Prechádzať zdrojové kódy

!6 fix doc error (#4367) (#4368)
Merge pull request !6 from zhch158/release/3.1

zhch158 3 mesiacov pred
rodič
commit
89ab0cfb75
100 zmenil súbory, kde vykonal 925 pridanie a 226 odobranie
  1. 31 0
      .github/workflows/deploy_docs.yml
  2. 6 6
      docs/installation/installation.en.md
  3. 6 6
      docs/installation/installation.md
  4. 1 2
      docs/installation/paddlepaddle_install.en.md
  5. 1 2
      docs/installation/paddlepaddle_install.md
  6. 26 0
      docs/module_usage/instructions/distributed_training.en.md
  7. 26 0
      docs/module_usage/instructions/distributed_training.md
  8. 8 2
      docs/module_usage/tutorials/cv_modules/3d_bev_detection.en.md
  9. 6 1
      docs/module_usage/tutorials/cv_modules/3d_bev_detection.md
  10. 8 2
      docs/module_usage/tutorials/cv_modules/anomaly_detection.en.md
  11. 6 1
      docs/module_usage/tutorials/cv_modules/anomaly_detection.md
  12. 8 2
      docs/module_usage/tutorials/cv_modules/face_detection.en.md
  13. 6 1
      docs/module_usage/tutorials/cv_modules/face_detection.md
  14. 8 2
      docs/module_usage/tutorials/cv_modules/face_feature.en.md
  15. 6 1
      docs/module_usage/tutorials/cv_modules/face_feature.md
  16. 8 2
      docs/module_usage/tutorials/cv_modules/human_detection.en.md
  17. 6 1
      docs/module_usage/tutorials/cv_modules/human_detection.md
  18. 8 2
      docs/module_usage/tutorials/cv_modules/human_keypoint_detection.en.md
  19. 6 1
      docs/module_usage/tutorials/cv_modules/human_keypoint_detection.md
  20. 8 2
      docs/module_usage/tutorials/cv_modules/image_classification.en.md
  21. 6 1
      docs/module_usage/tutorials/cv_modules/image_classification.md
  22. 8 2
      docs/module_usage/tutorials/cv_modules/image_feature.en.md
  23. 6 1
      docs/module_usage/tutorials/cv_modules/image_feature.md
  24. 8 2
      docs/module_usage/tutorials/cv_modules/image_multilabel_classification.en.md
  25. 6 1
      docs/module_usage/tutorials/cv_modules/image_multilabel_classification.md
  26. 8 2
      docs/module_usage/tutorials/cv_modules/instance_segmentation.en.md
  27. 6 1
      docs/module_usage/tutorials/cv_modules/instance_segmentation.md
  28. 8 2
      docs/module_usage/tutorials/cv_modules/mainbody_detection.en.md
  29. 6 1
      docs/module_usage/tutorials/cv_modules/mainbody_detection.md
  30. 8 2
      docs/module_usage/tutorials/cv_modules/object_detection.en.md
  31. 6 1
      docs/module_usage/tutorials/cv_modules/object_detection.md
  32. 8 2
      docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.en.md
  33. 6 1
      docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.md
  34. 8 2
      docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.en.md
  35. 6 1
      docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.md
  36. 8 2
      docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.en.md
  37. 6 1
      docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.md
  38. 8 2
      docs/module_usage/tutorials/cv_modules/rotated_object_detection.en.md
  39. 6 1
      docs/module_usage/tutorials/cv_modules/rotated_object_detection.md
  40. 8 2
      docs/module_usage/tutorials/cv_modules/semantic_segmentation.en.md
  41. 6 1
      docs/module_usage/tutorials/cv_modules/semantic_segmentation.md
  42. 8 2
      docs/module_usage/tutorials/cv_modules/small_object_detection.en.md
  43. 6 1
      docs/module_usage/tutorials/cv_modules/small_object_detection.md
  44. 8 2
      docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md
  45. 6 1
      docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.md
  46. 8 2
      docs/module_usage/tutorials/cv_modules/vehicle_detection.en.md
  47. 6 1
      docs/module_usage/tutorials/cv_modules/vehicle_detection.md
  48. 8 2
      docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.en.md
  49. 6 1
      docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md
  50. 8 2
      docs/module_usage/tutorials/ocr_modules/formula_recognition.en.md
  51. 6 1
      docs/module_usage/tutorials/ocr_modules/formula_recognition.md
  52. 8 2
      docs/module_usage/tutorials/ocr_modules/layout_detection.en.md
  53. 6 1
      docs/module_usage/tutorials/ocr_modules/layout_detection.md
  54. 8 2
      docs/module_usage/tutorials/ocr_modules/seal_text_detection.en.md
  55. 6 1
      docs/module_usage/tutorials/ocr_modules/seal_text_detection.md
  56. 8 2
      docs/module_usage/tutorials/ocr_modules/table_cells_detection.en.md
  57. 6 1
      docs/module_usage/tutorials/ocr_modules/table_cells_detection.md
  58. 8 2
      docs/module_usage/tutorials/ocr_modules/table_classification.en.md
  59. 6 1
      docs/module_usage/tutorials/ocr_modules/table_classification.md
  60. 8 2
      docs/module_usage/tutorials/ocr_modules/table_structure_recognition.en.md
  61. 6 1
      docs/module_usage/tutorials/ocr_modules/table_structure_recognition.md
  62. 8 2
      docs/module_usage/tutorials/ocr_modules/text_detection.en.md
  63. 6 1
      docs/module_usage/tutorials/ocr_modules/text_detection.md
  64. 8 2
      docs/module_usage/tutorials/ocr_modules/text_image_unwarping.en.md
  65. 6 1
      docs/module_usage/tutorials/ocr_modules/text_image_unwarping.md
  66. 8 2
      docs/module_usage/tutorials/ocr_modules/text_recognition.en.md
  67. 6 1
      docs/module_usage/tutorials/ocr_modules/text_recognition.md
  68. 8 2
      docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.en.md
  69. 6 1
      docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.md
  70. 8 2
      docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.en.md
  71. 6 1
      docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md
  72. 8 2
      docs/module_usage/tutorials/time_series_modules/time_series_classification.en.md
  73. 6 1
      docs/module_usage/tutorials/time_series_modules/time_series_classification.md
  74. 8 2
      docs/module_usage/tutorials/time_series_modules/time_series_forecasting.en.md
  75. 6 1
      docs/module_usage/tutorials/time_series_modules/time_series_forecasting.md
  76. 8 2
      docs/module_usage/tutorials/video_modules/video_classification.en.md
  77. 6 1
      docs/module_usage/tutorials/video_modules/video_classification.md
  78. 8 2
      docs/module_usage/tutorials/video_modules/video_detection.en.md
  79. 6 1
      docs/module_usage/tutorials/video_modules/video_detection.md
  80. 2 2
      docs/pipeline_deploy/high_performance_inference.en.md
  81. 2 2
      docs/pipeline_deploy/high_performance_inference.md
  82. 101 36
      docs/pipeline_deploy/serving.en.md
  83. 99 36
      docs/pipeline_deploy/serving.md
  84. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.en.md
  85. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.md
  86. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.en.md
  87. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.md
  88. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.en.md
  89. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.md
  90. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.en.md
  91. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.md
  92. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.en.md
  93. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md
  94. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/image_classification.en.md
  95. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md
  96. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md
  97. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md
  98. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md
  99. 6 1
      docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md
  100. 8 2
      docs/pipeline_usage/tutorials/cv_pipelines/object_detection.en.md

