Quellcode durchsuchen

Fix en docs (#3309)

* fix OVS doc

* fix modules docs

* fix tutorial docs

* fix sth

* fix sth

* fix_en_doxs
Zhang Zelun vor 9 Monaten
Ursprung
Commit
feecb58778

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

@@ -235,7 +235,7 @@ Related methods, parameters, and explanations are as follows:
 </table>
 
 * The `model_name` must be specified. After specifying `model_name`, the default model parameters built into PaddleX are used. If `model_dir` is specified, the user-defined model is used.
-* `threshold` is the threshold for filtering low-confidence objects. The default is `None`, which means using the settings from the previous layer. The priority of parameter settings from highest to lowest is: `predict parameter &gt; create_model initialization &gt; yaml configuration file`.
+* `threshold` is the threshold for filtering low-confidence objects. The default is `None`, which means using the settings from the lower priority. The priority of parameter settings from highest to lowest is: `predict parameter > create_model initialization > yaml configuration file`.
 
 * The `predict()` method of the general instance segmentation model is called for inference prediction. The `predict()` method has parameters `input`, `batch_size`, and `threshold`, which are explained as follows:
 
@@ -277,7 +277,7 @@ Related methods, parameters, and explanations are as follows:
 <td><code>float</code>/<code>None</code></td>
 <td>
 <ul>
-<li><b>None</b>, indicating the use of settings from the previous layer. The priority of parameter settings from highest to lowest is: <code>predict parameter &gt; create_model initialization &gt; yaml configuration file</code></li>
+<li><b>None</b>, indicating the use of settings from the lower priority. The priority of parameter settings from highest to lowest is: <code>predict parameter &gt; create_model initialization &gt; yaml configuration file</code></li>
 <li><b>float</b>, such as 0.5, indicating the use of <code>0.5</code> as the threshold for filtering low-confidence objects during inference</li>
 </ul>
 </td>

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

@@ -106,7 +106,7 @@ Related methods, parameters, and explanations are as follows:
 </table>
 
 * The `model_name` must be specified. After specifying `model_name`, the default model parameters built into PaddleX are used. If `model_dir` is specified, the user-defined model is used.
-* `threshold` is the threshold for filtering low-confidence objects. The default is `None`, which means using the settings from the previous layer. The priority of parameter settings from highest to lowest is: `predict parameter > create_model initialization > yaml configuration file`. Currently, two types of threshold settings are supported:
+* `threshold` is the threshold for filtering low-confidence objects. The default is `None`, which means using the settings from the lower priority. The priority of parameter settings from highest to lowest is: `predict parameter > create_model initialization > yaml configuration file`. Currently, two types of threshold settings are supported:
   * `float`, using the same threshold for all classes.
   * `dict`, where the key is the class ID and the value is the threshold, allowing different thresholds for different classes. Since main body detection is a single-class detection, this setting is not required.
 
@@ -150,7 +150,7 @@ Related methods, parameters, and explanations are as follows:
 <td><code>float</code>/<code>dict</code>/<code>None</code></td>
 <td>
 <ul>
-<li><b>None</b>, indicating the use of settings from the previous layer. The priority of parameter settings from highest to lowest is: <code>predict parameter > create_model initialization > yaml configuration file</code></li>
+<li><b>None</b>, indicating the use of settings from the lower priority. The priority of parameter settings from highest to lowest is: <code>predict parameter > create_model initialization > yaml configuration file</code></li>
 <li><b>float</b>, such as 0.5, indicating the use of <code>0.5</code> as the threshold for filtering low-confidence objects during inference</li>
 <li><b>dict</b>, such as <code>{0: 0.5, 1: 0.35}</code>, indicating the use of 0.5 as the threshold for class 0 and 0.35 for class 1 during inference. Since main body detection is a single-class detection, this setting is not required.</li>
 </ul>

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

@@ -105,7 +105,7 @@ Related methods, parameters, and explanations are as follows:
 </table>
 
 * The `model_name` must be specified. After specifying `model_name`, the model parameters built into PaddleX will be used by default. If `model_dir` is specified, the user-defined model will be used.
-* `thresholds` is the filtering threshold used by the model. The default is None, which means using the settings from the previous layer. The priority of parameter settings from high to low is: `predict parameter input > create_model initialization input > yaml configuration file setting`.
+* `thresholds` is the filtering threshold used by the model. The default is None, which means using the settings from the lower priority. The priority of parameter settings from high to low is: `predict parameter input > create_model initialization input > yaml configuration file setting`.
   * The GroundingDINO series of models require two thresholds during inference: box_threshold (default 0.3) and text_threshold (default 0.25). The parameter input format is `{"box_threshold": 0.3, "text_threshold": 0.25}`.
 
