并使用文本行方向分类模块. 如果设置为<code>None</code>，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
 <td><code>bool</code></td>
 <td><code>None</code></td>
 </tr>
@@ -1655,6 +1667,12 @@ PP-ChatOCRv4 预测的流程、API说明、产出说明如下：
 <td><code>None</code></td>
 </tr>
 <tr>
+<td><code>use_textline_orientation</code></td>
+<td>是否加载并使用文本行方向分类模块。</td>
+<td><code>bool</code></td>
+<td><code>None</code></td>
+</tr>
+<tr>
 <td><code>use_seal_recognition</code></td>
 <td>是否在推理时使用印章识别子产线。</td>
 <td><code>bool</code></td>

docs/version3.x/pipeline_usage/PP-StructureV3.md

@@ -1382,7 +1382,7 @@ paddleocr pp_structurev3 -i ./pp_structure_v3_demo.png --device gpu
 </tr>
 <tr>
 <td><code>use_textline_orientation</code></td>
-<td>是否加载并使用文本行方向分类模块。 如果不设置, default is <code>True</code>。</td>
+<td>是否加载并使用文本行方向分类模块。如果不设置，初始化为<code>True</code>。</td>
 <td><code>bool</code></td>
 <td></td>
 </tr>
@@ -1987,7 +1987,7 @@ for item in markdown_images:
 </tr>
 <tr>
 <td><code>use_textline_orientation</code></td>
-<td>是否加载并使用文本行方向分类模块. 如果设置为<code>None</code>, default is <code>True</code>.</td>
+<td>是否加载并使用文本行方向分类模块。如果设置为<code>None</code>，将默认使用产线初始化的该参数值，初始化为<code>True</code>。</td>
 <td><code>bool</code></td>
 <td><code>None</code></td>
 </tr>

docs/version3.x/pipeline_usage/table_recognition_v2.en.md

@@ -1872,30 +1872,6 @@ Below is the API reference for basic service-oriented deployment and examples of
 <td>No</td>
 </tr>
 <tr>
-<td><code>layoutThreshold</code></td>
-<td><code>number</code> | <code>null</code></td>
-<td>Please refer to the <code>layout_threshold</code> parameter description in the <code>predict</code> method of the model object.</td>
-<td>No</td>
-</tr>
-<tr>
-<td><code>layoutNms</code></td>
-<td><code>boolean</code> | <code>null</code></td>
-<td>Please refer to the <code>layout_nms</code> parameter description in the <code>predict</code> method of the model object.</td>
-<td>No</td>
-</tr>
-<tr>
-<td><code>layoutUnclipRatio</code></td>
-<td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>Please refer to the <code>layout_unclip_ratio</code> parameter description in the <code>predict</code> method of the model object.</td>
-<td>No</td>
-</tr>
-<tr>
-<td><code>layoutMergeBboxesMode</code></td>
-<td><code>string</code> | <code>null</code></td>
-<td>Please refer to the <code>layout_merge_bboxes_mode</code> parameter description in the <code>predict</code> method of the model object.</td>
-<td>No</td>
-</tr>
-<tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
 <td>Please refer to the <code>text_det_limit_side_len</code> parameter description in the <code>predict</code> method of the model object.</td>

docs/version3.x/pipeline_usage/table_recognition_v2.md

@@ -1875,30 +1875,6 @@ for res in output:
 <td>否</td>
 </tr>
 <tr>
-<td><code>layoutThreshold</code></td>
-<td><code>number</code> | <code>null</code></td>
-<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_threshold</code> 参数相关说明。</td>
-<td>否</td>
-</tr>
-<tr>
-<td><code>layoutNms</code></td>
-<td><code>boolean</code> | <code>null</code></td>
-<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_nms</code> 参数相关说明。</td>
-<td>否</td>
-</tr>
-<tr>
-<td><code>layoutUnclipRatio</code></td>
-<td><code>number</code> | <code>array</code> | <code>null</code></td>
-<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_unclip_ratio</code> 参数相关说明。</td>
-<td>否</td>
-</tr>
-<tr>
-<td><code>layoutMergeBboxesMode</code></td>
-<td><code>string</code> | <code>null</code></td>
-<td>请参阅产线对象中 <code>predict</code> 方法的 <code>layout_merge_bboxes_mode</code> 参数相关说明。</td>
-<td>否</td>
-</tr>
-<tr>
 <td><code>textDetLimitSideLen</code></td>
 <td><code>integer</code> | <code>null</code></td>
 <td>请参阅产线对象中 <code>predict</code> 方法的 <code>text_det_limit_side_len</code> 参数相关说明。</td>

mkdocs.yml

@@ -290,7 +290,7 @@ nav:
     - 表格结构识别模块: version3.x/module_usage/table_structure_recognition.md
     - 文本检测模块: version3.x/module_usage/text_detection.md
     - 文本图像矫正模块: version3.x/module_usage/text_image_unwarping.md
-    - 文本行方向分类模块: version3.x/module_usage/text_line_orientation_classification.md
+    - 文本行方向分类模块: version3.x/module_usage/textline_orientation_classification.md
     - 文本识别模块: version3.x/module_usage/text_recognition.md
   - 产线列表: 
     - 产线概述: version3.x/pipeline_usage/pipeline_overview.md