Refine ocr docs (#2242)

* Update paddlepaddle_install.md

* Update paddlepaddle_install_en.md

* refine docs

* refine docs

* refine

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md

@@ -24,7 +24,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，您可
 ### 2.1 命令行方式体验
 一行命令即可快速体验图像异常检测产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/uad_grid.png)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline anomaly_detection --input uad_grid.png --device gpu:0
 ```
 参数说明：
@@ -52,8 +52,8 @@ paddlex --get_pipeline_config anomaly_detection --save_path ./my_path
 
 获取产线配置文件后，可将 --pipeline 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./anomaly_detection.yaml`，只需执行：
 
-```
-paddlex --pipeline ./anomaly_detection.yaml --input uad_grid.png
+```bash
+paddlex --pipeline ./anomaly_detection.yaml --input uad_grid.png --device gpu:0
 ```
 
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
@@ -63,7 +63,7 @@ paddlex --pipeline ./anomaly_detection.yaml --input uad_grid.png
 运行后，得到的结果为：
 
 ```
-{'img_path': '/root/.paddlex/predict_input/uad_grid.png'}
+{'input_path': 'uad_grid.png'}
 ```
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_anomaly_detection/02.png)
 

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection_en.md

@@ -5,7 +5,7 @@
 ## 1. Introduction to Image Anomaly Detection Pipeline
 Image anomaly detection is an image processing technique that identifies unusual or non-conforming patterns within images through analysis. It is widely applied in industrial quality inspection, medical image analysis, and security monitoring. By leveraging machine learning and deep learning algorithms, image anomaly detection can automatically recognize potential defects, anomalies, or abnormal behaviors in images, enabling us to promptly identify issues and take corresponding actions. The image anomaly detection system is designed to automatically detect and mark anomalies in images, enhancing work efficiency and accuracy.
 
-![](/tmp/images/pipelines/image_anomaly_detection/01.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_anomaly_detection/01.png)
 
 **The image anomaly detection pipeline includes an unsupervised anomaly detection module, with the following model benchmarks**:
 
@@ -52,7 +52,7 @@ paddlex --get_pipeline_config anomaly_detection --save_path ./my_path
 After obtaining the pipeline configuration file, replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./anomaly_detection.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./anomaly_detection.yaml --input uad_grid.png
+paddlex --pipeline ./anomaly_detection.yaml --input uad_grid.png --device gpu:0
 ```
 
 Here, parameters such as `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If parameters are still specified, the specified parameters will take precedence.
@@ -62,9 +62,9 @@ Here, parameters such as `--model` and `--device` do not need to be specified, a
 After running, the result is:
 
 ```
-{'img_path': '/root/.paddlex/predict_input/uad_grid.png'}
+{'input_path': 'uad_grid.png'}
 ```
-![](/tmp/images/pipelines/image_anomaly_detection/02.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_anomaly_detection/02.png)
 
 The visualized image not saved by default. You can customize the save path through `--save_path`, and then all results will be saved in the specified path.
 

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md

@@ -627,7 +627,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验图像分类产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline image_classification --input general_image_classification_001.jpg --device gpu:0
 ```
 参数说明：
@@ -654,8 +654,8 @@ paddlex --get_pipeline_config image_classification --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./image_classification.yaml`，只需执行：
 
-```
-paddlex --pipeline ./image_classification.yaml --input general_image_classification_001.jpg
+```bash
+paddlex --pipeline ./image_classification.yaml --input general_image_classification_001.jpg --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -664,7 +664,7 @@ paddlex --pipeline ./image_classification.yaml --input general_image_classificat
 运行后，得到的结果为：
 
 ```
-{'img_path': './my_path/general_image_classification_001.jpg', 'class_ids': [296, 170, 356, 258, 248], 'scores': [0.62736, 0.03752, 0.03256, 0.0323, 0.03194], 'label_names': ['ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 'Irish wolfhound', 'weasel', 'Samoyed, Samoyede', 'Eskimo dog, husky']}
+{'input_path': 'general_image_classification_001.jpg', 'class_ids': [296, 170, 356, 258, 248], 'scores': [0.62736, 0.03752, 0.03256, 0.0323, 0.03194], 'label_names': ['ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 'Irish wolfhound', 'weasel', 'Samoyed, Samoyede', 'Eskimo dog, husky']}
 ```
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_classification/03.png)
 
@@ -1234,12 +1234,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行图像分类产线的推理，使用的命令为：
 
-```
+```bash
 paddlex --pipeline image_classification --input general_image_classification_001.jpg --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需将 `--device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline image_classification --input general_image_classification_001.jpg --device npu:0
 ```
 若您想在更多种类的硬件上使用通用图像分类产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/cv_pipelines/image_classification_en.md

@@ -5,7 +5,7 @@
 ## 1. Introduction to the General Image Classification Pipeline
 Image classification is a technique that assigns images to predefined categories. It is widely applied in object recognition, scene understanding, and automatic annotation. Image classification can identify various objects such as animals, plants, traffic signs, and categorize them based on their features. By leveraging deep learning models, image classification can automatically extract image features and perform accurate classification.
 
-![](/tmp/images/pipelines/image_classification/01.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_classification/01.png)
 
 **The General Image Classification Pipeline includes an image classification module. If you prioritize model accuracy, choose a model with higher accuracy. If you prioritize inference speed, select a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage size.**
 
@@ -616,7 +616,7 @@ PaddleX provides pre-trained model pipelines that can be quickly experienced. Yo
 ### 2.1 Online Experience
 You can [experience online](https://aistudio.baidu.com/community/app/100061/webUI) the effects of the General Image Classification Pipeline using the demo images provided by the official. For example:
 
-![](/tmp/images/pipelines/image_classification/02.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_classification/02.png)
 
 If you are satisfied with the pipeline's performance, you can directly integrate and deploy it. If not, you can also use your private data to **fine-tune the model within the pipeline**.
 
@@ -654,7 +654,7 @@ paddlex --get_pipeline_config image_classification --save_path ./my_path
 After obtaining the pipeline configuration file, replace `--pipeline` with the configuration file's save path to make the configuration file take effect. For example, if the configuration file's save path is `./image_classification.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./image_classification.yaml --input general_image_classification_001.jpg
+paddlex --pipeline ./image_classification.yaml --input general_image_classification_001.jpg --device gpu:0
 ```
 Here, parameters such as `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If you still specify parameters, the specified parameters will take precedence.
 
