add shape inference instruction for TensorRT

docs/execution_providers/TensorRT-ExecutionProvider.md

@@ -19,10 +19,11 @@ status = session_object.Load(model_file_name);
 ```
 The C API details are [here](../C_API.md#c-api).
 
-If certain operators in the model are not supported by TensorRT, ONNX Runtime will partition the graph and only send supported subgraphs to TensorRT execution provider. Because TensorRT requires all inputs of the subgraph have shape specified, ONNX Runtime will thow error if there is no shape for any inputs. In this case please infer shapes on the model first by running shape inference [here](https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/core/providers/nuphar/scripts/symbolic_shape_infer.py).
+#### Shape Inference for TensorRT subgraphs
+If some operators in the model are not supported by TensorRT, ONNX Runtime will partition the graph and only send supported subgraphs to TensorRT execution provider. Because TensorRT requires that all inputs of the subgraphs have shape specified, ONNX Runtime will throw error if there is no input shape info. In this case please run shape inference for the model first by running script [here](https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/core/providers/nuphar/scripts/symbolic_shape_infer.py).
 
 #### Sample
-To run Faster R-CNN model on TensorRT execution provider,
+This example shows how to run Faster R-CNN model on TensorRT execution provider,
 
 First, download Faster R-CNN onnx model from onnx model zoo [here](https://github.com/onnx/models/tree/master/vision/object_detection_segmentation/faster-rcnn).