TRTEXEC with LPRNet

The trtexec tool is a command-line wrapper included as part of the TensorRT samples. Refer to the official TensorRT documentation for instructions on installing or building trtexec on your target platform (including x86 with discrete GPU and Jetson devices).

This section describes how to generate a TensorRT engine using trtexec, which allows you to deploy TAO-trained models on TensorRT, Triton, and Deepstream.

Sample Command for a LPRNet Model

To generate an .onnx file for LPRNet, refer to the LPRNet documentation. LPRNet currently does not support INT8 calibration.

trtexec --onnx=/path/to/model.onnx \
        --maxShapes=image_input:1x3x48x96 \
        --minShapes=image_input:4x3x48x96 \
        --optShapes=image_input:16x3x48x96 \
        --calib=/path/to/int8/calib.txt \
        --fp16 \
        --saveEngine=/path/to/save/trt/model.engine