@@ -663,9 +663,9 @@ Here, parameters such as `--model` and `--device` do not need to be specified, a
 After running, the result will be:
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_image_classification_001.jpg', 'class_ids': [296, 170, 356, 258, 248], 'scores': [0.62736, 0.03752, 0.03256, 0.0323, 0.03194], 'label_names': ['ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 'Irish wolfhound', 'weasel', 'Samoyed, Samoyede', 'Eskimo dog, husky']}
+{'input_path': 'general_image_classification_001.jpg', 'class_ids': [296, 170, 356, 258, 248], 'scores': [0.62736, 0.03752, 0.03256, 0.0323, 0.03194], 'label_names': ['ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 'Irish wolfhound', 'weasel', 'Samoyed, Samoyede', 'Eskimo dog, husky']}
 ```
-![](/tmp/images/pipelines/image_classification/03.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_classification/03.png)
 
 
 The visualized image not saved by default. You can customize the save path through `--save_path`, and then all results will be saved in the specified path.

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -35,7 +35,7 @@ PaddleX 支持在本地使用命令行或 Python 体验通用图像多标签分
 ### 2.1 命令行方式体验
 一行命令即可快速体验图像多标签分类产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline multi_label_image_classification --input general_image_classification_001.jpg --device gpu:0
 ```
 参数说明：
@@ -62,8 +62,8 @@ paddlex --get_pipeline_config multi_label_image_classification --save_path ./my_
 
 获取产线配置文件后，可将 --pipeline 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./multi_label_image_classification.yaml`，只需执行：
 
-```
-paddlex --pipeline ./multi_label_image_classification.yaml --input general_image_classification_001.jpg
+```bash
+paddlex --pipeline ./multi_label_image_classification.yaml --input general_image_classification_001.jpg --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -73,7 +73,7 @@ paddlex --pipeline ./multi_label_image_classification.yaml --input general_image
 运行后，得到的结果为：
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_image_classification_001.jpg', 'class_ids': [21, 0, 30, 24], 'scores': [0.99257, 0.70596, 0.63001, 0.57852], 'label_names': ['bear', 'person', 'skis', 'backpack']}
+{'input_path': 'general_image_classification_001.jpg', 'class_ids': [21, 0, 30, 24], 'scores': [0.99257, 0.70596, 0.63001, 0.57852], 'label_names': ['bear', 'person', 'skis', 'backpack']}
 ```
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_multi_label_classification/02.png)
 
@@ -643,12 +643,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行图像多标签分类产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline multi_label_image_classification --input general_image_classification_001.jpg --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline multi_label_image_classification --input general_image_classification_001.jpg --device npu:0
 ```
 若您想在更多种类的硬件上使用通用图像多标签分类产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification_en.md

@@ -60,7 +60,7 @@ paddlex --get_pipeline_config multi_label_image_classification --save_path ./my_
 After obtaining the pipeline configuration file, replace `--pipeline` with the saved path of the configuration file to make it effective. For example, if the configuration file is saved at `./multi_label_image_classification.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./multi_label_image_classification.yaml --input https://paddle-model-ecology.bj
+paddlex --pipeline ./multi_label_image_classification.yaml --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg --device gpu:0
 ```
 
 Where `--model`, `--device`, and other parameters are not specified, the parameters in the configuration file will be used. If parameters are specified, the specified parameters will take precedence.
@@ -70,7 +70,7 @@ Where `--model`, `--device`, and other parameters are not specified, the paramet
 After running, the result obtained is:
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_image_classification_001.jpg', 'class_ids': [21, 0, 30, 24], 'scores': [0.99257, 0.70596, 0.63001, 0.57852], 'label_names': ['bear', 'person', 'skis', 'backpack']}
+{'input_path': 'general_image_classification_001.jpg', 'class_ids': [21, 0, 30, 24], 'scores': [0.99257, 0.70596, 0.63001, 0.57852], 'label_names': ['bear', 'person', 'skis', 'backpack']}
 ```
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/image_multi_label_classification/02.png)
 
@@ -626,7 +626,8 @@ paddlex --pipeline multi_label_image_classification --input https://paddle-model
 ```
 
 At this point, if you wish to switch the hardware to Ascend NPU, simply modify the `--device` in the Python command to `npu:0`:
-```
+
+```bash
 paddlex --pipeline multi_label_image_classification --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg --device npu:0
 ```
 If you want to use the General Image Multi-label Classification Pipeline on more diverse hardware, please refer to the [PaddleX Multi-device Usage Guide](../../../installation/multi_devices_use_guide_en.md).