 * The `predict()` method of the open-vocabulary object detection model is called for inference prediction. The parameters of the `predict()` method are `input`, `batch_size`, `thresholds`, and `prompt`, with specific explanations as follows:
@@ -148,7 +148,7 @@ Related methods, parameters, and explanations are as follows:
 <td><code>dict</code>/<code>None</code></td>
 <td>
 <ul>
-  <li><b>None</b>, indicating the use of the settings from the previous layer. The priority of parameter settings from high to low is: <code>predict parameter input > create_model initialization input > yaml configuration file setting</code></li>
+  <li><b>None</b>, indicating the use of the settings from the lower priority. The priority of parameter settings from high to low is: <code>predict parameter input > create_model initialization input > yaml configuration file setting</code></li>
   <li><b>dict</b>, such as <code>{"box_threshold": 0.3, "text_threshold": 0.25}</code>, indicating that the box_threshold is set to 0.3 and the text_threshold is set to 0.25 during inference</li>
 </ul>
 </td>

+ 3 - 4
docs/module_usage/tutorials/cv_modules/rotated_object_detection.en.md

@@ -28,7 +28,6 @@ Rotated object detection is a derivative of the object detection module, specifi
 </tr>
 </table>
 <p><b>Note: The above accuracy metrics are on the <a href="https://captain-whu.github.io/DOTA/">DOTA</a> validation set mAP(0.5:0.95)。All model GPU inference times are based on an NVIDIA TRX2080 Ti machine, with precision type F16, and CPU inference speeds are based on an Intel(R) Xeon(R) Gold 5117 CPU @ 2.00GHz, with 8 threads and precision type FP32.</b></p>
-> ❗ The above listed are the rotated object detection models currently supported by paddleX,actually PaddleDetection supports<b>10</b>rotated object detection models, For a detailed model list, please refer to <a href="https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.8/configs/rotate">PaddleDetection</a>
 
 
 ## III. Quick Integration
@@ -111,11 +110,11 @@ Related methods and parameter explanations are as follows:
 
 * The `model_name` must be specified. After specifying `model_name`, the model parameters built into PaddleX will be used by default. If `model_dir` is specified, the user-defined model will be used.
 
-* `threshold` is the threshold for filtering low-score objects. The default is `None`, which means using the settings from the previous layer. The priority of parameter settings from high to low is: `predict parameter input > create_model initialization > yaml configuration file setting`. Currently, two threshold setting methods are supported:
+* `threshold` is the threshold for filtering low-score objects. The default is `None`, which means using the settings from the lower priority. The priority of parameter settings from high to low is: `predict parameter input > create_model initialization > yaml configuration file setting`. Currently, two threshold setting methods are supported:
   * `float`: Use the same threshold for all classes.
   * `dict`: The key is the class ID, and the value is the threshold, allowing different thresholds for different classes.
 
-* `img_size` is the resolution used by the model for prediction. The default is `None`, which means using the settings from the previous layer. The priority of parameter settings from high to low is: `create_model initialization > yaml configuration file setting`.
+* `img_size` is the resolution used by the model for prediction. The default is `None`, which means using the settings from the lower priority. The priority of parameter settings from high to low is: `create_model initialization > yaml configuration file setting`.
 
 * The `predict()` method of the rotated object detection model is called for inference prediction. The parameters of the `predict()` method are `input`, `batch_size`, and `threshold`, with specific explanations as follows:
 
@@ -157,7 +156,7 @@ Related methods and parameter explanations are as follows:
 <td><code>float</code>/<code>dict</code>/<code>None</code></td>
 <td>
 <ul>
-  <li><b>None</b>, indicating the use of settings from the previous layer. The priority of parameter settings from high to low is: <code>predict parameter input > create_model initialization > yaml configuration file setting</code></li>
+  <li><b>None</b>, indicating the use of settings from the lower priority. The priority of parameter settings from high to low is: <code>predict parameter input > create_model initialization > yaml configuration file setting</code></li>
   <li><b>float</b>, such as 0.5, indicating the use of <code>0.5</code> as the threshold for all classes during inference</li>
   <li><b>dict</b>, such as <code>{0: 0.5, 1: 0.35}</code>, indicating the use of 0.5 as the threshold for class 0 and 0.35 as the threshold for class 1 during inference</li>
 </ul>

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

@@ -279,7 +279,7 @@ Related methods, parameters, and explanations are as follows:
 
 * The `model_name` must be specified. After specifying `model_name`, the built-in model parameters of PaddleX are used by default. If `model_dir` is specified, the user-defined model is used.
 
