TensorRT for jetson Nano
Dependencies:
PyTorch 1.2.0
Pycuda
https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pycuda
CUDA 10.0
Python3.6
albumentations==0.4.5
onnx==1.4.1
opencv-python==4.2.0.34
Download and install TensorRT https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-601/tensorrt-install-guide/index.html
Notes:
~/.bashrc
export LD_LIBRARY_PATH=/home/didpurwanto/Documents/important/TensorRT-6.0.1.5/lib:$LD_LIBRARY_PATH
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:TensorRT-6.0.1.5/lib
Thanks to:
https://learnopencv.com/how-to-convert-a-model-from-pytorch-to-tensorrt-and-speed-up-inference/