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md

@@ -50,7 +50,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验实例分割产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_instance_segmentation_004.png)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline instance_segmentation --input general_instance_segmentation_004.png --device gpu:0
 ```
 参数说明：
@@ -77,8 +77,8 @@ paddlex --get_pipeline_config instance_segmentation --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 ./instance_segmentation.yaml，只需执行：
 
-```
-paddlex --pipeline ./instance_segmentation.yaml --input general_instance_segmentation_004.png
+```bash
+paddlex --pipeline ./instance_segmentation.yaml --input general_instance_segmentation_004.png --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -87,7 +87,7 @@ paddlex --pipeline ./instance_segmentation.yaml --input general_instance_segment
 运行后，得到的结果为：
 
 ```
-{'img_path': '/my_path/general_instance_segmentation_004.png', 'boxes': [{'cls_id': 0, 'label': 'person', 'score': 0.8698326945304871, 'coordinate': [339, 0, 639, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8571141362190247, 'coordinate': [0, 0, 195, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8202633857727051, 'coordinate': [88, 113, 401, 574]}, {'cls_id': 0, 'label': 'person', 'score': 0.7108577489852905, 'coordinate': [522, 21, 767, 574]}, {'cls_id': 27, 'label': 'tie', 'score': 0.554280698299408, 'coordinate': [247, 311, 355, 574]}]}
+{'input_path': 'general_instance_segmentation_004.png', 'boxes': [{'cls_id': 0, 'label': 'person', 'score': 0.8698326945304871, 'coordinate': [339, 0, 639, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8571141362190247, 'coordinate': [0, 0, 195, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8202633857727051, 'coordinate': [88, 113, 401, 574]}, {'cls_id': 0, 'label': 'person', 'score': 0.7108577489852905, 'coordinate': [522, 21, 767, 574]}, {'cls_id': 27, 'label': 'tie', 'score': 0.554280698299408, 'coordinate': [247, 311, 355, 574]}]}
 ```
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/instance_segmentation/03.png)
 
@@ -673,12 +673,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行实例分割产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline instance_segmentation --input general_instance_segmentation_004.png --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline instance_segmentation --input general_instance_segmentation_004.png --device npu:0
 ```
 若您想在更多种类的硬件上使用通用实例分割产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation_en.md

@@ -81,8 +81,8 @@ paddlex --get_pipeline_config instance_segmentation --save_path ./my_path
 
 After obtaining the pipeline configuration file, you can replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./instance_segmentation.yaml`, simply execute:
 
-```
-paddlex --pipeline ./instance_segmentation.yaml --input general_instance_segmentation_004.png
+```bash
+paddlex --pipeline ./instance_segmentation.yaml --input general_instance_segmentation_004.png --device gpu:0
 ```
 
 Where `--model`, `--device`, and other parameters do not need to be specified, and the parameters in the configuration file will be used. If parameters are still specified, the specified parameters will take precedence.
@@ -92,7 +92,7 @@ Where `--model`, `--device`, and other parameters do not need to be specified, a
 After running, the result is:
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_instance_segmentation_004.png', 'boxes': [{'cls_id': 0, 'label': 'person', 'score': 0.8698326945304871, 'coordinate': [339, 0, 639, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8571141362190247, 'coordinate': [0, 0, 195, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8202633857727051, 'coordinate': [88, 113, 401, 574]}, {'cls_id': 0, 'label': 'person', 'score': 0.7108577489852905, 'coordinate': [522, 21, 767, 574]}, {'cls_id': 27, 'label': 'tie', 'score': 0.554280698299408, 'coordinate': [247, 311, 355, 574]}]}
+{'input_path': 'general_instance_segmentation_004.png', 'boxes': [{'cls_id': 0, 'label': 'person', 'score': 0.8698326945304871, 'coordinate': [339, 0, 639, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8571141362190247, 'coordinate': [0, 0, 195, 575]}, {'cls_id': 0, 'label': 'person', 'score': 0.8202633857727051, 'coordinate': [88, 113, 401, 574]}, {'cls_id': 0, 'label': 'person', 'score': 0.7108577489852905, 'coordinate': [522, 21, 767, 574]}, {'cls_id': 27, 'label': 'tie', 'score': 0.554280698299408, 'coordinate': [247, 311, 355, 574]}]}
 ```
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/instance_segmentation/03.png)

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md

@@ -340,7 +340,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验目标检测产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline object_detection --input general_object_detection_002.png --device gpu:0
 ```
 参数说明：
@@ -368,8 +368,8 @@ paddlex --get_pipeline_config object_detection --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./object_detection.yaml`，只需执行：
 
-```
-paddlex --pipeline ./object_detection.yaml --input general_object_detection_002.png
+```bash
+paddlex --pipeline ./object_detection.yaml --input general_object_detection_002.png --device gpu:0
 ```
 
