update multi-hardware install docs and modle list (#3316)

README.md

@@ -406,7 +406,7 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI
     <td>✅</td>
     <td>✅</td>
     <td>✅</td>
-    <td>🚧</td>
+    <td>✅</td>
   </tr>
   <tr>
     <td>通用表格识别</td>
@@ -420,7 +420,7 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI
     <td>✅</td>
     <td>✅</td>
     <td>✅</td>
-    <td>🚧</td>
+    <td>✅</td>
   </tr>
   <tr>
     <td>通用实例分割</td>
@@ -448,7 +448,7 @@ PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI
     <td>✅</td>
     <td>✅</td>
     <td>✅</td>
-    <td>🚧</td>
+    <td>✅</td>
   </tr>
   <tr>
     <td>时序异常检测</td>

docs/other_devices_support/paddlepaddle_install_DCU.en.md

@@ -27,7 +27,7 @@ Within the started docker container, download and install the wheel package rele
 
 ```bash
 # Download and install the wheel package
-pip install paddlepaddle-rocm -i https://www.paddlepaddle.org.cn/packages/nightly/dcu
+pip install paddlepaddle-dcu -i https://www.paddlepaddle.org.cn/packages/nightly/dcu
 ```
 
 After the installation package is installed, run the following command to verify it:

docs/other_devices_support/paddlepaddle_install_DCU.md

@@ -26,7 +26,7 @@ docker run -it --name paddle-dcu-dev -v `pwd`:/work \
 
 ```
 # 下载并安装 wheel 包
-pip install paddlepaddle-rocm -i https://www.paddlepaddle.org.cn/packages/nightly/dcu
+pip install paddlepaddle-dcu -i https://www.paddlepaddle.org.cn/packages/nightly/dcu
 ```
 验证安装包 安装完成之后，运行如下命令
 

docs/other_devices_support/paddlepaddle_install_MLU.en.md

@@ -30,8 +30,8 @@ Within the started docker container, download and install the wheel package rele
 ```bash
 # Download and install the wheel package
 # Note: You need to install the CPU version of PaddlePaddle first
-python -m pip install paddlepaddle==3.0.0.dev20240624 -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
-python -m pip install paddle-custom-mlu==3.0.0.dev20240806 -i https://www.paddlepaddle.org.cn/packages/nightly/mlu/
+python -m pip install paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu
+python -m pip install paddle-custom-mlu -i https://www.paddlepaddle.org.cn/packages/nightly/mlu
 ```
 
 Verify the installation. After installation, run the following command:

docs/other_devices_support/paddlepaddle_install_MLU.md

@@ -30,8 +30,8 @@ docker run -it --name paddle-mlu-dev -v $(pwd):/work \
 ```
 # 下载并安装 wheel 包
 # 注意需要先安装飞桨 cpu 版本
-python -m pip install paddlepaddle==3.0.0.dev20240624 -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
-python -m pip install paddle-custom-mlu==3.0.0.dev20240806 -i https://www.paddlepaddle.org.cn/packages/nightly/mlu/
+python -m pip install paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu
+python -m pip install paddle-custom-mlu -i https://www.paddlepaddle.org.cn/packages/nightly/mlu
 ```
 验证安装包 安装完成之后，运行如下命令
 

docs/other_devices_support/paddlepaddle_install_NPU.en.md

@@ -30,8 +30,8 @@ Currently, Python 3.9 wheel installation packages are provided. If you have a ne
 * Download and install the Python 3.9 wheel installation package
 ```bash
 # Note: You need to install the CPU version of PaddlePaddle first
-python3.9 -m pip install paddlepaddle==3.0.0.dev20240520 -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
-python3.9 -m pip install paddle_custom_npu==3.0.0.dev20240719 -i https://www.paddlepaddle.org.cn/packages/nightly/npu/
+python -m pip install paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu
+python -m pip install paddle-custom-npu -i https://www.paddlepaddle.org.cn/packages/nightly/npu
 ```
 * Set environment variables on the arm machine (not required for x86 environment)
 ```bash

docs/other_devices_support/paddlepaddle_install_NPU.md

@@ -30,8 +30,8 @@ docker run -it --name paddle-npu-dev -v $(pwd):/work \
 * 下载安装 Python3.9 的 wheel 安装包
 ```bash
 # 注意需要先安装飞桨 cpu 版本
-python3.9 -m pip install paddlepaddle==3.0.0.dev20240520 -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
-python3.9 -m pip install paddle_custom_npu==3.0.0.dev20240719 -i https://www.paddlepaddle.org.cn/packages/nightly/npu/
+python -m pip install paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu
+python -m pip install paddle-custom-npu -i https://www.paddlepaddle.org.cn/packages/nightly/npu
 ```
 * arm机器上需要设置环境变量（x86环境无需设置）
 ```bash