+ 31 - 0
.github/workflows/deploy_docs.yml

@@ -0,0 +1,31 @@
+name: Develop Docs
+on:
+  push:
+    branches: #设置更新哪个分支会更新站点
+      - release/3.1
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
+      - uses: actions/cache@v4
+        with:
+          key: mkdocs-material-${{ env.cache_id }}
+          path: .cache
+          restore-keys: |
+            mkdocs-material-
+      - run: pip install mike mkdocs-material jieba mkdocs-git-revision-date-localized-plugin mkdocs-git-committers-plugin-2 mkdocs-git-authors-plugin mkdocs-static-i18n mkdocs-minify-plugin 
+      - run: |
+          git fetch origin gh-pages --depth=1
+          mike deploy --push --update-aliases 3.1 latest
+          mike set-default --push latest

+ 6 - 6
docs/installation/installation.en.md

@@ -147,13 +147,13 @@ If your Docker version >= 19.03, please use:
 
 ```bash
 # For CPU
-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-cpu /bin/bash
+docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-cpu /bin/bash
 
 # gpu,requires GPU driver version ≥450.80.02 (Linux) or ≥452.39 (Windows)
-docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
+docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
 
 # gpu,requires GPU driver version ≥545.23.06(Linux) or ≥545.84(Windows)
-docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
+docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
 ```
 
 * If your Docker version <= 19.03 and >= 17.06, please use:
@@ -161,14 +161,14 @@ docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=hos
 <details><summary> Click Here</summary>
 
 <pre><code class="language-bash"># For CPU
-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-cpu /bin/bash
+docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-cpu /bin/bash
 
 # For GPU
 # gpu,requires GPU driver version ≥450.80.02 (Linux) or ≥452.39 (Windows)
-nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
+nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
 
 # gpu,requires GPU driver version ≥545.23.06(Linux) or ≥545.84(Windows)
-nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
+nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
 
 </code></pre></details>
 

+ 6 - 6
docs/installation/installation.md

@@ -155,14 +155,14 @@ paddlex --install PaddleXXX  # 例如PaddleOCR
 
 ```bash
 # 对于 CPU 用户
-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-cpu /bin/bash
+docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-cpu /bin/bash
 
 # 对于 GPU 用户
 # GPU 版本,需显卡驱动程序版本 ≥450.80.02(Linux)或 ≥452.39(Windows)
-docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
+docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
 
 # GPU 版本,需显卡驱动程序版本 ≥545.23.06(Linux)或 ≥545.84(Windows)
-docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
+docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
 ```
 
 
@@ -171,14 +171,14 @@ docker run --gpus all --name paddlex -v $PWD:/paddle --shm-size=8g --network=hos
 <details><summary> 点击展开</summary>
 
 <pre><code class="language-bash"># 对于 CPU 用户
-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-cpu /bin/bash
+docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-cpu /bin/bash
 
 # 对于 GPU 用户
 # GPU 版本,需显卡驱动程序版本 ≥450.80.02(Linux)或 ≥452.39(Windows)
-nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
+nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda11.8-cudnn8.9-trt8.6 /bin/bash
 
 # GPU 版本,需显卡驱动程序版本 ≥545.23.06(Linux)或 ≥545.84(Windows)
-nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.0.1-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
+nvidia-docker run --name paddlex -v $PWD:/paddle --shm-size=8g --network=host -it ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/paddlex:paddlex3.1.2-paddlepaddle3.0.0-gpu-cuda12.6-cudnn9.5-trt10.5 /bin/bash
 
 </code></pre></details>
 

+ 1 - 2
docs/installation/paddlepaddle_install.en.md

@@ -76,13 +76,12 @@ python -c "import paddle; print(paddle.__version__)"
 If the installation is successful, the following content will be output:
 
 ```bash
-3.0.0-rc0
+3.0.0
 ```
 
 If you want to use the [Paddle Inference TensorRT Subgraph Engine](https://www.paddlepaddle.org.cn/documentation/docs/en/guides/paddle_v3_features/paddle_trt_en.html), after installing Paddle, you need to refer to the [TensorRT Documentation](https://docs.nvidia.com/deeplearning/tensorrt/archives/index.html) to install the corresponding version of TensorRT:
 
 - For PaddlePaddle with CUDA 11.8, the compatible TensorRT version is 8.x (where x >= 6). PaddleX has completed compatibility tests of Paddle-TensorRT on TensorRT 8.6.1.6, so it is **strongly recommended to install TensorRT 8.6.1.6**.
-- For PaddlePaddle with CUDA 12.6, the compatible TensorRT version is 10.x (where x >= 5), and it is recommended to install TensorRT 10.5.0.18.
 
 Below is an example of installing TensorRT 8.6.1.6 using the "Tar File Installation" method in a CUDA 11.8 environment:
 

+ 1 - 2
docs/installation/paddlepaddle_install.md

@@ -76,13 +76,12 @@ python -c "import paddle; print(paddle.__version__)"
 如果已安装成功,将输出以下内容:
 
 ```bash
-3.0.0-rc0
+3.0.0
 ```
 
 如果想要使用 [Paddle Inference TensorRT 子图引擎](https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/paddle_v3_features/paddle_trt_cn.html),在安装paddle后需参考 [TensorRT 文档](https://docs.nvidia.com/deeplearning/tensorrt/archives/index.html) 安装相应版本的 TensorRT:
 
 - 对于 CUDA 11.8 版本的飞桨,兼容的 TensorRT 版本为 8.x(x>=6)。PaddleX 已在 TensorRT 8.6.1.6 上完成了 Paddle-TensorRT 的兼容性测试,因此**强烈建议安装 TensorRT 8.6.1.6**。
-- 对于 CUDA 12.6 版本的飞桨,兼容的 TensorRT 版本为 10.x(x>=5),建议安装 TensorRT 10.5.0.18。
 
 下面是在 CUDA 11.8 环境下使用 "Tar File Installation" 方式安装 TensoRT 8.6.1.6 的例子:
 

