# syntax=docker/dockerfile:1.6

# https://askubuntu.com/questions/972516/debian-frontend-environment-variable
ARG DEBIAN_FRONTEND=noninteractive
ARG BASE_IMAGE
ARG TRT_BASE=nvcr.io/nvidia/tensorrt:23.12-py3
ARG BUILD_ONNXRUNTIME_FROM_SOURCE=0
ARG ONNXRUNTIME_VERSION=1.25.1
ARG ONNXRUNTIME_BRANCH=rel-1.25.1
ARG TENSORRT_PYTHON_BRANCH=release/8.6
ARG L4T_APT_RELEASE=
ARG JETSON_SOC_REPO=

# Build TensorRT-specific library
FROM ${TRT_BASE} AS trt-deps

ARG TARGETARCH
ARG COMPUTE_LEVEL

RUN apt-get update \
    && TRT_DEV_PACKAGES="git build-essential cuda-nvcc-* cuda-nvtx-* libnvinfer-dev libnvinfer-plugin-dev libnvonnxparsers-dev" \
    && if apt-cache show libnvparsers-dev > /dev/null 2>&1; then TRT_DEV_PACKAGES="${TRT_DEV_PACKAGES} libnvparsers-dev"; fi \
    && apt-get install -y ${TRT_DEV_PACKAGES} \
    && rm -rf /var/lib/apt/lists/*
RUN --mount=type=bind,source=docker/tensorrt/detector/tensorrt_libyolo.sh,target=/tensorrt_libyolo.sh \
    /tensorrt_libyolo.sh

# COPY required individual CUDA deps
RUN mkdir -p /usr/local/cuda-deps
RUN if [ "$TARGETARCH" = "amd64" ]; then \
    cp /usr/local/cuda-12.3/targets/x86_64-linux/lib/libcurand.so.* /usr/local/cuda-deps/ && \
    cp /usr/local/cuda-12.3/targets/x86_64-linux/lib/libnvrtc.so.* /usr/local/cuda-deps/ && \
    cd /usr/local/cuda-deps/ && \
    for lib in libnvrtc.so.*; do \
    if [[ "$lib" =~ libnvrtc.so\.([0-9]+\.[0-9]+\.[0-9]+) ]]; then \
    version="${BASH_REMATCH[1]}"; \
    ln -sf "libnvrtc.so.$version" libnvrtc.so; \
    fi; \
    done && \
    for lib in libcurand.so.*; do \
    if [[ "$lib" =~ libcurand.so\.([0-9]+\.[0-9]+\.[0-9]+\.[0-9]+) ]]; then \
    version="${BASH_REMATCH[1]}"; \
    ln -sf "libcurand.so.$version" libcurand.so; \
    fi; \
    done; \
    fi

# Frigate w/ TensorRT Support as separate image
FROM deps AS tensorrt-base

#Disable S6 Global timeout
ENV S6_CMD_WAIT_FOR_SERVICES_MAXTIME=0

# COPY TensorRT Model Generation Deps
COPY --from=trt-deps /usr/local/lib/libyolo_layer.so /usr/local/lib/libyolo_layer.so
COPY --from=trt-deps /usr/local/src/tensorrt_demos /usr/local/src/tensorrt_demos

# COPY Individual CUDA deps folder
COPY --from=trt-deps /usr/local/cuda-deps /usr/local/cuda

COPY docker/tensorrt/detector/rootfs/ /
ENV YOLO_MODELS=""

HEALTHCHECK --start-period=600s --start-interval=5s --interval=15s --timeout=5s --retries=3 \
    CMD curl --fail --silent --show-error http://127.0.0.1:5000/api/version || exit 1

FROM ${BASE_IMAGE} AS build-wheels
ARG DEBIAN_FRONTEND
ARG BUILD_ONNXRUNTIME_FROM_SOURCE
ARG ONNXRUNTIME_VERSION
ARG ONNXRUNTIME_BRANCH
ARG TENSORRT_PYTHON_BRANCH
ARG L4T_APT_RELEASE
ARG JETSON_SOC_REPO

# Add deadsnakes PPA for python3.11
RUN apt-get -qq update && \
    apt-get -qq install -y --no-install-recommends \
    software-properties-common \
    && add-apt-repository ppa:deadsnakes/ppa

# Use a separate container to build wheels to prevent build dependencies in final image
RUN apt-get -qq update \
    && apt-get -qq install -y --no-install-recommends \
    python3.11 python3.11-dev \
    wget curl build-essential cmake git ninja-build \
    && rm -rf /var/lib/apt/lists/*