docs/support_list/model_list_dcu.en.md

@@ -41,6 +41,11 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>78.3</td>
 <td>214.2 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>PP-LCNet_x1_0</td>
+<td>71.32</td>
+<td>10.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-LCNet_x1_0_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LCNet_x1_0_pretrained.pdparams">Trained Model</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are Top-1 Accuracy on the [ImageNet-1k](https://www.image-net.org/index.php) validation set.</b>
@@ -59,22 +64,22 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>CLIP_vit_base_patch16_448_ML</td>
 <td>89.15</td>
 <td>325.6 M</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/CLIP_vit_base_patch16_448_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/CLIP_vit_base_patch16_448_ML_pretrained.pdparams">Training Model</a></td></tr>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/CLIP_vit_base_patch16_448_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/CLIP_vit_base_patch16_448_ML_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
 <td>PP-HGNetV2-B0_ML</td>
 <td>80.98</td>
 <td>39.6 M</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNetV2-B0_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B0_ML_pretrained.pdparams">Training Model</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNetV2-B0_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B0_ML_pretrained.pdparams">Trained Model</a></td>
 <tr>
 <td>PP-HGNetV2-B4_ML</td>
 <td>87.96</td>
 <td>88.5 M</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNetV2-B4_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B4_ML_pretrained.pdparams">Training Model</a></td></tr>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNetV2-B4_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B4_ML_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
 <td>PP-HGNetV2-B6_ML</td>
 <td>91.06</td>
 <td>286.5 M</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNetV2-B6_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B6_ML_pretrained.pdparams">Training Model</a></td></tr>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNetV2-B6_ML_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNetV2-B6_ML_pretrained.pdparams">Trained Model</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are for the multi-label classification task mAP of [COCO2017](https://cocodataset.org/#home).</b>
@@ -148,6 +153,36 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>54.7</td>
 <td>349.4 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-YOLOE_plus-X_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-YOLOE_plus-X_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>RT-DETR-R18</td>
+<td>46.5</td>
+<td>70.7 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-R18_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-R18_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>FCOS-ResNet50</td>
+<td>39.6</td>
+<td>124.2 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/FCOS-ResNet50_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/FCOS-ResNet50_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>YOLOX-N</td>
+<td>26.1</td>
+<td>3.4M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOX-N_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOX-N_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>FasterRCNN-ResNet34-FPN</td>
+<td>37.8</td>
+<td>137.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/FasterRCNN-ResNet34-FPN_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/FasterRCNN-ResNet34-FPN_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>YOLOv3-DarkNet53</td>
+<td>39.1</td>
+<td>219.7 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOv3-DarkNet53_infer.tar">Inference ModelInference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOv3-DarkNet53_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>Cascade-FasterRCNN-ResNet50-FPN</td>
+<td>41.1</td>
+<td>245.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/Cascade-FasterRCNN-ResNet50-FPN_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/Cascade-FasterRCNN-ResNet50-FPN_pretrained.pdparams">Trained Model</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are mAP(0.5:0.95) on the [COCO2017](https://cocodataset.org/#home) validation set.</b>
@@ -181,7 +216,7 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </table>
 <b>Note: The above accuracy metrics are for </b>[VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset)<b> validation set mAP(0.5:0.95)。</b>
 