+ 26 - 0
docs/module_usage/instructions/distributed_training.en.md

@@ -0,0 +1,26 @@
+---
+comments: true
+---
+
+# Distributed Training
+
+## Introduction
+
+Distributed training refers to splitting a training task across multiple computing nodes according to certain methods, and then aggregating and updating the gradients and other information obtained from the split computations. PaddlePaddle’s distributed training technology originates from Baidu’s business practices and has been validated in ultra-large-scale business scenarios in fields such as natural language processing, computer vision, search, and recommendation. High-performance distributed training is one of PaddlePaddle’s core technical advantages. For example, in tasks such as image classification, distributed training can achieve nearly linear speedup. Take ImageNet as an example, the ImageNet22k dataset contains 14 million images, and training on a single GPU would be extremely time-consuming. Therefore, PaddleX supports distributed training interfaces to complete training tasks, supporting both single-machine and multi-machine training. For more methods and documentation on distributed training, please refer to:[Distributed Training Quick Start Tutorial](https://fleet-x.readthedocs.io/en/latest/paddle_fleet_rst/parameter_server/ps_quick_start.html)。
+
+
+## Usage
+
+* Taking [Image Classification Model Training](../tutorials/cv_modules/image_classification.en.md)as an example, compared to single-machine training, for multi-machine training you only need to add the `Train.dist_ips` parameter, which indicates the list of IP addresses of machines participating in distributed training, separated by commas. Below is a sample code to run.
+
+```
+python main.py -c paddlex/configs/modules/image_classification/PP-LCNet_x1_0.yaml  \
+    -o Global.mode=train \
+    -o Global.dataset_dir=./dataset/cls_flowers_examples
+    -o Train.dist_ips="xx.xx.xx.xx,xx.xx.xx.xx"
+```
+**Note**:
+
+- The IP addresses of different machines should be separated by commas and can be checked using `ifconfig` or `ipconfig`.
+- Passwordless SSH should be set up between different machines, and they should be able to ping each other directly; otherwise, communication cannot be completed.
+- The code, data, and execution commands or scripts must be consistent across all machines, and the training command or script must be run on all machines. Finally, the first device of the first machine in the `Train.dist_ips` list will be trainer0, and so on.

+ 26 - 0
docs/module_usage/instructions/distributed_training.md

@@ -0,0 +1,26 @@
+---
+comments: true
+---
+
+# 分布式训练
+
+## 简介
+
+分布式训练指的是将训练任务按照一定方法拆分到多个计算节点进行计算,再按照一定的方法对拆分后计算得到的梯度等信息进行聚合与更新。飞桨分布式训练技术源自百度的业务实践,在自然语言处理、计算机视觉、搜索和推荐等领域经过超大规模业务检验。分布式训练的高性能,是飞桨的核心优势技术之一,例如在图像分类等任务上,分布式训练可以达到几乎线性的加速比,以ImageNet为例,ImageNet22k数据集中包含1400W张图像,如果使用单卡训练,会非常耗时。因此PaddleX中支持使用分布式训练接口完成训练任务,同时支持单机训练与多机训练。更多关于分布式训练的方法与文档可以参考:[分布式训练快速开始教程](https://fleet-x.readthedocs.io/en/latest/paddle_fleet_rst/parameter_server/ps_quick_start.html)。
+
+
+## 使用方法
+
+* 以[图像分类模型训练](../tutorials/cv_modules/image_classification.md)为例,相比单机训练,多机训练时,只需要添加 `Train.dist_ips` 的参数,该参数表示需要参与分布式训练的机器的ip列表,不同机器的ip用逗号隔开。下面为运行代码示例。
+
+```
+python main.py -c paddlex/configs/modules/image_classification/PP-LCNet_x1_0.yaml  \
+    -o Global.mode=train \
+    -o Global.dataset_dir=./dataset/cls_flowers_examples
+    -o Train.dist_ips="xx.xx.xx.xx,xx.xx.xx.xx"
+```
+**注**:
+
+- 不同机器的ip信息需要用逗号隔开,可以通过 `ifconfig` 或者 `ipconfig` 查看。
+- 不同机器之间需要做免密设置,且可以直接ping通,否则无法完成通信。
+- 不同机器之间的代码、数据与运行命令或脚本需要保持一致,且所有的机器上都需要运行设置好的训练命令或者脚本。最终 `Train.dist_ips` 中的第一台机器的第一块设备是trainer0,以此类推。

+ 8 - 2
docs/module_usage/tutorials/cv_modules/3d_bev_detection.en.md

@@ -32,13 +32,19 @@ The 3D multimodal fusion detection module is a key component in the fields of co
       <li><b>Performance Test Environment</b>
           <ul>
           <li><strong>Test Dataset:</strong>The above accuracy metrics are based on the <a href="https://www.nuscenes.org/nuscenes">nuscenes</a> validation set with mAP(0.5:0.95) and NDS 60.9, and the precision type is FP32.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/3d_bev_detection.md

@@ -40,7 +40,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/anomaly_detection.en.md

@@ -35,13 +35,19 @@ Unsupervised anomaly detection is a technology that automatically identifies and
       <li><b>Performance Test Environment</b>
           <ul>
               <li><strong>Test Dataset:</strong>The above model accuracy indicators are measured from the MVTec_AD dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/anomaly_detection.md

@@ -40,7 +40,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/face_detection.en.md

@@ -67,13 +67,19 @@ Face detection is a fundamental task in object detection, aiming to automaticall
       <li><b>Performance Test Environment</b>
           <ul>
                     <li><strong>Test Dataset:</strong>The above accuracy metrics are evaluated on the WIDER-FACE validation set with an input size of 640*640.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/face_detection.md

@@ -70,7 +70,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/face_feature.en.md

@@ -51,13 +51,19 @@ Face feature models typically take standardized face images processed through de
       <li><b>Performance Test Environment</b>
           <ul>
                <li><strong>Test Dataset:</strong>The above accuracy metrics are Accuracy scores measured on the AgeDB-30, CFP-FP, and LFW datasets.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/face_feature.md

@@ -56,7 +56,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/human_detection.en.md

@@ -47,13 +47,19 @@ Human detection is a subtask of object detection, which utilizes computer vision
       <li><b>Performance Test Environment</b>
           <ul>
                 <li><strong>Test Dataset:</strong>The evaluation set for the above accuracy metrics is CrowdHuman dataset mAP(0.5:0.95).</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/human_detection.md

@@ -50,7 +50,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/human_keypoint_detection.en.md

@@ -51,13 +51,19 @@ Keypoint detection algorithms mainly include two approaches: Top-Down and Bottom
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong>The above accuracy metrics are based on the COCO dataset AP(0.5:0.95) using ground truth annotations for bounding boxes.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/human_keypoint_detection.md

@@ -55,7 +55,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/image_classification.en.md

@@ -773,13 +773,19 @@ The image classification module is a crucial component in computer vision system
       <li><b>Performance Test Environment</b>
           <ul>
                 <li><strong>Test Dataset:</strong><a href="https://www.image-net.org/index.php">ImageNet-1k</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/image_classification.md

@@ -772,7 +772,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/image_feature.en.md

@@ -52,13 +52,19 @@ The image feature module is one of the important tasks in computer vision, prima
       <li><b>Performance Test Environment</b>
           <ul>
               <li><strong>Test Dataset:</strong>PaddleX Custom Dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/image_feature.md

@@ -56,7 +56,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/image_multilabel_classification.en.md

@@ -79,13 +79,19 @@ The image multi-label classification module is a crucial component in computer v
       <li><b>Performance Test Environment</b>
           <ul>
           <li><strong>Test Dataset:</strong>multi-label classification task on  <a href="https://cocodataset.org/#home">COCO2017</a></li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/image_multilabel_classification.md

@@ -83,7 +83,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/instance_segmentation.en.md

@@ -182,13 +182,19 @@ The instance segmentation module is a crucial component in computer vision syste
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong><a href="https://cocodataset.org/#home">COCO2017</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/instance_segmentation.md