# Ensure python3 defaults to python3.11
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# --ignore-installed: on the JP7 Ubuntu 24.04 (noble) base the deadsnakes python3.11 ships a
# distro-packaged pip 24.0 with no RECORD file, so get-pip.py's default reinstall fails with
# "uninstall-no-record-file". Installing over it without uninstalling avoids that; harmless on JP6.
RUN wget -q https://bootstrap.pypa.io/get-pip.py -O get-pip.py \
    && sed -i 's/args.append("setuptools")/args.append("setuptools==77.0.3")/' get-pip.py \
    && python3 get-pip.py --ignore-installed "pip"

FROM build-wheels AS trt-wheels
ARG DEBIAN_FRONTEND
ARG TARGETARCH
ARG BUILD_ONNXRUNTIME_FROM_SOURCE
ARG ONNXRUNTIME_VERSION
ARG ONNXRUNTIME_BRANCH
ARG TENSORRT_PYTHON_BRANCH

# python-tensorrt build deps are 3.4 GB!
RUN apt-get update \
    && TRT_DEV_PACKAGES="ccache cuda-cudart-dev-* cuda-nvcc-* libnvonnxparsers-dev libnvinfer-plugin-dev" \
    && if apt-cache show libnvparsers-dev > /dev/null 2>&1; then TRT_DEV_PACKAGES="${TRT_DEV_PACKAGES} libnvparsers-dev"; fi \
    && apt-get install -y ${TRT_DEV_PACKAGES} \
    && ([ -e /usr/local/cuda ] || ln -s /usr/local/cuda-* /usr/local/cuda) \
    && rm -rf /var/lib/apt/lists/*;

# The JP7 base image ships a stale cmake 3.24 at /usr/local/bin/cmake that shadows apt's 3.28.
# TensorRT 10.11's python CMakeLists (and the ONNX Runtime source build) require cmake >= 3.27,
# so install a current cmake from pip into /usr/local/bin ahead of the stale one. No-op risk on
# JP6 where the bundled cmake already satisfies the minimum.
RUN pip3 install --no-cache-dir --upgrade "cmake>=3.27"

# Determine version of tensorrt already installed in base image, e.g. "Version: 8.4.1-1+cuda11.4"
RUN NVINFER_VER="$(dpkg-query -W -f='${Version}\n' 'libnvinfer*' 2>/dev/null | grep -E '^[0-9]+[.][0-9]+[.][0-9]+' | sort -V | tail -n1)" \
    && test -n "$NVINFER_VER" \
    && TENSORRT_VER="$(echo "$NVINFER_VER" | grep -Eo '^[0-9]+[.][0-9]+[.][0-9]+')" \
    && TENSORRT_MAJOR="$(echo "$TENSORRT_VER" | cut -d. -f1)" \
    && echo "$TENSORRT_VER" > /etc/TENSORRT_VER \
    && echo "$TENSORRT_MAJOR" > /etc/TENSORRT_MAJOR

RUN --mount=type=bind,source=docker/tensorrt/detector/build_python_tensorrt.sh,target=/deps/build_python_tensorrt.sh \
    --mount=type=cache,target=/root/.ccache \
    export PATH="/usr/lib/ccache:$PATH" CCACHE_DIR=/root/.ccache CCACHE_MAXSIZE=2G \
    && TENSORRT_VER=$(cat /etc/TENSORRT_VER) TENSORRT_PYTHON_BRANCH="${TENSORRT_PYTHON_BRANCH}" /deps/build_python_tensorrt.sh

COPY docker/tensorrt/requirements-arm64.txt /requirements-tensorrt.txt

RUN pip3 wheel --wheel-dir=/trt-wheels -r /requirements-tensorrt.txt

# See https://elinux.org/Jetson_Zoo#ONNX_Runtime
RUN --mount=type=bind,source=docker/tensorrt/detector/build_onnxruntime_arm64.sh,target=/deps/build_onnxruntime_arm64.sh \
    mkdir -p /trt-wheels \
    && if [ "${BUILD_ONNXRUNTIME_FROM_SOURCE}" = "1" ]; then \
        ONNXRUNTIME_VERSION="${ONNXRUNTIME_VERSION}" ONNXRUNTIME_BRANCH="${ONNXRUNTIME_BRANCH}" /deps/build_onnxruntime_arm64.sh; \
    else \
        wget -q https://nvidia.box.com/shared/static/9yvw05k6u343qfnkhdv2x6xhygze0aq1.whl -O /trt-wheels/onnxruntime_gpu-1.19.0-cp311-cp311-linux_aarch64.whl; \
    fi