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
@@ -379,7 +379,7 @@ paddlex --pipeline ./object_detection.yaml --input general_object_detection_002.
 运行后，得到的结果为：
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_object_detection_002.png', 'boxes': [{'cls_id': 49, 'label': 'orange', 'score': 0.8188097476959229, 'coordinate': [661, 93, 870, 305]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7743489146232605, 'coordinate': [76, 274, 330, 520]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7270504236221313, 'coordinate': [285, 94, 469, 297]}, {'cls_id': 46, 'label': 'banana', 'score': 0.5570532083511353, 'coordinate': [310, 361, 685, 712]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5484835505485535, 'coordinate': [764, 285, 924, 440]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5160726308822632, 'coordinate': [853, 169, 987, 303]}, {'cls_id': 60, 'label': 'dining table', 'score': 0.5142655968666077, 'coordinate': [0, 0, 1072, 720]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5101479291915894, 'coordinate': [57, 23, 213, 176]}]}
+{'input_path': 'general_object_detection_002.png', 'boxes': [{'cls_id': 49, 'label': 'orange', 'score': 0.8188097476959229, 'coordinate': [661, 93, 870, 305]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7743489146232605, 'coordinate': [76, 274, 330, 520]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7270504236221313, 'coordinate': [285, 94, 469, 297]}, {'cls_id': 46, 'label': 'banana', 'score': 0.5570532083511353, 'coordinate': [310, 361, 685, 712]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5484835505485535, 'coordinate': [764, 285, 924, 440]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5160726308822632, 'coordinate': [853, 169, 987, 303]}, {'cls_id': 60, 'label': 'dining table', 'score': 0.5142655968666077, 'coordinate': [0, 0, 1072, 720]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5101479291915894, 'coordinate': [57, 23, 213, 176]}]}
 ```
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/object_detection/03.png)
@@ -962,12 +962,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行目标检测产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline object_detection --input general_object_detection_002.png --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline object_detection --input general_object_detection_002.png --device npu:0
 ```
 若您想在更多种类的硬件上使用通用目标检测产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/cv_pipelines/object_detection_en.md

@@ -369,7 +369,7 @@ paddlex --get_pipeline_config object_detection --save_path ./my_path
 After obtaining the pipeline configuration file, replace `--pipeline` with the configuration file save path to make the configuration file effective. For example, if the configuration file save path is `./object_detection.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./object_detection.yaml --input general_object_detection_002.png
+paddlex --pipeline ./object_detection.yaml --input general_object_detection_002.png --device gpu:0
 ```
 
 Here, parameters such as `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If these parameters are still specified, the specified parameters will take precedence.
@@ -379,7 +379,7 @@ Here, parameters such as `--model` and `--device` do not need to be specified, a
 After running, the result will be:
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_object_detection_002.png', 'boxes': [{'cls_id': 49, 'label': 'orange', 'score': 0.8188097476959229, 'coordinate': [661, 93, 870, 305]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7743489146232605, 'coordinate': [76, 274, 330, 520]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7270504236221313, 'coordinate': [285, 94, 469, 297]}, {'cls_id': 46, 'label': 'banana', 'score': 0.5570532083511353, 'coordinate': [310, 361, 685, 712]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5484835505485535, 'coordinate': [764, 285, 924, 440]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5160726308822632, 'coordinate': [853, 169, 987, 303]}, {'cls_id': 60, 'label': 'dining table', 'score': 0.5142655968666077, 'coordinate': [0, 0, 1072, 720]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5101479291915894, 'coordinate': [57, 23, 213, 176]}]}
+{'input_path': 'general_object_detection_002.png', 'boxes': [{'cls_id': 49, 'label': 'orange', 'score': 0.8188097476959229, 'coordinate': [661, 93, 870, 305]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7743489146232605, 'coordinate': [76, 274, 330, 520]}, {'cls_id': 47, 'label': 'apple', 'score': 0.7270504236221313, 'coordinate': [285, 94, 469, 297]}, {'cls_id': 46, 'label': 'banana', 'score': 0.5570532083511353, 'coordinate': [310, 361, 685, 712]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5484835505485535, 'coordinate': [764, 285, 924, 440]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5160726308822632, 'coordinate': [853, 169, 987, 303]}, {'cls_id': 60, 'label': 'dining table', 'score': 0.5142655968666077, 'coordinate': [0, 0, 1072, 720]}, {'cls_id': 47, 'label': 'apple', 'score': 0.5101479291915894, 'coordinate': [57, 23, 213, 176]}]}
 ```
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/object_detection/03.png)

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md

@@ -58,7 +58,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验语义分割产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/application/semantic_segmentation/makassaridn-road_demo.png)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline semantic_segmentation --input makassaridn-road_demo.png --device gpu:0
 ```
 参数说明：
@@ -85,8 +85,8 @@ paddlex --get_pipeline_config semantic_segmentation --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./semantic_segmentation.yaml`，只需执行：
 
-```
-paddlex --pipeline ./semantic_segmentation.yaml --input semantic_segmentation/makassaridn-road_demo.png
+```bash
+paddlex --pipeline ./semantic_segmentation.yaml --input makassaridn-road_demo.png --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -95,7 +95,7 @@ paddlex --pipeline ./semantic_segmentation.yaml --input semantic_segmentation/ma
 运行后，得到的结果为：
 
