Build tensorRT engine for ONNX model

[mili.yazdani77]

Hi , I did the following conversion on my model :
keras(.h5) -----> tensorflow(.pb) ----->ONNX(.onnx)
and now I want to build tensorRT engine for this ONNX model , I’m new in this case so I appreciate it if you give me a simple solution .
thanks

[AastaLLL]

Hi,

You can find a python example in the below topic:

Custom ResNet Jetson Xavier

Hi, The error comes from dynamic shape usage. If you don’t need to reshape the model at the runtime, please set EXPLICIT_BATCH to use static shape instead. Here is an example of onnx model for your reference: import cv2 import time import numpy as np import tensorrt as trt import pycuda.autoinit import pycuda.driver as cuda EXPLICIT_BATCH = 1 << (int)(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH) TRT_LOGGER = trt.Logger(trt.Logger.INFO) runtime = trt.Runtime(TRT_LOGGER) host_inputs = …

Or you can run the inference with our trtexec binary directly.

/usr/src/tensorrt/bin/trtexec --onnx=[your/.onnx]

Thanks.