-* The `target_size` is specified during initialization to set the resolution for model inference. The default value is `None`. `-1` indicates that the original image size is used for inference, and `None` indicates that the settings from the previous layer are used. The priority order for parameter settings is: `predict parameter &gt; create_model initialization &gt; yaml configuration file`.
+* The `target_size` is specified during initialization to set the resolution for model inference. The default value is `None`. `-1` indicates that the original image size is used for inference, and `None` indicates that the settings from the lower priority are used. The priority order for parameter settings is: `predict parameter > create_model initialization > yaml configuration file`.
 
 * The `predict()` method of the general semantic segmentation model is called for inference and prediction. The parameters of the `predict()` method are `input`, `batch_size`, and `target_size`, with specific explanations as follows:
 
@@ -322,7 +322,7 @@ Related methods, parameters, and explanations are as follows:
 <td>
 <ul>
 <li><b>-1</b>, indicating inference using the original image size</li>
-<li><b>None</b>, indicating the settings from the previous layer are used. The priority order for parameter settings is: <code>predict parameter &gt; create_model initialization &gt; yaml configuration file</code></li>
+<li><b>None</b>, indicating the settings from the lower priority are used. The priority order for parameter settings is: <code>predict parameter &gt; create_model initialization &gt; yaml configuration file</code></li>
 <li><b>int</b>, such as 512, indicating inference using a resolution of <code>(512, 512)</code></li>
 <li><b>tuple</b>, such as (512, 1024), indicating inference using a resolution of <code>(512, 1024)</code></li>
 </ul>

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

@@ -124,7 +124,7 @@ Related methods, parameters, and explanations are as follows:
 </table>
 
 * The `model_name` must be specified. After specifying `model_name`, the default model parameters built into PaddleX are used. If `model_dir` is specified, the user-defined model is used.
-* `threshold` is the threshold for filtering low-confidence objects. The default is `None`, which means using the settings from the previous layer. The priority of parameter settings from highest to lowest is: `predict parameter > create_model initialization > yaml configuration file`. Currently, two types of threshold settings are supported:
+* `threshold` is the threshold for filtering low-confidence objects. The default is `None`, which means using the settings from the lower priority. The priority of parameter settings from highest to lowest is: `predict parameter > create_model initialization > yaml configuration file`. Currently, two types of threshold settings are supported:
   * `float`, using the same threshold for all classes.
   * `dict`, where the key is the class ID and the value is the threshold, allowing different thresholds for different classes.
 
@@ -168,7 +168,7 @@ Related methods, parameters, and explanations are as follows:
 <td><code>float</code>/<code>dict</code>/<code>None</code></td>
 <td>
 <ul>
-<li><b>None</b>, indicating the use of settings from the previous layer. The priority of parameter settings from highest to lowest is: <code>predict parameter > create_model initialization > yaml configuration file</code></li>
+<li><b>None</b>, indicating the use of settings from the lower priority. The priority of parameter settings from highest to lowest is: <code>predict parameter > create_model initialization > yaml configuration file</code></li>
 <li><b>float</b>, such as 0.5, indicating the use of <code>0.5</code> as the threshold for filtering low-confidence objects during inference</li>
 <li><b>dict</b>, such as <code>{0: 0.5, 1: 0.35}</code>, indicating the use of 0.5 as the threshold for class 0 and 0.35 for class 1 during inference.</li>
 </ul>

+ 3 - 3
docs/module_usage/tutorials/cv_modules/vehicle_detection.en.md

@@ -110,7 +110,7 @@ Related methods, parameters, and explanations are as follows:
 
 * The `model_name` must be specified. After specifying `model_name`, the built-in model parameters of PaddleX are used by default. If `model_dir` is specified, the user-defined model is used.
 
-* The `threshold` is the threshold for filtering low-score objects. The default value is `None`, indicating that the settings from the previous layer are used. The priority order for parameter settings is: `predict parameter &gt; create_model initialization &gt; yaml configuration file`. Currently, two types of threshold settings are supported:
+* The `threshold` is the threshold for filtering low-score objects. The default value is `None`, indicating that the settings from the lower priority are used. The priority order for parameter settings is: `predict parameter > create_model initialization > yaml configuration file`. Currently, two types of threshold settings are supported:
   * `float`: Use the same threshold for all classes.
   * `dict`: The key is the class ID, and the value is the threshold. Different thresholds can be set for different classes. For vehicle detection, which is a single-class detection task, this setting is not required.
 