FROM build-wheels AS trt-model-wheels
ARG DEBIAN_FRONTEND

RUN apt-get update \
    && apt-get install -y protobuf-compiler libprotobuf-dev \
    && rm -rf /var/lib/apt/lists/*
RUN --mount=type=bind,source=docker/tensorrt/requirements-models-arm64.txt,target=/requirements-tensorrt-models.txt \
    pip3 wheel --wheel-dir=/trt-model-wheels --no-deps -r /requirements-tensorrt-models.txt

FROM wget AS jetson-ffmpeg
ARG DEBIAN_FRONTEND
ARG L4T_APT_RELEASE
ARG JETSON_SOC_REPO
ENV CCACHE_DIR /root/.ccache
ENV CCACHE_MAXSIZE 2G
RUN --mount=type=bind,source=docker/tensorrt/build_jetson_ffmpeg.sh,target=/deps/build_jetson_ffmpeg.sh \
    --mount=type=cache,target=/root/.ccache \
    L4T_APT_RELEASE="${L4T_APT_RELEASE}" JETSON_SOC_REPO="${JETSON_SOC_REPO}" /deps/build_jetson_ffmpeg.sh

# Frigate w/ TensorRT for NVIDIA Jetson platforms
FROM tensorrt-base AS frigate-tensorrt
RUN apt-get update \
    && pick_package() { for package in "$@"; do if apt-cache show "$package" > /dev/null 2>&1; then echo "$package"; return 0; fi; done; return 1; } \
    && PROTOBUF_RUNTIME="$(pick_package libprotobuf23 libprotobuf32t64 libprotobuf32)" \
    && apt-get install -y python-is-python3 "${PROTOBUF_RUNTIME}" \
    && rm -rf /var/lib/apt/lists/*

COPY --from=jetson-ffmpeg /rootfs /
ENV DEFAULT_FFMPEG_VERSION="jetson"
ENV INCLUDED_FFMPEG_VERSIONS="${DEFAULT_FFMPEG_VERSION}:${INCLUDED_FFMPEG_VERSIONS}"

# ffmpeg runtime dependencies
RUN apt-get -qq update \
    && pick_package() { for package in "$@"; do if apt-cache show "$package" > /dev/null 2>&1; then echo "$package"; return 0; fi; done; return 1; } \
    && X264_RUNTIME="$(pick_package libx264-163 libx264-164)" \
    && X265_RUNTIME="$(pick_package libx265-199 libx265-209)" \
    && apt-get -qq install -y --no-install-recommends \
    "${X264_RUNTIME}" "${X265_RUNTIME}" libegl1 \
    && rm -rf /var/lib/apt/lists/*

# Fixes "Error loading shared libs"
RUN mkdir -p /etc/ld.so.conf.d && echo /usr/lib/ffmpeg/jetson/lib/ > /etc/ld.so.conf.d/ffmpeg.conf

COPY --from=trt-wheels /etc/TENSORRT_VER /etc/TENSORRT_VER
COPY --from=trt-wheels /etc/TENSORRT_MAJOR /etc/TENSORRT_MAJOR
RUN --mount=type=bind,from=trt-wheels,source=/trt-wheels,target=/deps/trt-wheels \
    --mount=type=bind,from=trt-model-wheels,source=/trt-model-wheels,target=/deps/trt-model-wheels \
    pip3 uninstall -y onnxruntime \
    # --ignore-installed: on the noble JP7 base, `-U` would try to upgrade distro-managed deps that
    # lack a RECORD file (e.g. wheel/setuptools), failing with "uninstall-no-record-file". Install
    # the TRT/ORT GPU wheels over them into /usr/local instead. Harmless on JP6.
    && pip3 install -U --ignore-installed /deps/trt-wheels/*.whl \
    && pip3 install -U --ignore-installed /deps/trt-model-wheels/*.whl \
    && ldconfig

WORKDIR /opt/frigate/
COPY --from=rootfs / /

# Fixes "Error importing detector runtime: /usr/lib/aarch64-linux-gnu/libstdc++.so.6: cannot allocate memory in static TLS block"
ENV LD_PRELOAD /usr/lib/aarch64-linux-gnu/libstdc++.so.6