@@ -186,7 +186,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/mainbody_detection.en.md

@@ -38,13 +38,19 @@ Mainbody detection is a fundamental task in object detection, aiming to identify
       <li><b>Performance Test Environment</b>
           <ul>
               <li><strong>Test Dataset:</strong>PaddleClas mainbody detection dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/mainbody_detection.md

@@ -42,7 +42,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/object_detection.en.md

@@ -430,13 +430,19 @@ The object detection module is a crucial component in computer vision systems, r
       <li><b>Performance Test Environment</b>
           <ul>
             <li><strong>Test Dataset:</strong> <a href="https://cocodataset.org/#home">COCO2017</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/object_detection.md

@@ -434,7 +434,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.en.md

@@ -47,13 +47,19 @@ Open-vocabulary object detection is an advanced object detection technology aime
       <li><b>Performance Test Environment</b>
           <ul>
               <li><strong>Test Dataset:</strong>  Based on the open vocabulary object detection model trained on the three datasets: O365, GoldG, and Cap4M.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/open_vocabulary_detection.md

@@ -52,7 +52,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.en.md

@@ -39,13 +39,19 @@ Open-vocabulary segmentation is an image segmentation task that aims to segment
   <ul>
       <li><b>Performance Test Environment</b>
           <ul>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/open_vocabulary_segmentation.md

@@ -44,7 +44,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.en.md

@@ -40,13 +40,19 @@ Pedestrian attribute recognition is a crucial component in computer vision syste
       <li><b>Performance Test Environment</b>
           <ul>
                 <li><strong>Test Dataset:</strong> PaddleX's internal self-built dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/pedestrian_attribute_recognition.md

@@ -44,7 +44,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/rotated_object_detection.en.md

@@ -35,13 +35,19 @@ Rotated object detection is a derivative of the object detection module, specifi
       <li><b>Performance Test Environment</b>
           <ul>
                  <li><strong>Test Dataset:</strong>  <a href="https://captain-whu.github.io/DOTA/">DOTA</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/rotated_object_detection.md

@@ -39,7 +39,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/semantic_segmentation.en.md

@@ -229,13 +229,19 @@ Semantic segmentation is a technique in computer vision that classifies each pix
       <li><b>Performance Test Environment</b>
           <ul>
             <li><strong>Test Dataset:</strong>  <a href="https://groups.csail.mit.edu/vision/datasets/ADE20K/">ADE20k</a> dataset and <a href="https://www.cityscapes-dataset.com/">Cityscapes</a> dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/semantic_segmentation.md

@@ -234,7 +234,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/small_object_detection.en.md

@@ -55,13 +55,19 @@ Small object detection typically refers to accurately detecting and locating sma
       <li><b>Performance Test Environment</b>
           <ul>
                 <li><strong>Test Dataset:</strong>  VisDrone-DET dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/small_object_detection.md

@@ -60,7 +60,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.en.md

@@ -40,13 +40,19 @@ Vehicle attribute recognition is a crucial component in computer vision systems.
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong>  VeRi dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/vehicle_attribute_recognition.md

@@ -44,7 +44,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/cv_modules/vehicle_detection.en.md

@@ -42,13 +42,19 @@ Vehicle detection is a subtask of object detection, specifically referring to th
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong>  PPVehicle dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/cv_modules/vehicle_detection.md

@@ -48,7 +48,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.en.md

@@ -40,13 +40,19 @@ The document image orientation classification module is aim to distinguish the o
       <li><b>Performance Test Environment</b>
           <ul>
              <li><strong>Test Dataset:</strong> Self-built multi-scene dataset (1000 images, including ID cards/documents, etc.)</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/doc_img_orientation_classification.md

@@ -44,7 +44,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/formula_recognition.en.md

@@ -99,13 +99,19 @@ The formula recognition module is a crucial component of OCR (Optical Character
       <li><b>Performance Test Environment</b>
           <ul>
               <li><strong>Test Dataset:</strong>PaddleX Internal Self-built Formula Recognition Test Set</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/formula_recognition.md

@@ -101,7 +101,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/layout_detection.en.md

@@ -257,13 +257,19 @@ The core task of structure analysis is to parse and segment the content of input
                    <li>17-Class Area Detection Model: A self-built layout area detection dataset by PaddleOCR, including 892 common document type images such as Chinese and English papers, magazines, and research reports.</li>
                  </ul>
              </li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/layout_detection.md

@@ -266,7 +266,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/seal_text_detection.en.md

@@ -49,13 +49,19 @@ The seal text detection module typically outputs multi-point bounding boxes arou
       <li><b>Performance Test Environment</b>
           <ul>
                <li><strong>Test Dataset:</strong> PaddleX Custom Dataset, Containing 500 Images of Circular Stamps.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/seal_text_detection.md

@@ -52,7 +52,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/table_cells_detection.en.md

@@ -40,13 +40,19 @@ The table cell detection module is a key component of table recognition tasks, r
       <li><b>Performance Test Environment</b>
           <ul>
              <li><strong>Test Dataset:</strong> PaddleX Internal Self-built Evaluation Dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/table_cells_detection.md

@@ -44,7 +44,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/table_classification.en.md

@@ -33,13 +33,19 @@ The table classification module is a key component of a computer vision system,
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong> PaddleX Internal Self-built Evaluation Dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/table_classification.md

@@ -38,7 +38,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/table_structure_recognition.en.md

@@ -60,13 +60,19 @@ SLANet_plus is an enhanced version of SLANet, a table structure recognition mode
       <li><b>Performance Test Environment</b>
           <ul>
           <li><strong>Test Dataset:</strong> PaddleX Internal Self-built Evaluation Dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/table_structure_recognition.md

@@ -62,7 +62,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/text_detection.en.md

@@ -83,13 +83,19 @@ The text detection module is a crucial component in OCR (Optical Character Recog
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong>PaddleOCR3.0 newly constructed multilingual dataset (including Chinese, Traditional Chinese, English, Japanese), covering street scenes, web images, documents, handwriting, blur, rotation, distortion, etc., totaling 2677 images.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/text_detection.md

@@ -89,7 +89,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/text_image_unwarping.en.md

@@ -40,13 +40,19 @@ The primary purpose of Text Image Unwarping is to perform geometric transformati
           <ul>
           <li><strong>Test Dataset:</strong>
           <a href="https://www3.cs.stonybrook.edu/~cvl/docunet.html">DocUNet benchmark</a> dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/text_image_unwarping.md

@@ -45,7 +45,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/text_recognition.en.md

@@ -384,13 +384,19 @@ The ultra-lightweight cyrillic alphabet recognition model trained based on the P
                  <li>Multilingual Recognition Model: A self-built multilingual dataset using PaddleX.</li>
                </ul>
              </li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/text_recognition.md

@@ -417,7 +417,12 @@ devanagari_PP-OCRv3_mobile_rec_infer.tar">推理模型</a>/<a href="https://padd
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.en.md

@@ -51,13 +51,19 @@ The text line orientation classification module primarily distinguishes the orie
       <li><b>Performance Test Environment</b>
           <ul>
              <li><strong>Test Dataset:</strong> PaddleX Self-built Dataset, Covering Multiple Scenarios Such as Documents and Certificates, Containing 1000 Images.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/ocr_modules/textline_orientation_classification.md