-## Semantic Segmentation Module
+## [Semantic Segmentation Module](../module_usage/tutorials/cv_modules/semantic_segmentation.en.md)
 <table>
 <thead>
 <tr>
@@ -201,6 +236,11 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>81.10</td>
 <td>162.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/Deeplabv3_Plus-R101_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/Deeplabv3_Plus-R101_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>PP-LiteSeg-T</td>
+<td>73.10</td>
+<td>28.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-LiteSeg-T_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LiteSeg-T_pretrained.pdparams">Trained Model</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are mIoU on the [Cityscapes](https://www.cityscapes-dataset.com/) dataset.</b>
@@ -290,3 +330,36 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </tbody>
 </table>
 <b>Note: The evaluation set for the above accuracy metrics is PaddleOCR's self-built Chinese dataset, covering street scenes, web images, documents, handwriting, and more scenarios, with 11,000 images for text recognition.</b>
+
+## [Time Series Forecasting Module](../module_usage/tutorials/time_series_modules/time_series_forecasting.en.md)
+<table>
+<thead>
+<tr>
+<th>Model Name</th>
+<th>mse</th>
+<th>mae</th>
+<th>Model Size (M)</th>
+<th>Model Download Link</th></tr>
+</thead>
+<tbody>
+<tr>
+<td>DLinear</td>
+<td>0.382</td>
+<td>0.394</td>
+<td>72K</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/DLinear_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/DLinear_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>NLinear</td>
+<td>0.386</td>
+<td>0.392</td>
+<td>40K</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/NLinear_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/NLinear_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>RLinear</td>
+<td>0.384</td>
+<td>0.392</td>
+<td>40K</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RLinear_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RLinear_pretrained.pdparams">Trained Model</a></td></tr>
+</tbody>
+</table>
+<b>Note: The above accuracy metrics are measured on the [ETTH1](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Etth1.tar) dataset (evaluation results on the test set test.csv).</b>

docs/support_list/model_list_dcu.md

@@ -6,7 +6,7 @@ comments: true
 
 PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模块包含若干模型，具体使用哪些模型，您可以根据下边的 benchmark 数据来选择。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
 
-## 图像分类模块
+## [图像分类模块](../module_usage/tutorials/cv_modules/image_classification.md)
 <table>
 <thead>
 <tr>
@@ -41,6 +41,11 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>78.3</td>
 <td>214.2 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>PP-LCNet_x1_0</td>
+<td>71.32</td>
+<td>10.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-LCNet_x1_0_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LCNet_x1_0_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标为</b>[ImageNet-1k](https://www.image-net.org/index.php)<b>验证集 Top1 Acc。</b>
@@ -98,7 +103,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为 AliProducts recall@1。</b>
 
-## 目标检测模块
+## [目标检测模块](../module_usage/tutorials/cv_modules/object_detection.md)
 <table>
 <thead>
 <tr>
@@ -148,6 +153,31 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>54.7</td>
 <td>349.4 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-YOLOE_plus-X_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-YOLOE_plus-X_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>RT-DETR-R18</td>
+<td>46.5</td>
+<td>70.7 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RT-DETR-R18_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RT-DETR-R18_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>FCOS-ResNet50</td>
+<td>39.6</td>
+<td>124.2 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/FCOS-ResNet50_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/FCOS-ResNet50_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>YOLOX-N</td>
+<td>26.1</td>
+<td>3.4M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOX-N_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOX-N_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>FasterRCNN-ResNet34-FPN</td>
+<td>37.8</td>
+<td>137.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/FasterRCNN-ResNet34-FPN_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/FasterRCNN-ResNet34-FPN_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>Cascade-FasterRCNN-ResNet50-FPN</td>
+<td>41.1</td>
+<td>245.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/Cascade-FasterRCNN-ResNet50-FPN_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/Cascade-FasterRCNN-ResNet50-FPN_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标为</b>[COCO2017](https://cocodataset.org/#home)<b>验证集 mAP(0.5:0.95)。</b>
@@ -181,7 +211,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为 </b>[VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset)<b> 验证集 mAP(0.5:0.95)。</b>
 
-## 语义分割模块
+## [语义分割模块](../module_usage/tutorials/cv_modules/semantic_segmentation.md)
 <table>
 <thead>
 <tr>
@@ -201,6 +231,11 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>81.10</td>
 <td>162.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/Deeplabv3_Plus-R101_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/Deeplabv3_Plus-R101_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>PP-LiteSeg-T</td>
+<td>73.10</td>
+<td>28.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-LiteSeg-T_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LiteSeg-T_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标为</b>[Cityscapes](https://www.cityscapes-dataset.com/)<b>数据集 mloU。</b>
@@ -244,7 +279,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 **注：以上精度指标是在WIDER-FACE验证集上，以640
 \*640作为输入尺寸评估得到的。**
 