 ```
-{'img_path': '/root/.paddlex/predict_input/general_object_detection_002.png'}
+{'input_path': 'general_object_detection_002.png'}
 ```
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/semantic_segmentation/03.png)
 可视化图片默认不进行保存，您可以通过 `--save_path` 自定义保存路径，随后所有结果将被保存在指定路径下。
@@ -108,7 +108,7 @@ from paddlex import create_pipeline
 
 pipeline = create_pipeline(pipeline="semantic_segmentation")
 
-output = pipeline.predict("semantic_segmentation/makassaridn-road_demo.png")
+output = pipeline.predict("makassaridn-road_demo.png")
 for res in output:
     res.print() ## 打印预测的结构化输出
     res.save_to_img("./output/") ## 保存结果可视化图像
@@ -154,7 +154,7 @@ for res in output:
 ```python
 from paddlex import create_pipeline
 pipeline = create_pipeline(pipeline="./my_path/semantic_segmentation.yaml")
-output = pipeline.predict("semantic_segmentation/makassaridn-road_demo.png")
+output = pipeline.predict("makassaridn-road_demo.png")
 for res in output:
     res.print() ## 打印预测的结构化输出
     res.save_to_img("./output/") ## 保存结果可视化图像
@@ -643,12 +643,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行语义分割产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline semantic_segmentation --input semantic_segmentation/makassaridn-road_demo.png --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline semantic_segmentation --input semantic_segmentation/makassaridn-road_demo.png --device npu:0
 ```
 若您想在更多种类的硬件上使用通用语义分割产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation_en.md

@@ -87,7 +87,7 @@ paddlex --get_pipeline_config semantic_segmentation --save_path ./my_path
 After obtaining the pipeline configuration file, replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./semantic_segmentation.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./semantic_segmentation.yaml --input makassaridn-road_demo.png
+paddlex --pipeline ./semantic_segmentation.yaml --input makassaridn-road_demo.png --device gpu:0
 ```
 
 Here, parameters such as `--model` and `--device` do not need to be specified, and the parameters in the configuration file will be used. If parameters are still specified, the specified parameters will take precedence.
@@ -97,7 +97,7 @@ Here, parameters such as `--model` and `--device` do not need to be specified, a
 After running, the result is:
 
 ```bash
-{'img_path': '/root/.paddlex/predict_input/general_object_detection_002.png'}
+{'input_path': 'general_object_detection_002.png'}
 ```
 
 ![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/semantic_segmentation/03.png)

docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction.md

@@ -203,20 +203,14 @@ for res in visual_result:
     res.save_to_html('./output')
     res.save_to_xlsx('./output')
 
-vector = pipeline.build_vector(visual_info=visual_info)
-
-chat_result = pipeline.chat(
-    key_list=["乙方", "手机号"],
-    visual_info=visual_info,
-    vector=vector,
-    )
+chat_result = pipeline.chat(["乙方", "手机号"])
 chat_result.print()
 ```
 **注**：请先在[百度云千帆平台](https://console.bce.baidu.com/qianfan/ais/console/onlineService)获取自己的ak与sk（详细流程请参考[AK和SK鉴权调用API流程](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Hlwerugt8)），将ak与sk填入至指定位置后才能正常调用大模型。
 
 运行后，输出结果如下：
 
-```python
+```
 {'chat_res': {'乙方': '股份测试有限公司', '手机号': '19331729920'}, 'prompt': ''}
 ```
 
@@ -735,3 +729,4 @@ predict = create_pipeline( pipeline="PP-ChatOCRv3-doc",
                             device = "npu:0" )
 ```
 若您想在更多种类的硬件上使用通用文档场景信息抽取产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。
+

docs/pipeline_usage/tutorials/information_extration_pipelines/document_scene_information_extraction_en.md

@@ -199,20 +199,14 @@ for res in visual_result:
     res.save_to_html('./output')
     res.save_to_xlsx('./output')
 
-vector = pipeline.build_vector(visual_info=visual_info)
-
-chat_result = pipeline.chat(
-    key_list=["乙方", "手机号"],
-    visual_info=visual_info,
-    vector=vector,
-    )
+chat_result = pipeline.chat(["乙方", "手机号"])
 chat_result.print()
 ```
 **Note**: Please first obtain your ak and sk on the [Baidu Cloud Qianfan Platform](https://console.bce.baidu.com/qianfan/ais/console/onlineService) (for detailed steps, please refer to the [AK and SK Authentication API Call Process](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Hlwerugt8)), and fill in your ak and sk to the specified locations to enable normal calls to the large model.
 
 After running, the output is as follows:
 
-```python
+```
 {'chat_res': {'乙方': '股份测试有限公司', '手机号': '19331729920'}, 'prompt': ''}
 ```
 
@@ -629,3 +623,4 @@ predict = create_pipeline(
 ```
 
 If you want to use the PP-ChatOCRv3-doc Pipeline on more types of hardware, please refer to the [PaddleX Multi-Device Usage Guide](../../../installation/multi_devices_use_guide_en.md).
+

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -41,7 +41,7 @@ PaddleX 支持在本地使用命令行或 Python 体验公式识别产线的效
 ### 2.1 命令行方式体验
 一行命令即可快速体验公式识别产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/demo_image/general_formula_recognition.png)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline formula_recognition --input general_formula_recognition.png --device gpu:0
 ```
 参数说明：
@@ -68,8 +68,8 @@ paddlex --get_pipeline_config formula_recognition --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./formula_recognition.yaml`，只需执行：
 
-```
-paddlex --pipeline ./formula_recognition.yaml --input general_formula_recognition.png
+```bash
+paddlex --pipeline ./formula_recognition.yaml --input general_formula_recognition.png --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition_en.md

@@ -69,8 +69,8 @@ paddlex --get_pipeline_config formula_recognition --save_path ./my_path
 ```
 
