fix (#3673)

zhang-prog · zhang-prog · commit 97939bf81d7e · 2025-03-20T11:34:18.000+08:00
diff --git a/docs/pipeline_deploy/high_performance_inference.md b/docs/pipeline_deploy/high_performance_inference.md
@@ -244,7 +244,7 @@ PaddleX 结合模型信息与运行环境信息为每个模型提供默认的高
         }
     )
 
-    output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+    output = model.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg")
     ```
 
   在 `trt_dynamic_shapes` 或 `dynamic_shapes` 中，需要为每一个输入张量指定动态形状，格式为：`{输入张量名称}: [{最小形状}, [{最优形状}], [{最大形状}]]`。有关最小形状、最优形状以及最大形状的相关介绍及更多细节，请参考 [TensorRT 官方文档](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#work_dynamic_shapes)。

Original file line number	Diff line number	Diff line change
`@@ -244,7 +244,7 @@ PaddleX 结合模型信息与运行环境信息为每个模型提供默认的高`
`244`	`244`	`}`
`245`	`245`	`)`
`246`	`246`
`247`		`- output = pipeline.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"`
	`247`	`+ output = model.predict("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg")`
`248`	`248`	```
`249`	`249`
`250`	`250`	在 `trt_dynamic_shapes` 或 `dynamic_shapes` 中，需要为每一个输入张量指定动态形状，格式为：`{输入张量名称}: [{最小形状}, [{最优形状}], [{最大形状}]]`。有关最小形状、最优形状以及最大形状的相关介绍及更多细节，请参考 [TensorRT 官方文档](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#work_dynamic_shapes)。