-## 文本检测模块
+## [文本检测模块](../module_usage/tutorials/ocr_modules/text_detection.md)
 <table>
 <thead>
 <tr>
@@ -268,7 +303,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中检测包含 500 张图片。</b>
 
-## 文本识别模块
+## [文本识别模块](../module_usage/tutorials/ocr_modules/text_recognition.md)
 <table>
 <thead>
 <tr>
@@ -291,3 +326,36 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </tbody>
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中文本识别包含 1.1w 张图片。</b>
+
+## [时序预测模块](../module_usage/tutorials/time_series_modules/time_series_forecasting.md)
+<table>
+<thead>
+<tr>
+<th>模型名称</th>
+<th>mse</th>
+<th>mae</th>
+<th>模型存储大小（M)</th>
+<th>模型下载链接</th></tr>
+</thead>
+<tbody>
+<tr>
+<td>DLinear</td>
+<td>0.382</td>
+<td>0.394</td>
+<td>72K</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/DLinear_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/DLinear_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>NLinear</td>
+<td>0.386</td>
+<td>0.392</td>
+<td>40K</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/NLinear_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/NLinear_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>RLinear</td>
+<td>0.384</td>
+<td>0.392</td>
+<td>40K</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/RLinear_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/RLinear_pretrained.pdparams">训练模型</a></td></tr>
+</tbody>
+</table>
+<b>注：以上精度指标测量自</b>[ETTH1](https://paddle-model-ecology.bj.bcebos.com/paddlex/data/Etth1.tar)<b>数据集 </b><b>（在测试集test.csv上的评测结果）</b><b>。</b>

docs/support_list/model_list_mlu.en.md

@@ -67,11 +67,21 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>13.0 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/MobileNetV3_small_x1_25_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/MobileNetV3_small_x1_25_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PP-HGNet_base</td>
+<td>85.0</td>
+<td>249.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_base_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_base_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PP-HGNet_small</td>
 <td>81.51</td>
 <td>86.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_small_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_small_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PP-HGNet_tiny</td>
+<td>79.83</td>
+<td>52.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_tiny_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_tiny_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PP-LCNet_x0_5</td>
 <td>63.14</td>
 <td>6.7 M</td>
@@ -112,30 +122,60 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>32.1 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-LCNet_x2_5_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LCNet_x2_5_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet18_vd</td>
+<td>72.3</td>
+<td>41.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet18_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet18_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet18</td>
 <td>71.0</td>
 <td>41.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet18_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet18_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet34_vd</td>
+<td>76.0</td>
+<td>77.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet34_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet34_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet34</td>
 <td>74.6</td>
 <td>77.3 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet34_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet34_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet50_vd</td>
+<td>79.1</td>
+<td>90.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet50_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet50</td>
 <td>76.5</td>
 <td>90.8 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet50_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet101_vd</td>
+<td>80.2</td>
+<td>158.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet101_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet101_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet101</td>
 <td>77.6</td>
 <td>158.7 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet101_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet101_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet152_vd</td>
+<td>80.6</td>
+<td>214.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet152</td>
 <td>78.3</td>
 <td>214.2 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>ResNet200_vd</td>
+<td>80.9</td>
+<td>266.0 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet200_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet200_vd_pretrained.pdparams">Trained Model</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are Top-1 Accuracy on the [ImageNet-1k](https://www.image-net.org/index.php) validation set.</b>
@@ -156,11 +196,21 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>20.9 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PicoDet-M</td>
+<td>37.5</td>
+<td>16.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-M_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-M_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PicoDet-S</td>
 <td>29.1</td>
 <td>4.4 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PicoDet-XS</td>
+<td>26.2</td>
+<td>5.7M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-XS_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-XS_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PP-YOLOE_plus-L</td>
 <td>52.9</td>
 <td>185.3 M</td>
@@ -184,7 +234,7 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </table>
 <b>Note: The above accuracy metrics are mAP(0.5:0.95) on the [COCO2017](https://cocodataset.org/#home) validation set.</b>
 
-## Semantic Segmentation Module
+## [Semantic Segmentation Module](../module_usage/tutorials/cv_modules/semantic_segmentation.en.md)
 <table>
 <thead>
 <tr>
@@ -203,6 +253,30 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </table>
 <b>Note: The above accuracy metrics are based on the mIoU of the [Cityscapes](https://www.cityscapes-dataset.com/) dataset.</b>
 