 After obtaining the Pipeline configuration file, replace `--pipeline` with the configuration file's save path to make the configuration file effective. For example, if the configuration file is saved as  `./formula_recognition.yaml`, simply execute:
-```
-paddlex --pipeline ./formula_recognition.yaml --input general_formula_recognition.png
+```bash
+paddlex --pipeline ./formula_recognition.yaml --input general_formula_recognition.png --device gpu:0
 ```
 Here, parameters such as `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If parameters are still specified, the specified parameters will take precedence.
 

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -92,7 +92,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 ### 2.1 命令行方式体验
 一行命令即可快速体验表格识别产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline table_recognition --input table_recognition.jpg --device gpu:0
 ```
 参数说明：
@@ -119,8 +119,8 @@ paddlex --get_pipeline_config table_recognition --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./table_recognition.yaml`，只需执行：
 
-```
-paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg
+```bash
+paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -132,7 +132,7 @@ paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg
    <summary> 👉点击展开</summary>
 
 ```
-{'input_path': '/root/.paddlex/predict_input/table_recognition.jpg', 'layout_result': {'input_path': '/root/.paddlex/predict_input/table_recognition.jpg', 'boxes': [{'cls_id': 3, 'label': 'Table', 'score': 0.6014542579650879, 'coordinate': [0, 21, 551, 118]}]}, 'ocr_result': {'dt_polys': [array([[37., 40.],
+{'input_path': 'table_recognition.jpg', 'layout_result': {'input_path': 'table_recognition.jpg', 'boxes': [{'cls_id': 3, 'label': 'Table', 'score': 0.6014542579650879, 'coordinate': [0, 21, 551, 118]}]}, 'ocr_result': {'dt_polys': [array([[37., 40.],
        [75., 40.],
        [75., 60.],
        [37., 60.]], dtype=float32), array([[123.,  37.],
@@ -165,7 +165,7 @@ paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg
        [278., 118.]], dtype=float32), array([[446., 102.],
        [504., 104.],
        [503., 118.],
-       [445., 118.]], dtype=float32)], 'rec_text': ['Dres', '连续工作3', '取出来放在网上，没想', '江、整江等八大', 'Abstr', 'rSrivi', '$709.', 'cludingGiv', '2.72', 'Ingcubic', '$744.78'], 'rec_score': [0.9934158325195312, 0.9990204572677612, 0.9967061877250671, 0.9375461935997009, 0.9947397112846375, 0.9972746968269348, 0.9904290437698364, 0.973427414894104, 0.9983080625534058, 0.993423342704773, 0.9964120984077454], 'input_path': '/root/.paddlex/predict_input/table_recognition.jpg'}, 'table_result': [{'input_path': '/root/.paddlex/predict_input/table_recognition.jpg', 'layout_bbox': [0, 21, 551, 118], 'bbox': array([[  4.395736 ,  25.238262 , 113.31014  ,  25.316246 , 115.454315 ,
+       [445., 118.]], dtype=float32)], 'rec_text': ['Dres', '连续工作3', '取出来放在网上，没想', '江、整江等八大', 'Abstr', 'rSrivi', '$709.', 'cludingGiv', '2.72', 'Ingcubic', '$744.78'], 'rec_score': [0.9934158325195312, 0.9990204572677612, 0.9967061877250671, 0.9375461935997009, 0.9947397112846375, 0.9972746968269348, 0.9904290437698364, 0.973427414894104, 0.9983080625534058, 0.993423342704773, 0.9964120984077454], 'input_path': 'table_recognition.jpg'}, 'table_result': [{'input_path': 'table_recognition.jpg', 'layout_bbox': [0, 21, 551, 118], 'bbox': array([[  4.395736 ,  25.238262 , 113.31014  ,  25.316246 , 115.454315 ,
          71.8867   ,   3.7177477,  71.7937   ],
        [110.727455 ,  25.94007  , 210.07187  ,  26.028755 , 209.66394  ,
          65.96484  , 109.59861  ,  66.09809  ],
@@ -826,12 +826,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行表格识别产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline table_recognition --input table_recognition.jpg --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 修改为npu 即可：
 
-```
+```bash
 paddlex --pipeline table_recognition --input table_recognition.jpg --device npu:0
 ```
 若您想在更多种类的硬件上使用通用表格识别产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_en.md

@@ -116,7 +116,7 @@ paddlex --get_pipeline_config table_recognition --save_path ./my_path
 After obtaining the pipeline configuration file, replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./table_recognition.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg
+paddlex --pipeline ./table_recognition.yaml --input table_recognition.jpg --device gpu:0
 ```
 
 Here, parameters like `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If they are still specified, the specified parameters will take precedence.

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md

@@ -46,7 +46,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验时序异常检测产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_ad.csv)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline ts_ad --input ts_ad.csv --device gpu:0
 ```
 参数说明：
@@ -73,8 +73,8 @@ paddlex --get_pipeline_config ts_ad --save_path ./my_path
 
 获取产线配置文件后，可将` --pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./ts_ad.yaml`，只需执行：
 
-```
-paddlex --pipeline ./ts_ad.yaml --input ts_ad.cs
+```bash
+paddlex --pipeline ./ts_ad.yaml --input ts_ad.cs --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -83,7 +83,7 @@ paddlex --pipeline ./ts_ad.yaml --input ts_ad.cs
 运行后，得到的结果为：
 
 ```
-{'ts_path': '/root/.paddlex/predict_input/ts_ad.csv', 'anomaly':            label
+{'input_path': 'ts_ad.csv', 'anomaly':            label
 timestamp
 220226         0
 220227         0
@@ -627,12 +627,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行时序异常检测产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline ts_ad --input ts_ad.cs --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的` --device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline ts_ad --input ts_ad.cs --device npu:0
 ```
 若您想在更多种类的硬件上使用通用时序异常检测产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection_en.md

@@ -5,7 +5,7 @@
 ## 1. Introduction to the General Time Series Anomaly Detection Pipeline
 Time series anomaly detection is a technique for identifying abnormal patterns or behaviors in time series data. It is widely applied in fields such as network security, equipment monitoring, and financial fraud detection. By analyzing normal trends and patterns in historical data, it discovers events that significantly deviate from expected behaviors, such as sudden spikes in network traffic or unusual transaction activities. Time series anomaly detection enable automatic identification of anomalies in data. This technology provides real-time alerts for enterprises and organizations, helping them promptly address potential risks and issues. It plays a crucial role in ensuring system stability and security.
 
