Browse Source

fix high_performance_deploy.md description (#2194)

* fix description

* fix description

* optimize word-spacing

* optimize table format
zhang-prog 1 năm trước cách đây
mục cha
commit
cb26c4280a

+ 10 - 9
docs/pipeline_deploy/high_performance_deploy.md

@@ -27,31 +27,32 @@
   </tr>
   <tr>
     <td>3.8</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device cpu --py 38</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.8 - --arch x86_64 --os linux --device cpu --py 38</td>
   </tr>
   <tr>
     <td>3.9</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device cpu --py 39</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.9 - --arch x86_64 --os linux --device cpu --py 39</td>
   </tr>
   <tr>
     <td>3.10</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device cpu --py 310</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.10 - --arch x86_64 --os linux --device cpu --py 310</td>
   </tr>
   <tr>
-    <td rowspan="3">GPU</td>
+    <td rowspan="3">GPU&nbsp;(CUDA&nbsp;11.8&nbsp;+&nbsp;cuDNN&nbsp;8.6)</td>
     <td>3.8</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 38</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.8 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 38</td>
   </tr>
   <tr>
     <td>3.9</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 39</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.9 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 39</td>
   </tr>
   <tr>
     <td>3.10</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 310</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.10 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 310</td>
   </tr>
 </table>
 
+* 当设备类型为 GPU 时,请使用与环境匹配的 CUDA 和 cuDNN 版本对应的安装指令,否则,将无法正常使用高性能推理插件。
 * 对于 Linux 系统,使用 Bash 执行安装指令。
 * 当设备类型为 CPU 时,安装的高性能推理插件仅支持使用 CPU 进行推理;对于其他设备类型,安装的高性能推理插件则支持使用 CPU 或其他设备进行推理。
 
@@ -105,7 +106,7 @@ pipeline = create_pipeline(
 +   use_hpip=True,
 +   serial_number="{序列号}",
 )
- 
+
  output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg")
 ```
 
@@ -272,4 +273,4 @@ PaddleX 为每个模型提供默认的高性能推理配置,并将其存储在
     <td>文档图像方向分类</td>
     <td>PP-LCNet_x1_0_doc_ori</td>
   </tr>
-</table>
+</table>

+ 13 - 9
docs/pipeline_deploy/high_performance_deploy_en.md

@@ -27,31 +27,35 @@ Find the corresponding installation command based on your processor architecture
   </tr>
   <tr>
     <td>3.8</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device cpu --py 38</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.8 - --arch x86_64 --os linux --device cpu --py 38</td>
   </tr>
   <tr>
     <td>3.9</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device cpu --py 39</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.9 - --arch x86_64 --os linux --device cpu --py 39</td>
   </tr>
   <tr>
     <td>3.10</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device cpu --py 310</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.10 - --arch x86_64 --os linux --device cpu --py 310</td>
   </tr>
   <tr>
-    <td rowspan="3">GPU</td>
+    <td rowspan="3">GPU&nbsp;(CUDA&nbsp;11.8&nbsp;+&nbsp;cuDNN&nbsp;8.6)</td>
     <td>3.8</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 38</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.8 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 38</td>
   </tr>
   <tr>
     <td>3.9</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 39</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.9 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 39</td>
   </tr>
   <tr>
     <td>3.10</td>
-    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 310</td>
+    <td>curl -s https://paddle-model-ecology.bj.bcebos.com/paddlex/PaddleX3.0/deploy/paddlex_hpi/install_script/latest/install_paddlex_hpi.py | python3.10 - --arch x86_64 --os linux --device gpu_cuda118_cudnn86 --py 310</td>
   </tr>
 </table>
 
+* When the device type is GPU, please use the installation instructions corresponding to the CUDA and cuDNN versions that match your environment. Otherwise, you will not be able to use the high-performance inference plugin properly.
+* For Linux systems, execute the installation instructions using Bash.
+* When the device type is CPU, the installed high-performance inference plugin only supports inference using the CPU; for other device types, the installed high-performance inference plugin supports inference using the CPU or other devices.
+
 ### 1.2 Obtaining Serial Numbers and Activation
 
 On the [Baidu AIStudio Community - AI Learning and Training Platform](https://aistudio.baidu.com/paddlex/commercialization) page, under the "Open-source Pipeline Deployment Serial Number Inquiry and Acquisition" section, select "Acquire Now" as shown in the following image:
@@ -103,7 +107,7 @@ pipeline = create_pipeline(
 +   use_hpip=True,
 +   serial_number="{serial_number}",
 )
- 
+
 output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg")
 ```
 
@@ -272,4 +276,4 @@ PaddleX provides default high-performance inference configurations for each mode
     <td>PP-LCNet_x1_0_doc_ori</td>
   </tr>
 
-</table>
+</table>