@@ -154,7 +154,7 @@ Related methods, parameters, and explanations are as follows:
 <td><code>float</code>/<code>dict</code>/<code>None</code></td>
 <td>
 <ul>
-<li><b>None</b>, indicating the settings from the previous layer are used. The priority order for parameter settings is: <code>predict parameter &gt; create_model initialization &gt; yaml configuration file</code></li>
+<li><b>None</b>, indicating the settings from the lower priority are used. The priority order for parameter settings is: <code>predict parameter &gt; create_model initialization &gt; yaml configuration file</code></li>
 <li><b>float</b>, such as 0.5, indicating the threshold of 0.5 is used for filtering low-score objects during inference</li>
 <li><b>dict</b>, such as <code>{0: 0.5, 1: 0.35}</code>, indicating a threshold of 0.5 for class 0 and 0.35 for class 1 during inference. Vehicle detection is a single-class detection task and does not require this setting.</li>
 </ul>
@@ -430,4 +430,4 @@ Other related parameters can be set by modifying the fields under `Global` and `
 
 #### 4.4.2 Model Integration
 The weights you produced can be directly integrated into the vehicle 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.
-</table>
+</table>

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

@@ -1034,7 +1034,7 @@ SubModules:
   InstanceSegmentation:
     module_name: instance_segmentation
     model_name: Mask-RT-DETR-S
-    model_dir: null # 替换为微调后的实例分割模型权重路径
+    model_dir: null # Here replaced with the newly fine-tuned weight path.
     batch_size: 1
     threshold: 0.5
 ```

+ 5 - 5
docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.en.md

@@ -537,9 +537,9 @@ print(result["detectedObjects"])
 <details><summary>C++</summary>
 
 <pre><code class="language-cpp">#include &lt;iostream&gt;
-#include &quot;cpp-httplib/httplib.h&quot; // <url id="cu9pu8852ceh1d3h24gg" 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 &quot;nlohmann/json.hpp&quot; // <url id="cu9pu8852ceh1d3h24h0" type="url" status="parsed" title="GitHub - nlohmann/json: JSON for Modern C++" wc="80311">https://github.com/nlohmann/json</url> 
-#include &quot;base64.hpp&quot; // <url id="cu9pu8852ceh1d3h24hg" type="url" status="parsed" title="GitHub - tobiaslocker/base64: A modern C++ base64 encoder / decoder" wc="2293">https://github.com/tobiaslocker/base64</url> 
+#include &quot;cpp-httplib/httplib.h&quot; // <url id="cu9pu8852ceh1d3h24gg" 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 &quot;nlohmann/json.hpp&quot; // <url id="cu9pu8852ceh1d3h24h0" type="url" status="parsed" title="GitHub - nlohmann/json: JSON for Modern C++" wc="80311">https://github.com/nlohmann/json</url>
+#include &quot;base64.hpp&quot; // <url id="cu9pu8852ceh1d3h24hg" 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(&quot;localhost:8080&quot;);
@@ -969,7 +969,7 @@ SubModules:
   RotatedObjectDetection:
     module_name: rotated_object_detection
     model_name: PP-YOLOE-R-L
-    model_dir: null # 替换为微调后的旋转目标检测模型权重路径
+    model_dir: null # Here replaced with the newly fine-tuned weight path.
     batch_size: 1
     threshold: 0.5
 ```
@@ -989,4 +989,4 @@ paddlex --pipeline rotated_object_detection \
         --device npu:0
 ```
 
-If you want to use rotated object detection on more types of hardware, please refer to the [PaddleX Multi-Hardware Usage Guide](../../../other_devices_support/multi_devices_use_guide.en.md).
+If you want to use rotated object detection on more types of hardware, please refer to the [PaddleX Multi-Hardware Usage Guide](../../../other_devices_support/multi_devices_use_guide.en.md).

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

@@ -990,7 +990,7 @@ SubModules:
   SemanticSegmentation:
     module_name: semantic_segmentation
     model_name: PP-LiteSeg-T
-    model_dir: null # 替换为微调后的语义分割模型权重路径
+    model_dir: null # Here replaced with the newly fine-tuned weight path.
     batch_size: 1
     target_size: None
 ```

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

@@ -886,7 +886,7 @@ SubModules:
   SmallObjectDetection:
     module_name: small_object_detection
     model_name: PP-YOLOE_plus_SOD-L
-    model_dir: null # 替换为微调后的小目标检测模型权重路径
+    model_dir: null # Here replaced with the newly fine-tuned weight path.
     batch_size: 1
     threshold: 0.5
 ```