-![](/tmp/images/pipelines/time_series/05.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/time_series/05.png)
 
 **The General Time Series Anomaly Detection Pipeline includes a time series anomaly detection module. If you prioritize model accuracy, choose a model with higher precision. If you prioritize inference speed, select a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage footprint.**
 
@@ -30,7 +30,7 @@ The pre-trained model pipelines provided by PaddleX allow for quick experience o
 ### 2.1 Online Experience
 You can [experience online](https://aistudio.baidu.com/community/app/105706/webUI?source=appCenter) the effects of the General Time Series Anomaly Detection Pipeline using the official demo for recognition, for example:
 
-![](/tmp/images/pipelines/time_series/06.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/time_series/06.png)
 
 If you are satisfied with the pipeline's performance, you can directly integrate and deploy it. If not, you can also use your private data to **fine-tune the model within the pipeline online**.
 
@@ -67,7 +67,7 @@ paddlex --get_pipeline_config ts_ad --save_path ./my_path
 After obtaining the pipeline configuration file, you can replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./ts_ad.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./ts_ad.yaml --input ts_ad.csv
+paddlex --pipeline ./ts_ad.yaml --input ts_ad.csv --device gpu:0
 ```
 
 Here, parameters such as `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If parameters are still specified, the specified parameters will take precedence.
@@ -77,7 +77,7 @@ Here, parameters such as `--model` and `--device` do not need to be specified, a
 After running, the result obtained is:
 
 ```json
-{'ts_path': '/root/.paddlex/predict_input/ts_ad.csv', 'anomaly':            label
+{'input_path': 'ts_ad.csv', 'anomaly':            label
 timestamp
 220226         0
 220227         0

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md

@@ -39,7 +39,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验时序分类产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_cls.csv)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline ts_cls --input ts_cls.csv --device gpu:0
 ```
 参数说明：
@@ -66,8 +66,8 @@ paddlex --get_pipeline_config ts_cls --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./ts_cls.yaml`，只需执行：
 
-```
-paddlex --pipeline ./ts_cls.yaml --input ts_cls.csv
+```bash
+paddlex --pipeline ./ts_cls.yaml --input ts_cls.csv --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -76,7 +76,7 @@ paddlex --pipeline ./ts_cls.yaml --input ts_cls.csv
 运行后，得到的结果为：
 
 ```
-{'ts_path': '/root/.paddlex/predict_input/ts_cls.csv', 'classification':         classid     score
+{'input_path': 'ts_cls.csv', 'classification':         classid     score
 sample
 0             0  0.617688}
 ```
@@ -563,12 +563,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行时序分类产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline ts_cls --input ts_cls.csv --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 进行修改即可：
 
-```
+```bash
 paddlex --pipeline ts_cls --input ts_cls.csv --device npu:0
 ```
 若您想在更多种类的硬件上使用通用时序分类产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification_en.md

@@ -5,7 +5,7 @@
 ## 1. Introduction to General Time Series Classification Pipeline
 Time series classification is a technique that categorizes time-series data into predefined classes, widely applied in fields such as behavior recognition and financial trend analysis. By analyzing features that vary over time, it identifies different patterns or events, for example, classifying a speech signal as "greeting" or "request," or categorizing stock price movements as "rising" or "falling." Time series classification typically employs machine learning and deep learning models, effectively capturing temporal dependencies and variation patterns to provide accurate classification labels for data. This technology plays a pivotal role in applications such as intelligent monitoring and market forecasting.
 
-![](/tmp/images/pipelines/time_series/01.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/time_series/01.png)
 
 **The General Time Series Classification Pipeline includes a Time Series Classification module.**
 
@@ -26,7 +26,7 @@ PaddleX provides pre-trained model pipelines that can be quickly experienced. Yo
 ### 2.1 Online Experience
 You can [experience online](https://aistudio.baidu.com/community/app/105707/webUI?source=appCenter) the effects of the General Time Series Classification Pipeline using the official demo for recognition, for example:
 
-![](/tmp/images/pipelines/time_series/02.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/time_series/02.png)
 
 If you are satisfied with the pipeline's performance, you can directly integrate and deploy it. If not, you can also use your private data to **fine-tune the model in the pipeline online**.
 
