Mxnet-tensorrt integration on the jetson tx2

nchafni · October 24, 2018, 6:56pm

Has anyone used the tensorrt integration on the jetson.

I’m getting build errors relating to not finding onnx. Onnx has been installed and I tried mapping it in a few different ways.

Is the integration affected by the jetson not supporting the tensorrt python api?

kellen · October 25, 2018, 12:55am

Hey @nchafni. It’s quite difficult to build TRT manually on the TX2 at the moment. What I would recommend is to follow the installation steps in the CI very closely. If you first build ONNX, then ONNX-TensorRT it should be the easiest way to verify that you have the correct dependencies.

github.com

apache/incubator-mxnet/blob/master/ci/docker/runtime_functions.sh#L492


build_ubuntu_gpu() {
build_ubuntu_gpu_cuda91_cudnn7
}


build_ubuntu_gpu_tensorrt() {


set -ex


build_ccache_wrappers


# Build ONNX
pushd .
echo "Installing ONNX."
cd 3rdparty/onnx-tensorrt/third_party/onnx
rm -rf build
mkdir -p build
cd build
cmake \
    -DCMAKE_CXX_FLAGS=-I/usr/include/python${PYVER}\
    -DBUILD_SHARED_LIBS=ON ..\
    -G Ninja

You would need to substitute CUDA_ARCH="-gencode arch=compute_62,code=compute_62" instead of CUDA_ARCH="-gencode arch=compute_70,code=compute_70"

Topic		Replies	Views
How can build mxnet-tensorrt integration on the jetson tx2? Discussion	6	1729	September 25, 2019
Build from source flag USE_TENSORRT on jetson nano failed? Discussion	3	517	May 12, 2020
MxNet support for Jetson Orin modules (Cuda 11.4) Discussion	1	350	January 10, 2023
Doubts for cross-compiling mxnet for jetson nano and TX2 Site Feedback	1	1176	August 7, 2019
How to build mxnet with tensorrt support? Discussion	4	2856	June 19, 2020

Mxnet-tensorrt integration on the jetson tx2

Related Topics