I am trying to build an image using the build-push action for Nvidia Jetson architecture (linux/arm/v8).
• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
I wanted to take advantage of cross compilation docker features but it is not working as expected.
This simple Dockerfile works when I build it on Nvidia Jetson but it does not when I try to build from another system:
# syntax=docker/dockerfile:experimental FROM nvcr.io/nvidia/deepstream-l4t:5.0.1-20.09-samples as build WORKDIR / RUN --mount=type=cache,id=apt-build,target=/var/cache/apt \ apt update && apt install -y \ git \ wget \ cmake \ g++ && \ rm -rf /var/lib/apt/lists/* RUN git clone --depth=1 --single-branch --branch patch-1 https://github.com/mmeendez8/amirstan_plugin.git && \ cd /amirstan_plugin && \ git submodule update --init --progress --depth=1 && \ mkdir build && \ cd build && \ cmake .. -DWITH_DEEPSTREAM=true && \ make -j10
Jetson build command:
docker buildx build --f Dockerfile -t deepstream:jetson .
x86 build command:
docker buildx build --platform linux/arm64 -f Dockerfile -t deepstream:jetson .
Error output on x86 shows that:
#11 38.05 -- Found TensorRT headers at TENSORRT_INCLUDE_DIR-NOTFOUND #11 38.06 -- Find TensorRT libs at TENSORRT_LIBRARY_INFER-NOTFOUND;TENSORRT_LIBRARY_PARSERS-NOTFOUND;TENSORRT_LIBRARY_INFER_PLUGIN-NOTFOUND #11 38.07 -- Could NOT find TENSORRT (missing: TENSORRT_INCLUDE_DIR TENSORRT_LIBRARY) #11 38.07 ERRORCannot find TensorRT library.
I guess the deepstream jetson base container is build upon the l4t base container (NVIDIA NGC). In its documentation I can read the following:
The platform specific libraries and select device nodes for a particular device are mounted by the NVIDIA container runtime into the l4t-base container from the underlying host, thereby providing necessary dependencies for l4t applications to execute within the container. This approach enables the l4t-base container to be shared between various Jetson devices.
So I guess there is no way to make this cross compilation work with jetson containers since most of dependencies are on the Jetson host system. Is this correct?