- tx2和tegra nano的库升级，前提条件，升级前后系统版本一致。目前版本是18.04
- 在TX2或者nano上，删除掉cuda和cudnn相关库，以免冲突；
sudo apt-get autoremove cuda-toolkit-10-0 libcudnn7-dev libopencv-dev libnvinfer-dev libvisio*
- 将使用SDK manager下载好的TX2的安装库进行安装,cd 到这些库目录所在的位置。
sudo dpkg -i cuda-repo-l4t-10-0-local-10.0.166_1.0-1_arm64.deb
cuda-repo-l4t-10-0-local-10.0.326_1.0-1_arm64.deb
graphsurgeon-tf_5.1.6-1+cuda10.0_arm64.deb
libcudnn7_7.5.0.56-1+cuda10.0_arm64.deb
libcudnn7-dev_7.5.0.56-1+cuda10.0_arm64.deb
libcudnn7-doc_7.5.0.56-1+cuda10.0_arm64.deb
libnvidia-container-tools_0.9.0~beta.1_arm64.deb
libnvidia-container0_0.9.0~beta.1_arm64.deb
libnvinfer-dev_5.1.6-1+cuda10.0_arm64.deb
libnvinfer-samples_5.1.6-1+cuda10.0_all.deb
libnvinfer5_5.1.6-1+cuda10.0_arm64.deb
libopencv_3.3.1-2-g31ccdfe11_arm64.deb
libopencv-dev_3.3.1-2-g31ccdfe11_arm64.deb
libopencv-python_3.3.1-2-g31ccdfe11_arm64.deb
libopencv-samples_3.3.1-2-g31ccdfe11_arm64.deb
libvisionworks-repo_1.6.0.500n_arm64.deb
libvisionworks-sfm-repo_0.90.4_arm64.deb
libvisionworks-tracking-repo_0.88.2_arm64.deb
nvidia-container-runtime_0.9.0_beta.1+docker18.09.2-1_arm64.deb
nvidia-container-runtime-hook_0.9.0_beta.1-1_arm64.deb
nvidia-docker2_0.9.0_beta.1+docker18.09.2-1_arm64.deb
python-libnvinfer_5.1.6-1+cuda10.0_arm64.deb
python-libnvinfer-dev_5.1.6-1+cuda10.0_arm64.deb
python3-libnvinfer_5.1.6-1+cuda10.0_arm64.deb
python3-libnvinfer-dev_5.1.6-1+cuda10.0_arm64.deb
tensorrt_5.1.6.1-1+cuda10.0_arm64.deb
uff-converter-tf_5.1.6-1+cuda10.0_arm64.deb
