How to convert saved_model to onnx to run with Jetson Inference

[AastaLLL]

Hi,

ONNX use INT8 as input format but TensorRT requires a float32 buffer.
Please check below comment to update the input data type via ONNX graphsurgeon.

Exporting Tensorflow models to Jetson Nano

Hi, Elviron The root cause is onnx expects input image to be INT8 but TensorRT use Float32. To solve this issue, you can modify the input data format of ONNX with our graphsurgeon API directly. 1. Install ONNX Graphsurgeon API $ sudo apt-get install python3-pip libprotobuf-dev protobuf-compiler $ git clone https://github.com/NVIDIA/TensorRT.git $ cd TensorRT/tools/onnx-graphsurgeon/ $ make install 2. Modify your model import onnx_graphsurgeon as gs import onnx import numpy as np graph = g…

Thanks.