+## [Image Feature Module](../module_usage/tutorials/cv_modules/image_feature.en.md)
+<table>
+<thead>
+<tr>
+<th>Model Name</th>
+<th>recall@1（%）</th>
+<th>Model Size</th>
+<th>Model Download Link</th></tr>
+</thead>
+<tbody>
+<tr>
+<td>PP-ShiTuV2_rec_CLIP_vit_base</td>
+<td>88.69</td>
+<td>306.6 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-ShiTuV2_rec_CLIP_vit_base_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-ShiTuV2_rec_CLIP_vit_base_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>PP-ShiTuV2_rec_CLIP_vit_large</td>
+<td>91.03</td>
+<td>1.05 G</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-ShiTuV2_rec_CLIP_vit_large_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-ShiTuV2_rec_CLIP_vit_large_pretrained.pdparams">Trained Model</a></td></tr>
+</tbody>
+</table>
+<b>Note: The above accuracy metrics are for AliProducts recall@1。</b>
+
 ## [Abnormality Detection Module](../module_usage/tutorials/cv_modules/anomaly_detection.en.md)
 <table>
 <thead>
@@ -308,7 +382,7 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </table>
 <b>Note: The evaluation set for the above accuracy metrics is PaddleOCR's self-built layout analysis dataset, containing 10,000 images.</b>
 
-## Time Series Forecasting Module
+## [Time Series Forecasting Module](../module_usage/tutorials/time_series_modules/time_series_forecasting.en.md)
 <table>
 <thead>
 <tr>

docs/support_list/model_list_mlu.md

@@ -6,7 +6,7 @@ comments: true
 
 PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模块包含若干模型，具体使用哪些模型，您可以根据下边的 benchmark 数据来选择。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
 
-## 图像分类模块
+## [图像分类模块](../module_usage/tutorials/cv_modules/image_classification.md)
 <table>
 <thead>
 <tr>
@@ -67,11 +67,21 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>13.0 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/MobileNetV3_small_x1_25_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/MobileNetV3_small_x1_25_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PP-HGNet_base</td>
+<td>85.0</td>
+<td>249.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_base_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_base_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PP-HGNet_small</td>
 <td>81.51</td>
 <td>86.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_small_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_small_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PP-HGNet_tiny</td>
+<td>79.83</td>
+<td>52.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_tiny_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_tiny_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PP-LCNet_x0_5</td>
 <td>63.14</td>
 <td>6.7 M</td>
@@ -136,11 +146,41 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>78.3</td>
 <td>214.2 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet18_vd</td>
+<td>72.3</td>
+<td>41.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet18_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet18_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet34_vd</td>
+<td>76.0</td>
+<td>77.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet34_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet34_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet50_vd</td>
+<td>79.1</td>
+<td>90.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet50_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet101_vd</td>
+<td>80.2</td>
+<td>158.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet101_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet101_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet152_vd</td>
+<td>80.6</td>
+<td>214.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet200_vd</td>
+<td>80.9</td>
+<td>266.0 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet200_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet200_vd_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标为</b>[ImageNet-1k](https://www.image-net.org/index.php)<b>验证集 Top1 Acc。</b>
 
-## 目标检测模块
+## [目标检测模块](../module_usage/tutorials/cv_modules/object_detection.md)
 <table>
 <thead>
 <tr>
@@ -156,11 +196,21 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>20.9 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PicoDet-M</td>
+<td>37.5</td>
+<td>16.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-M_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-M_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PicoDet-S</td>
 <td>29.1</td>
 <td>4.4 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PicoDet-XS</td>
+<td>26.2</td>
+<td>5.7M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-XS_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-XS_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PP-YOLOE_plus-L</td>
 <td>52.9</td>
 <td>185.3 M</td>
@@ -184,7 +234,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为</b>[COCO2017](https://cocodataset.org/#home)<b>验证集 mAP(0.5:0.95)。</b>
 
-## 语义分割模块
+## [语义分割模块](../module_usage/tutorials/cv_modules/semantic_segmentation.md)
 <table>
 <thead>
 <tr>
@@ -203,6 +253,30 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为</b>[Cityscapes](https://www.cityscapes-dataset.com/)<b>数据集 mloU。</b>
 