@@ -56,7 +56,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.en.md

@@ -65,13 +65,19 @@ Time series anomaly detection focuses on identifying abnormal points or periods
       <li><b>Performance Test Environment</b>
           <ul>
             <li><strong>Test Dataset:</strong> <b>PSM</b> dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/time_series_modules/time_series_anomaly_detection.md

@@ -72,7 +72,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/time_series_modules/time_series_classification.en.md

@@ -35,13 +35,19 @@ Time series classification involves identifying and categorizing different patte
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong> UWaveGestureLibrary.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/time_series_modules/time_series_classification.md

@@ -40,7 +40,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/time_series_modules/time_series_forecasting.en.md

@@ -97,13 +97,19 @@ Time series forecasting aims to predict the possible values or states at a futur
       <li><b>Performance Test Environment</b>
           <ul>
             <li><strong>Test Dataset:</strong> <a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Etth1.tar">ETTH1</a> test dataset.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/time_series_modules/time_series_forecasting.md

@@ -105,7 +105,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/video_modules/video_classification.en.md

@@ -48,13 +48,19 @@ PP-TSM is a video classification model developed by Baidu PaddlePaddle's Vision
       <li><b>Performance Test Environment</b>
           <ul>
                <li><strong>Test Dataset:</strong> <a href="https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/zh-CN/dataset/k400.md">K400</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/video_modules/video_classification.md

@@ -53,7 +53,12 @@ PP-TSM是一种百度飞桨视觉团队自研的视频分类模型。该模型
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/module_usage/tutorials/video_modules/video_detection.en.md

@@ -36,13 +36,19 @@ YOWO is a single-stage network with two branches. One branch extracts spatial fe
       <li><b>Performance Test Environment</b>
           <ul>
                <li><strong>Test Dataset:</strong> <a href="http://www.thumos.info/download.html">UCF101-24</a> test set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/module_usage/tutorials/video_modules/video_detection.md

@@ -40,7 +40,12 @@ YOWO是具有两个分支的单阶段网络。一个分支通过2D-CNN提取关
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 2 - 2
docs/pipeline_deploy/high_performance_inference.en.md

@@ -302,11 +302,11 @@ The available configuration items for `backend_config` vary for different backen
   </tr>
   <tr>
     <td><code>openvino</code></td>
-    <td><code>cpu_num_threads</code> (<code>int</code>): The number of logical processors used for CPU inference. The default is <code>8</code>.</td>
+    <td><code>cpu_num_threads</code> (<code>int</code>): The number of logical processors used for CPU inference. The default is <code>10</code>.</td>
   </tr>
   <tr>
     <td><code>onnxruntime</code></td>
-    <td><code>cpu_num_threads</code> (<code>int</code>): The number of parallel computation threads within the operator during CPU inference. The default is <code>8</code>.</td>
+    <td><code>cpu_num_threads</code> (<code>int</code>): The number of parallel computation threads within the operator during CPU inference. The default is <code>10</code>.</td>
   </tr>
   <tr>
     <td><code>tensorrt</code></td>

+ 2 - 2
docs/pipeline_deploy/high_performance_inference.md

@@ -303,11 +303,11 @@ output = model.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/
   </tr>
   <tr>
     <td><code>openvino</code></td>
-    <td><code>cpu_num_threads</code>(<code>int</code>):CPU 推理使用的逻辑处理器数量。默认为 <code>8</code>。</td>
+    <td><code>cpu_num_threads</code>(<code>int</code>):CPU 推理使用的逻辑处理器数量。默认为 <code>10</code>。</td>
   </tr>
   <tr>
     <td><code>onnxruntime</code></td>
-    <td><code>cpu_num_threads</code>(<code>int</code>):CPU 推理时算子内部的并行计算线程数。默认为 <code>8</code>。</td>
+    <td><code>cpu_num_threads</code>(<code>int</code>):CPU 推理时算子内部的并行计算线程数。默认为 <code>10</code>。</td>
   </tr>
   <tr>
     <td><code>tensorrt</code></td>

+ 101 - 36
docs/pipeline_deploy/serving.en.md

@@ -128,131 +128,131 @@ Find the high-stability serving SDK corresponding to the pipeline in the table b
 <tbody>
 <tr>
 <td>PP-ChatOCR-doc v3</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz">paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz">paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General image classification</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_image_classification_sdk.tar.gz">paddlex_hps_image_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_image_classification_sdk.tar.gz">paddlex_hps_image_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General object detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_object_detection_sdk.tar.gz">paddlex_hps_object_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_object_detection_sdk.tar.gz">paddlex_hps_object_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General instance segmentation</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_instance_segmentation_sdk.tar.gz">paddlex_hps_instance_segmentation_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_instance_segmentation_sdk.tar.gz">paddlex_hps_instance_segmentation_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General semantic segmentation</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_semantic_segmentation_sdk.tar.gz">paddlex_hps_semantic_segmentation_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_semantic_segmentation_sdk.tar.gz">paddlex_hps_semantic_segmentation_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Image multi-label classification</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_image_multilabel_classification_sdk.tar.gz">paddlex_hps_image_multilabel_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_image_multilabel_classification_sdk.tar.gz">paddlex_hps_image_multilabel_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General image recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_PP-ShiTuV2_sdk.tar.gz">paddlex_hps_PP-ShiTuV2_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_PP-ShiTuV2_sdk.tar.gz">paddlex_hps_PP-ShiTuV2_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Pedestrian attribute recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz">paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz">paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Vehicle attribute recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz">paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz">paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Face recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_face_recognition_sdk.tar.gz">paddlex_hps_face_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_face_recognition_sdk.tar.gz">paddlex_hps_face_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Small object detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_small_object_detection_sdk.tar.gz">paddlex_hps_small_object_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_small_object_detection_sdk.tar.gz">paddlex_hps_small_object_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Image anomaly detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_anomaly_detection_sdk.tar.gz">paddlex_hps_anomaly_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_anomaly_detection_sdk.tar.gz">paddlex_hps_anomaly_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Human keypoint detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_human_keypoint_detection_sdk.tar.gz">paddlex_hps_human_keypoint_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_human_keypoint_detection_sdk.tar.gz">paddlex_hps_human_keypoint_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Open vocabulary detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_open_vocabulary_detection_sdk.tar.gz">paddlex_hps_open_vocabulary_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_open_vocabulary_detection_sdk.tar.gz">paddlex_hps_open_vocabulary_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Open vocabulary segmentation</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz">paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz">paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Rotated object detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_rotated_object_detection_sdk.tar.gz">paddlex_hps_rotated_object_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_rotated_object_detection_sdk.tar.gz">paddlex_hps_rotated_object_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>3D multi-modal fusion detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_3d_bev_detection_sdk.tar.gz">paddlex_hps_3d_bev_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_3d_bev_detection_sdk.tar.gz">paddlex_hps_3d_bev_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General OCR</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_OCR_sdk.tar.gz">paddlex_hps_OCR_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_OCR_sdk.tar.gz">paddlex_hps_OCR_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General table recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_table_recognition_sdk.tar.gz">paddlex_hps_table_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_table_recognition_sdk.tar.gz">paddlex_hps_table_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General table recognition v2</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_table_recognition_v2_sdk.tar.gz">paddlex_hps_table_recognition_v2_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_table_recognition_v2_sdk.tar.gz">paddlex_hps_table_recognition_v2_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General layout parsing</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_layout_parsing_sdk.tar.gz">paddlex_hps_layout_parsing_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_layout_parsing_sdk.tar.gz">paddlex_hps_layout_parsing_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>PP-StructureV3</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_PP-StructureV3_sdk.tar.gz">paddlex_hps_PP-StructureV3_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_PP-StructureV3_sdk.tar.gz">paddlex_hps_PP-StructureV3_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Formula recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_formula_recognition_sdk.tar.gz">paddlex_hps_formula_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_formula_recognition_sdk.tar.gz">paddlex_hps_formula_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Seal text recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_seal_recognition_sdk.tar.gz">paddlex_hps_seal_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_seal_recognition_sdk.tar.gz">paddlex_hps_seal_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Document image preprocessing</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_doc_preprocessor_sdk.tar.gz">paddlex_hps_doc_preprocessor_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_doc_preprocessor_sdk.tar.gz">paddlex_hps_doc_preprocessor_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Time series forecasting</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_ts_forecast_sdk.tar.gz">paddlex_hps_ts_forecast_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_ts_forecast_sdk.tar.gz">paddlex_hps_ts_forecast_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Time series anomaly detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_ts_anomaly_detection_sdk.tar.gz">paddlex_hps_ts_anomaly_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_ts_anomaly_detection_sdk.tar.gz">paddlex_hps_ts_anomaly_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Time series classification</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_ts_classification_sdk.tar.gz">paddlex_hps_ts_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_ts_classification_sdk.tar.gz">paddlex_hps_ts_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Multilingual speech recognition</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_multilingual_speech_recognition_sdk.tar.gz">paddlex_hps_multilingual_speech_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_multilingual_speech_recognition_sdk.tar.gz">paddlex_hps_multilingual_speech_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General video classification</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_video_classification_sdk.tar.gz">paddlex_hps_video_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_video_classification_sdk.tar.gz">paddlex_hps_video_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>General video detection</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_video_detection_sdk.tar.gz">paddlex_hps_video_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_video_detection_sdk.tar.gz">paddlex_hps_video_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>Document understanding</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_doc_understanding_sdk.tar.gz">paddlex_hps_doc_understanding_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_doc_understanding_sdk.tar.gz">paddlex_hps_doc_understanding_sdk.tar.gz</a></td>
 </tr>
 </tbody>
 </table>
@@ -308,13 +308,13 @@ First, pull the Docker image as needed:
 - Image supporting deployment with NVIDIA GPU (the machine must have NVIDIA drivers that support CUDA 11.8 installed):
 
