Tensorflow Object Detection API on Jetson Xavier NX

Hi,
I am new here, recently i trained a model custom model based on mobilenet v2 fpnlite using the tensorflow object detection api. Currently i am able to run the model on my laptop, and I hope to enquire how do I proceed to deploy this model on my jetson xavier.

Thanks in advanced!

Moving to Jetson Xavier NX forum for resolution.

Hi,

You can deploy it with TensorFlow directly on the Xavier.
The installation procedure can be found in the below document:
https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html

However, it’s more recommended to convert the model into TensorRT engine.
It can give you a better performance on Jetson as well as save the memory usage.

This is a two-step conversion:

  1. Convert your model into ONNX format via tf2onnx.

  2. Follow below tutorial to deploy the model with TensorRT.
    TensorRT/samples/opensource/sampleOnnxMNIST at master · NVIDIA/TensorRT · GitHub

Thanks.

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.