+## [图像特征模块](../module_usage/tutorials/cv_modules/image_feature.md)
+<table>
+<thead>
+<tr>
+<th>模型名称</th>
+<th>recall@1（%）</th>
+<th>模型存储大小</th>
+<th>模型下载链接</th></tr>
+</thead>
+<tbody>
+<tr>
+<td>PP-ShiTuV2_rec_CLIP_vit_base</td>
+<td>88.69</td>
+<td>306.6 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-ShiTuV2_rec_CLIP_vit_base_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-ShiTuV2_rec_CLIP_vit_base_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>PP-ShiTuV2_rec_CLIP_vit_large</td>
+<td>91.03</td>
+<td>1.05 G</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-ShiTuV2_rec_CLIP_vit_large_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-ShiTuV2_rec_CLIP_vit_large_pretrained.pdparams">训练模型</a></td></tr>
+</tbody>
+</table>
+<b>注：以上精度指标为 AliProducts recall@1。</b>
+
 ## [异常检测模块](../module_usage/tutorials/cv_modules/anomaly_detection.md)
 <table>
 <thead>
@@ -242,7 +316,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 **注：以上精度指标是在WIDER-FACE验证集上，以640
 \*640作为输入尺寸评估得到的。**
 
-## 文本检测模块
+## [文本检测模块](../module_usage/tutorials/ocr_modules/text_detection.md)
 <table>
 <thead>
 <tr>
@@ -266,7 +340,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中检测包含 500 张图片。</b>
 
-## 文本识别模块
+## [文本识别模块](../module_usage/tutorials/ocr_modules/text_recognition.md)
 <table>
 <thead>
 <tr>
@@ -290,7 +364,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中文本识别包含 1.1w 张图片。</b>
 
-## 版面区域分析模块
+## [版面区域检测模块](../module_usage/tutorials/ocr_modules/layout_detection.md)
 <table>
 <thead>
 <tr>
@@ -309,7 +383,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的版面区域分析数据集，包含 1w 张图片。</b>
 
-## 时序预测模块
+## [时序预测模块](../module_usage/tutorials/time_series_modules/time_series_forecasting.md)
 <table>
 <thead>
 <tr>

docs/support_list/model_list_npu.en.md

@@ -711,6 +711,11 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>46.9</td>
 <td>90.0 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOX-M_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOX-M_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>YOLOX-N</td>
+<td>26.1</td>
+<td>3.4M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOX-N_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOX-N_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are for </b>[VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset)<b> validation set mAP(0.5:0.95)。</b>

docs/support_list/model_list_npu.md

@@ -6,7 +6,7 @@ comments: true
 
 PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模块包含若干模型，具体使用哪些模型，您可以根据下边的 benchmark 数据来选择。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
 
-## 图像分类模块
+## [图像分类模块](../module_usage/tutorials/cv_modules/image_classification.md)
 <table>
 <thead>
 <tr>
@@ -502,7 +502,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为 VeRi 数据集 mA。</b>
 
-## 目标检测模块
+## [目标检测模块](../module_usage/tutorials/cv_modules/object_detection.md)
 <table>
 <thead>
 <tr>
@@ -711,6 +711,11 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>46.9</td>
 <td>90.0 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOX-M_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOX-M_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>YOLOX-N</td>
+<td>26.1</td>
+<td>3.4M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/YOLOX-N_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/YOLOX-N_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标为 </b>[VisDrone-DET](https://github.com/VisDrone/VisDrone-Dataset)<b> 验证集 mAP(0.5:0.95)。</b>
@@ -739,7 +744,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为 </b>[CrowdHuman](https://bj.bcebos.com/v1/paddledet/data/crowdhuman.zip)<b> 验证集 mAP(0.5:0.95)。</b>
 
-## 语义分割模块
+## [语义分割模块](../module_usage/tutorials/cv_modules/semantic_segmentation.md)
 <table>
 <thead>
 <tr>
@@ -1045,7 +1050,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为 </b>[MVTec AD](https://www.mvtec.com/company/research/datasets/mvtec-ad)<b> 验证集 平均异常分数。</b>
 
-## 文本检测模块
+## [文本检测模块](../module_usage/tutorials/ocr_modules/text_detection.md)
 <table>
 <thead>
 <tr>
@@ -1069,7 +1074,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中检测包含 500 张图片。</b>
 