     ```bash
-    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1.0-gpu
+    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1-gpu
     ```
 
 - CPU-only Image:
 
     ```bash
-    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1.0-cpu
+    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1-cpu
     ```
 
 With the image prepared, navigate to the `server` directory and execute the following command to run the server:
@@ -350,7 +350,13 @@ I1216 11:37:21.643494 35 http_server.cc:167] Started Metrics Service at 0.0.0.0:
 
 ### 2.4 Invoke the Service
 
-Currently, only the Python client is supported for calling the service. Supported Python versions are 3.8 to 3.12.
+Users can call the pipeline service through the Python client provided by the SDK or by manually constructing HTTP requests (with no restriction on client programming languages). 
+
+
+The services deployed using the high-stability serving solution offer the primary operations that match those of the basic serving solution. For each primary operation, the endpoint names and the request and response data fields are consistent with the basic serving solution. Please refer to the "Development Integration/Deployment" section in the tutorials for each pipeline. The tutorials for each pipeline can be found [here](../pipeline_usage/pipeline_develop_guide.en.md).
+
+
+#### 2.4.1 Use Python Client
 
 Navigate to the `client` directory of the high-stability serving SDK, and run the following command to install dependencies:
 
@@ -360,6 +366,65 @@ python -m pip install -r requirements.txt
 python -m pip install paddlex_hps_client-*.whl
 ```
 
+The Python client currently supports Python versions 3.8 to 3.12.
+
 The `client.py` script in the `client` directory contains examples of how to call the service and provides a command-line interface.
 
-The services deployed using the high-stability serving solution offer the primary operations that match those of the basic serving solution. For each primary operation, the endpoint names and the request and response data fields are consistent with the basic serving solution. Please refer to the "Development Integration/Deployment" section in the tutorials for each pipeline. The tutorials for each pipeline can be found [here](../pipeline_usage/pipeline_develop_guide.en.md).
+#### 2.4.2 Manually Construct HTTP Requests
+
+The following method demonstrates how to call the service using the HTTP interface in scenarios where the Python client is not applicable.
+
+First, you need to manually construct the HTTP request body. The request body must be in JSON format and contains the following fields:
+
+- `inputs`: Input tensor information. The input tensor name `name` is uniformly set to `input`, the shape is `[1, 1]`, and the data type `datatype` is `BYTES`. The  tensor data `data` contains a single JSON string, and the content of this JSON should follow the pipeline-specific format (consistent with the basic serving solution).
+- `outputs`: Output tensor information. The output tensor name `name` is uniformly set to `output`.
+
+Taking the general OCR pipeline as an example, the constructed request body is as follows:
+
+```JSON
+{
+  "inputs": [
+    {
+      "name": "input",
+      "shape": [1, 1],
+      "datatype": "BYTES",
+      "data": [
+        "{\"file\":\"https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_001.png\",\"visualize\":false}"
+      ]
+    }
+  ],
+  "outputs": [
+    {
+      "name": "output"
+    }
+  ]
+}
+```
+
+Send the constructed request body to the corresponding HTTP inference endpoint of the service. By default, the service listens on HTTP port `8000`, and the inference request URL follows the format `http://{hostname}:8000/v2/models/{endpoint name}/infer`.
+
+Using the general OCR pipeline as an example, the following is a `curl` command to send the request:
+
+```bash
+# Assuming `REQUEST_JSON` is the request body constructed in the previous step
+curl -s -X POST http://localhost:8000/v2/models/ocr/infer \
+    -H 'Content-Type: application/json' \
+    -d "${REQUEST_JSON}"
+```
+
+Finally, the response from the service needs to be parsed. The raw response body has the following structure:
+
+```json
+{
+  "outputs": [
+    {
+      "name": "output",
+      "data": [
+        "{\"errorCode\": 0, \"result\": {\"ocrResults\": [...]}}"
+      ]
+    }
+  ]
+}
+```
+
+`outputs[0].data[0]` is a JSON string. The internal fields follow the same format as the response body in the basic serving solution. For detailed parsing rules, please refer to the usage guide for each specific pipeline.

+ 99 - 36
docs/pipeline_deploy/serving.md

@@ -128,131 +128,131 @@ paddlex --serve --pipeline image_classification --use_hpip
 <tbody>
 <tr>
 <td>文档场景信息抽取 v3</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz">paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz">paddlex_hps_PP-ChatOCRv3-doc_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用图像分类</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_image_classification_sdk.tar.gz">paddlex_hps_image_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_image_classification_sdk.tar.gz">paddlex_hps_image_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用目标检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_object_detection_sdk.tar.gz">paddlex_hps_object_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_object_detection_sdk.tar.gz">paddlex_hps_object_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用实例分割</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_instance_segmentation_sdk.tar.gz">paddlex_hps_instance_segmentation_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_instance_segmentation_sdk.tar.gz">paddlex_hps_instance_segmentation_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用语义分割</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_semantic_segmentation_sdk.tar.gz">paddlex_hps_semantic_segmentation_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_semantic_segmentation_sdk.tar.gz">paddlex_hps_semantic_segmentation_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用图像多标签分类</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_image_multilabel_classification_sdk.tar.gz">paddlex_hps_image_multilabel_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_image_multilabel_classification_sdk.tar.gz">paddlex_hps_image_multilabel_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用图像识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_PP-ShiTuV2_sdk.tar.gz">paddlex_hps_PP-ShiTuV2_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_PP-ShiTuV2_sdk.tar.gz">paddlex_hps_PP-ShiTuV2_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>行人属性识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz">paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz">paddlex_hps_pedestrian_attribute_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>车辆属性识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz">paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz">paddlex_hps_vehicle_attribute_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>人脸识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_face_recognition_sdk.tar.gz">paddlex_hps_face_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_face_recognition_sdk.tar.gz">paddlex_hps_face_