l4t-tensorRT image and cudnn

[masip85]

Ok, with your advice I could compile opencv. Now I need tensorRT(libinfer) dev, for compiling. tensorRT project.

But:

Problem creating my devel container in jetson AGX container

Hello I need for compiling tkdnn project: cuda 10.2 - dev cudnn 8.0.0 - dev tensorrt 7.2. -dev I need to do this inside a container, but… you didn’t upload previous devel for docker pull nvcr.io/nvidia/l4t-base: [imagen] My first approach in my 32.6 flashed agx jetson, was using containers which have self contained cuda packages(from docker pull nvcr.io/nvidia/l4t-cuda:10.2.460-runtime) Then,inside the container , add repositories ARCH=arm64 SOC=t194 https://developer.download.nvidia.…