-## 文本识别模块
+## [文本识别模块](../module_usage/tutorials/ocr_modules/text_recognition.md)
 <table>
 <thead>
 <tr>
@@ -1127,7 +1132,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 [PaddleOCR算法模型挑战赛 - 赛题一：OCR端到端识别任务](https://aistudio.baidu.com/competition/detail/1131/0/introduction)B榜。</b>
 
-## 表格结构识别模块
+## [表格结构识别模块](../module_usage/tutorials/ocr_modules/table_structure_recognition.md)
 <table>
 <thead>
 <tr>
@@ -1213,7 +1218,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为 PaddleX 内部自建数据集 Top-1 Acc 。</b>
 
-## 版面区域分析模块
+## [版面区域检测模块](../module_usage/tutorials/ocr_modules/layout_detection.md)
 <table>
 <thead>
 <tr>
@@ -1247,7 +1252,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的版面区域分析数据集，包含 1w 张图片。</b>
 
-## 时序预测模块
+## [时序预测模块](../module_usage/tutorials/time_series_modules/time_series_forecasting.md)
 <table>
 <thead>
 <tr>

docs/support_list/model_list_xpu.en.md

@@ -67,11 +67,21 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>13.0 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/MobileNetV3_small_x1_25_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/MobileNetV3_small_x1_25_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PP-HGNet_base</td>
+<td>85.0</td>
+<td>249.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_base_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_base_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PP-HGNet_small</td>
 <td>81.51</td>
 <td>86.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_small_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_small_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PP-HGNet_tiny</td>
+<td>79.83</td>
+<td>52.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_tiny_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_tiny_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PP-LCNet_x0_5</td>
 <td>63.14</td>
 <td>6.7 M</td>
@@ -112,30 +122,60 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>32.1 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-LCNet_x2_5_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-LCNet_x2_5_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet18_vd</td>
+<td>72.3</td>
+<td>41.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet18_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet18_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet18</td>
 <td>71.0</td>
 <td>41.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet18_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet18_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet34_vd</td>
+<td>76.0</td>
+<td>77.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet34_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet34_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet34</td>
 <td>74.6</td>
 <td>77.3 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet34_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet34_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet50_vd</td>
+<td>79.1</td>
+<td>90.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet50_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet50</td>
 <td>76.5</td>
 <td>90.8 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet50_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet101_vd</td>
+<td>80.2</td>
+<td>158.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet101_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet101_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet101</td>
 <td>77.6</td>
 <td>158.7 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet101_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet101_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>ResNet152_vd</td>
+<td>80.6</td>
+<td>214.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_vd_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>ResNet152</td>
 <td>78.3</td>
 <td>214.2 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
+<td>ResNet200_vd</td>
+<td>80.9</td>
+<td>266.0 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet200_vd_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet200_vd_pretrained.pdparams">Trained Model</a></td></tr>
 </tbody>
 </table>
 <b>Note: The above accuracy metrics are Top-1 Accuracy on the [ImageNet-1k](https://www.image-net.org/index.php) validation set.</b>
@@ -156,11 +196,21 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td>20.9 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PicoDet-M</td>
+<td>37.5</td>
+<td>16.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-M_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-M_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PicoDet-S</td>
 <td>29.1</td>
 <td>4.4 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PicoDet-XS</td>
+<td>26.2</td>
+<td>5.7M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-XS_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-XS_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PP-YOLOE_plus-L</td>
 <td>52.9</td>
 <td>185.3 M</td>
@@ -184,7 +234,7 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </table>
 <b>Note: The above accuracy metrics are mAP(0.5:0.95) on the [COCO2017](https://cocodataset.org/#home) validation set.</b>
 
-## Semantic Segmentation Module
+## [Semantic Segmentation Module](../module_usage/tutorials/cv_modules/semantic_segmentation.en.md)
 <table>
 <thead>
 <tr>
@@ -308,7 +358,7 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 </table>
 <b>Note: The evaluation set for the above accuracy metrics is PaddleOCR's self-built layout analysis dataset, containing 10,000 images.</b>
 