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>小目标检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_small_object_detection_sdk.tar.gz">paddlex_hps_small_object_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_small_object_detection_sdk.tar.gz">paddlex_hps_small_object_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>图像异常检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_anomaly_detection_sdk.tar.gz">paddlex_hps_anomaly_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_anomaly_detection_sdk.tar.gz">paddlex_hps_anomaly_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>人体关键点检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_human_keypoint_detection_sdk.tar.gz">paddlex_hps_human_keypoint_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_human_keypoint_detection_sdk.tar.gz">paddlex_hps_human_keypoint_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>开放词汇检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_open_vocabulary_detection_sdk.tar.gz">paddlex_hps_open_vocabulary_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_open_vocabulary_detection_sdk.tar.gz">paddlex_hps_open_vocabulary_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>开放词汇分割</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz">paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz">paddlex_hps_open_vocabulary_segmentation_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>旋转目标检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_rotated_object_detection_sdk.tar.gz">paddlex_hps_rotated_object_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_rotated_object_detection_sdk.tar.gz">paddlex_hps_rotated_object_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>3D 多模态融合检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_3d_bev_detection_sdk.tar.gz">paddlex_hps_3d_bev_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_3d_bev_detection_sdk.tar.gz">paddlex_hps_3d_bev_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用 OCR</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_OCR_sdk.tar.gz">paddlex_hps_OCR_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_OCR_sdk.tar.gz">paddlex_hps_OCR_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用表格识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_table_recognition_sdk.tar.gz">paddlex_hps_table_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_table_recognition_sdk.tar.gz">paddlex_hps_table_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用表格识别 v2</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_table_recognition_v2_sdk.tar.gz">paddlex_hps_table_recognition_v2_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_table_recognition_v2_sdk.tar.gz">paddlex_hps_table_recognition_v2_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用版面解析</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_layout_parsing_sdk.tar.gz">paddlex_hps_layout_parsing_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_layout_parsing_sdk.tar.gz">paddlex_hps_layout_parsing_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用版面解析 v3</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_PP-StructureV3_sdk.tar.gz">paddlex_hps_PP-StructureV3_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_PP-StructureV3_sdk.tar.gz">paddlex_hps_PP-StructureV3_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>公式识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_formula_recognition_sdk.tar.gz">paddlex_hps_formula_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_formula_recognition_sdk.tar.gz">paddlex_hps_formula_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>印章文本识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_seal_recognition_sdk.tar.gz">paddlex_hps_seal_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_seal_recognition_sdk.tar.gz">paddlex_hps_seal_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>文档图像预处理</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_doc_preprocessor_sdk.tar.gz">paddlex_hps_doc_preprocessor_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_doc_preprocessor_sdk.tar.gz">paddlex_hps_doc_preprocessor_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>时序预测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_ts_forecast_sdk.tar.gz">paddlex_hps_ts_forecast_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_ts_forecast_sdk.tar.gz">paddlex_hps_ts_forecast_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>时序异常检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_ts_anomaly_detection_sdk.tar.gz">paddlex_hps_ts_anomaly_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_ts_anomaly_detection_sdk.tar.gz">paddlex_hps_ts_anomaly_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>时序分类</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_ts_classification_sdk.tar.gz">paddlex_hps_ts_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_ts_classification_sdk.tar.gz">paddlex_hps_ts_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>多语种语音识别</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_multilingual_speech_recognition_sdk.tar.gz">paddlex_hps_multilingual_speech_recognition_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_multilingual_speech_recognition_sdk.tar.gz">paddlex_hps_multilingual_speech_recognition_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用视频分类</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_video_classification_sdk.tar.gz">paddlex_hps_video_classification_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_video_classification_sdk.tar.gz">paddlex_hps_video_classification_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>通用视频检测</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_video_detection_sdk.tar.gz">paddlex_hps_video_detection_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_video_detection_sdk.tar.gz">paddlex_hps_video_detection_sdk.tar.gz</a></td>
 </tr>
 <tr>
 <td>文档理解</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1.0/paddlex_hps_doc_understanding_sdk.tar.gz">paddlex_hps_doc_understanding_sdk.tar.gz</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hps/public/sdks/v3.1/paddlex_hps_doc_understanding_sdk.tar.gz">paddlex_hps_doc_understanding_sdk.tar.gz</a></td>
 </tr>
 </tbody>
 </table>
@@ -308,13 +308,13 @@ paddlex --serve --pipeline image_classification --use_hpip
 - 支持使用 NVIDIA GPU 部署的镜像(机器上需要安装有支持 CUDA 11.8 的 NVIDIA 驱动):
 
     ```bash
-    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1.0-gpu
+    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1-gpu
     ```
 
 - CPU-only 镜像:
 
     ```bash
-    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1.0-cpu
+    docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.1-cpu
     ```
 
 准备好镜像后,切换到 `server` 目录,执行如下命令运行服务器:
@@ -350,7 +350,11 @@ I1216 11:37:21.643494 35 http_server.cc:167] Started Metrics Service at 0.0.0.0:
 
 ### 2.4 调用服务
 
-目前,仅支持使用 Python 客户端调用服务。支持的 Python 版本为 3.8 至 3.12。
+用户可以通过 SDK 中的 Python 客户端调用产线服务,或者手动构造 HTTP 请求(对客户端语言无限制)。
+
+使用高稳定性服务化部署方案部署的服务,提供与基础服务化部署方案相匹配的主要操作。对于每个主要操作,端点名称以及请求和响应的数据字段都与基础服务化部署方案保持一致。请参阅各产线使用教程中的 <b>“开发集成/部署”</b> 部分。在 [此处](../pipeline_usage/pipeline_develop_guide.md) 可以找到各产线的使用教程。
+
+#### 2.4.1 使用 Python 客户端
 
 切换到高稳定性服务化部署 SDK 的 `client` 目录,执行如下命令安装依赖:
 
@@ -360,6 +364,65 @@ python -m pip install -r requirements.txt
 python -m pip install paddlex_hps_client-*.whl
 ```
 
