Tensorflow to TensorRT Model Conversion for Retraining the Model


We use Jetson-inference’s pre-trained object detection model for our application. But we want to train weights with our site dataset. Would you provide a source for converting a Tensorflow model to TensorRT for Xavier Nx?

Thank you


Please convert your model into onnx format with tf2onnx or keras2onnx, and following this sample for TensorRT:


@myagmur did you get a performance boost on the nx when you converted your tf model to a tf_rt model?

you have to convert your model into TensorRT to run it on NX

I did, I am using the process described here: Accelerating Inference In TF-TRT User Guide :: NVIDIA Deep Learning Frameworks Documentation

I am not seeing any performance improvement.