@@ -68,7 +68,7 @@ paddlex --get_pipeline_config ts_cls --save_path ./my_path
 After obtaining the pipeline configuration file, you can replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./ts_ad.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./ts_cls.yaml --input ts_cls.csv
+paddlex --pipeline ./ts_cls.yaml --input ts_cls.csv --device gpu:0
 ```
 
 In this command, parameters such as `--model` and `--device` are not required to be specified, as they will use the parameters defined in the configuration file. If these parameters are specified, the specified values will take precedence.
@@ -78,7 +78,7 @@ In this command, parameters such as `--model` and `--device` are not required to
 After execution, the result is:
 
 ```bash
-{'ts_path': '/root/.paddlex/predict_input/ts_cls.csv', 'classification':         classid     score
+{'input_path': 'ts_cls.csv', 'classification':         classid     score
 sample
 0             0  0.617688}
 ```

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md

@@ -44,7 +44,7 @@ PaddleX 所提供的预训练的模型产线均可以快速体验效果，你可
 #### 2.2.1 命令行方式体验
 一行命令即可快速体验时序预测产线效果，使用 [测试文件](https://paddle-model-ecology.bj.bcebos.com/paddlex/ts/demo_ts/ts_fc.csv)，并将 `--input` 替换为本地路径，进行预测
 
-```
+```bash
 paddlex --pipeline ts_fc --input ts_fc.csv --device gpu:0
 ```
 参数说明：
@@ -71,8 +71,8 @@ paddlex --get_pipeline_config ts_fc --save_path ./my_path
 
 获取产线配置文件后，可将 `--pipeline` 替换为配置文件保存路径，即可使配置文件生效。例如，若配置文件保存路径为 `./ts_fc.yaml`，只需执行：
 
-```
-paddlex --pipeline ./ts_fc.yaml --input ts_fc.csv
+```bash
+paddlex --pipeline ./ts_fc.yaml --input ts_fc.csv --device gpu:0
 ```
 其中，`--model`、`--device` 等参数无需指定，将使用配置文件中的参数。若依然指定了参数，将以指定的参数为准。
 
@@ -81,7 +81,7 @@ paddlex --pipeline ./ts_fc.yaml --input ts_fc.csv
 运行后，得到的结果为：
 
 ```
-{'ts_path': '/root/.paddlex/predict_input/ts_fc.csv', 'forecast':                            OT
+{'input_path': 'ts_fc.csv', 'forecast':                            OT
 date
 2018-06-26 20:00:00  9.586131
 2018-06-26 21:00:00  9.379762
@@ -625,12 +625,12 @@ PaddleX 支持英伟达 GPU、昆仑芯 XPU、昇腾 NPU和寒武纪 MLU 等多
 
 例如，您使用英伟达 GPU 进行时序预测产线的推理，使用的 Python 命令为：
 
-```
+```bash
 paddlex --pipeline ts_fc --input ts_fc.csv --device gpu:0
 ```
 此时，若您想将硬件切换为昇腾 NPU，仅需对 Python 命令中的 `--device` 修改为 npu:0 即可：
 
-```
+```bash
 paddlex --pipeline ts_fc --input ts_fc.csv --device npu:0
 ```
 若您想在更多种类的硬件上使用通用时序预测产线，请参考[PaddleX多硬件使用指南](../../../other_devices_support/multi_devices_use_guide.md)。

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting_en.md

@@ -5,7 +5,7 @@
 ## 1. Introduction to the General Time Series Forecasting Pipeline
 Time series forecasting is a technique that utilizes historical data to predict future trends by analyzing the patterns of change in time series data. It is widely applied in fields such as financial markets, weather forecasting, and sales prediction. Time series forecasting often employs statistical methods or deep learning models (e.g., LSTM, ARIMA), capable of handling temporal dependencies in data to provide accurate predictions, assisting decision-makers in better planning and response. This technology plays a crucial role in various industries, including energy management, supply chain optimization, and market analysis.
 
-![](/tmp/images/pipelines/time_series/03.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/time_series/03.png)
 
 **The General Time Series Forecasting Pipeline includes a time series forecasting module. If you prioritize model accuracy, choose a model with higher accuracy. If you prioritize inference speed, select a model with faster inference. If you prioritize model storage size, choose a model with a smaller storage size.**
 
@@ -32,7 +32,7 @@ The pre-trained model pipelines provided by PaddleX allow for quick experience o
 ### 2.1 Online Experience
 You can [experience the General Time Series Forecasting Pipeline online](https://aistudio.baidu.com/community/app/105706/webUI?source=appCenter) using the demo provided by the official team, for example:
 
-![](/tmp/images/pipelines/time_series/04.png)
+![](https://raw.githubusercontent.com/cuicheng01/PaddleX_doc_images/main/images/pipelines/time_series/04.png)
 
 If you are satisfied with the pipeline's performance, you can directly integrate and deploy it. If not, you can also use your private data to **fine-tune the model within the pipeline online**.
 
@@ -69,7 +69,7 @@ paddlex --get_pipeline_config ts_fc --save_path ./my_path
 After obtaining the pipeline configuration file, you can replace `--pipeline` with the configuration file save path to make the configuration file take effect. For example, if the configuration file save path is `./ts_fc.yaml`, simply execute:
 
 ```bash
-paddlex --pipeline ./ts_fc.yaml --input ts_fc.csv
+paddlex --pipeline ./ts_fc.yaml --input ts_fc.csv --device gpu:0
 ```
 
 Here, parameters such as `--model` and `--device` do not need to be specified, as they will use the parameters in the configuration file. If parameters are still specified, the specified parameters will take precedence.
@@ -79,7 +79,7 @@ Here, parameters such as `--model` and `--device` do not need to be specified, a
 After running, the result is:
 
 ```bash
-{'ts_path': '/root/.paddlex/predict_input/ts_fc.csv', 'forecast':                            OT
+{'input_path': 'ts_fc.csv', 'forecast':                            OT
 date
 2018-06-26 20:00:00  9.586131
 2018-06-26 21:00:00  9.379762