+Python 客户端目前支持的 Python 版本为 3.8 至 3.12。
+
 `client` 目录的 `client.py` 脚本包含服务的调用示例,并提供命令行接口。
 
-使用高稳定性服务化部署方案部署的服务,提供与基础服务化部署方案相匹配的主要操作。对于每个主要操作,端点名称以及请求和响应的数据字段都与基础服务化部署方案保持一致。请参阅各产线使用教程中的 <b>“开发集成/部署”</b> 部分。在 [此处](../pipeline_usage/pipeline_develop_guide.md) 可以找到各产线的使用教程。
+#### 2.4.2 手动构造 HTTP 请求
+
+以下方式手工构造 HTTP 请求体并调用,适用于 Python 客户端不适用的情形。
+
+首先,需要构造请求体。请求体为 JSON 格式,包含以下字段:
+
+- `inputs`:输入张量信息。输入张量名称 `name` 统一为 `input`,张量形状 `shape` 为 `[1, 1]`,数据类型 `datatype` 为 `BYTES`。张量数据 `data` 包含一个 JSON 字符串,JSON 的内容需对应不同产线字段(与基础服务化部署一致)。
+- `outputs`:输出张量信息。输出张量名称 `name` 统一为`output`。
+
+以通用 OCR 产线为例,构造的请求体内容示例如下:
+
+```JSON
+{
+  "inputs": [
+    {
+      "name": "input",
+      "shape": [1, 1],
+      "datatype": "BYTES",
+      "data": [
+        "{\"file\":\"https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_001.png\",\"visualize\":false}"
+      ]
+    }
+  ],
+  "outputs": [
+    {
+      "name": "output"
+    }
+  ]
+}
+```
+
+将构造好的请求体通过发送到服务对应的 HTTP 推理端点。服务默认监听的 HTTP 端口为 `8000`,推理请求的 URL 格式为 `http://{主机名}:8000/v2/models/{端点名称}/infer`。
+
+以通用 OCR 产线为例,如下是通过 `curl` 向发送请求的例子:
+
+```bash
+# 假设 `REQUEST_JSON` 为上一步骤中构造的请求体
+curl -s -X POST http://localhost:8000/v2/models/ocr/infer \
+    -H 'Content-Type: application/json' \
+    -d "${REQUEST_JSON}"
+```
+
+最后,需要解析服务的响应。响应体的原始结构如下:
+
+```json
+{
+  "outputs": [
+    {
+      "name": "output",
+      "data": [
+        "{\"errorCode\": 0, \"result\": {\"ocrResults\": [...]}}"
+      ]
+    }
+  ]
+}
+```
+
+其中 `outputs[0].data[0]` 是一个 JSON 字符串,其中的字段与基础服务化部署方案中的响应体保持一致,具体解析规则可以查看各产线使用教程。

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.en.md

@@ -41,13 +41,19 @@ Please note that the 3D multi-modal fusion detection pipeline currently does not
       <li><b>Performance Test Environment</b>
           <ul>
               <li><strong>Test Dataset:</strong><a href="https://www.nuscenes.org/nuscenes">nuscenes</a> validation set</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.md

@@ -45,7 +45,12 @@ BEVFusion 是一种多模态 3D 目标检测模型,通过将环视摄像头图
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.en.md

@@ -113,13 +113,19 @@ The face recognition pipeline is an end-to-end system dedicated to solving face
                 <li>Face Feature Model: Evaluated on the AgeDB-30, CFP-FP, and LFW datasets, respectively.</li>
               </ul>
             </li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.md

@@ -118,7 +118,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.en.md

@@ -82,13 +82,19 @@ PP-ShiTuV2 is a practical general image recognition system mainly composed of th
                 <li>Image Feature Model: AliProducts Dataset.</li>
               </ul>
             </li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.md

@@ -86,7 +86,12 @@ PP-ShiTuV2 是一个实用的通用图像识别系统,主要由主体检测、
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.en.md

@@ -85,13 +85,19 @@ PaddleX's Human Keypoint Detection Pipeline is a Top-Down solution consisting of
                 <li>Human Keypoint Detection Model: COCO Dataset AP(0.5:0.95), with detection boxes obtained from ground truth annotations.</li>
               </ul>
             </li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.md

@@ -89,7 +89,12 @@ PaddleX 的人体关键点检测产线是一个 Top-Down 方案,由行人检
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.en.md

@@ -36,13 +36,19 @@ This pipeline integrates the high-precision anomaly detection model STFPM, which
       <li><b>Performance Test Environment</b>
           <ul>
             <li><strong>Test Dataset:</strong>The above accuracy metrics are the average anomaly scores on the <b><a href="https://www.mvtec.com/company/research/datasets/mvtec-ad">MVTec AD</a></b> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md

@@ -44,7 +44,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/image_classification.en.md

@@ -780,13 +780,19 @@ Image classification is a technique that assigns images to predefined categories
       <li><b>Performance Test Environment</b>
           <ul>
              <li><strong>Test Dataset:</strong><a href="https://www.image-net.org/index.php">ImageNet-1k</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md

@@ -783,7 +783,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md

@@ -65,13 +65,19 @@ Image multi-label classification is a technique that assigns multiple relevant c
       <li><b>Performance Test Environment</b>
           <ul>
              <li><strong>Test Dataset:</strong>multi-label classification task on <b><a href="https://cocodataset.org/#home">COCO2017</a></b>.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -72,7 +72,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md

@@ -182,13 +182,19 @@ Instance segmentation is a computer vision task that not only identifies the obj
       <li><b>Performance Test Environment</b>
           <ul>
            <li><strong>Test Dataset:</strong><a href="https://cocodataset.org/#home">COCO2017</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

+ 6 - 1
docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md

@@ -192,7 +192,12 @@ comments: true
                   <ul>
                       <li>GPU:NVIDIA Tesla T4</li>
                       <li>CPU:Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>其他环境:Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                  </ul>
+              </li>
+              <li><strong>软件环境:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
                   </ul>
               </li>
           </ul>

+ 8 - 2
docs/pipeline_usage/tutorials/cv_pipelines/object_detection.en.md

@@ -423,13 +423,19 @@ Object detection aims to identify the categories and locations of multiple objec
       <li><b>Performance Test Environment</b>
           <ul>
                <li><strong>Test Dataset:</strong><a href="https://cocodataset.org/#home">COCO2017</a> validation set.</li>
-              <li><strong>Hardware Configuration</strong>
+              <li><strong>Hardware Configuration:</strong>
                   <ul>
                       <li>GPU: NVIDIA Tesla T4</li>
                       <li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
-                      <li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
                   </ul>
               </li>
+              <li><strong>Software Environment:</strong>
+                  <ul>
+                      <li>Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
+                      <li>paddlepaddle 3.0.0 / paddlex 3.0.3</li>
+                  </ul>
+              </li>
+              </li>
           </ul>
       </li>
       <li><b>Inference Mode Description</b></li>

Niektoré súbory nie sú zobrazené, pretože je v týchto rozdielových dátach zmenené mnoho súborov