-## Time Series Forecasting Module
+## [Time Series Forecasting Module](../module_usage/tutorials/time_series_modules/time_series_forecasting.en.md)
 <table>
 <thead>
 <tr>

docs/support_list/model_list_xpu.md

@@ -6,7 +6,7 @@ comments: true
 
 PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模块包含若干模型，具体使用哪些模型，您可以根据下边的 benchmark 数据来选择。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
 
-## 图像分类模块
+## [图像分类模块](../module_usage/tutorials/cv_modules/image_classification.md)
 <table>
 <thead>
 <tr>
@@ -67,11 +67,21 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>13.0 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/MobileNetV3_small_x1_25_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/MobileNetV3_small_x1_25_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PP-HGNet_base</td>
+<td>85.0</td>
+<td>249.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_base_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_base_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PP-HGNet_small</td>
 <td>81.51</td>
 <td>86.5 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_small_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_small_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PP-HGNet_tiny</td>
+<td>79.83</td>
+<td>52.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-HGNet_tiny_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-HGNet_tiny_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PP-LCNet_x0_5</td>
 <td>63.14</td>
 <td>6.7 M</td>
@@ -136,11 +146,41 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>78.3</td>
 <td>214.2 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet18_vd</td>
+<td>72.3</td>
+<td>41.5 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet18_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet18_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet34_vd</td>
+<td>76.0</td>
+<td>77.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet34_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet34_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet50_vd</td>
+<td>79.1</td>
+<td>90.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet50_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet101_vd</td>
+<td>80.2</td>
+<td>158.4 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet101_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet101_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet152_vd</td>
+<td>80.6</td>
+<td>214.3 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet152_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet152_vd_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
+<td>ResNet200_vd</td>
+<td>80.9</td>
+<td>266.0 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/ResNet200_vd_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet200_vd_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标为</b>[ImageNet-1k](https://www.image-net.org/index.php)<b>验证集 Top1 Acc。</b>
 
-## 目标检测模块
+## [目标检测模块](../module_usage/tutorials/cv_modules/object_detection.md)
 <table>
 <thead>
 <tr>
@@ -156,11 +196,21 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>20.9 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-L_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-L_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PicoDet-M</td>
+<td>37.5</td>
+<td>16.8 M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-M_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-M_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PicoDet-S</td>
 <td>29.1</td>
 <td>4.4 M</td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-S_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PicoDet-XS</td>
+<td>26.2</td>
+<td>5.7M</td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PicoDet-XS_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-XS_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PP-YOLOE_plus-L</td>
 <td>52.9</td>
 <td>185.3 M</td>
@@ -184,7 +234,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标为</b>[COCO2017](https://cocodataset.org/#home)<b>验证集 mAP(0.5:0.95)。</b>
 
-## 语义分割模块
+## [语义分割模块](../module_usage/tutorials/cv_modules/semantic_segmentation.md)
 <table>
 <thead>
 <tr>
@@ -242,7 +292,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 **注：以上精度指标是在WIDER-FACE验证集上，以640
 \*640作为输入尺寸评估得到的。**
 
-## 文本检测模块
+## [文本检测模块](../module_usage/tutorials/ocr_modules/text_detection.md)
 <table>
 <thead>
 <tr>
@@ -261,12 +311,12 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td>PP-OCRv4_server_det</td>
 <td>82.69</td>
 <td>100.1M</td>
-<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-OCRv4_server_det ）_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det ）_pretrained.pdparams">训练模型</a></td></tr>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0rc0/PP-OCRv4_server_det_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_server_det_pretrained.pdparams">训练模型</a></td></tr>
 </tbody>
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中检测包含 500 张图片。</b>
 
-## 文本识别模块
+## [文本识别模块](../module_usage/tutorials/ocr_modules/text_recognition.md)
 <table>
 <thead>
 <tr>
@@ -290,7 +340,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的中文数据集，覆盖街景、网图、文档、手写多个场景，其中文本识别包含 1.1w 张图片。</b>
 
-## 版面区域分析模块
+## [版面区域检测模块](../module_usage/tutorials/ocr_modules/layout_detection.md)
 <table>
 <thead>
 <tr>
@@ -309,7 +359,7 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 </table>
 <b>注：以上精度指标的评估集是 PaddleOCR 自建的版面区域分析数据集，包含 1w 张图片。</b>
 
-## 时序预测模块
+## [时序预测模块](../module_usage/tutorials/time_series_modules/time_series_forecasting.md)
 <table>
 <thead>
 <tr>