WIP Autonomous Driving Perception (with conjunction with Udacity Simulator)
- Download prebuilt binaries
NOTE: Currently due to limitation of developer environment, only Linux OS is supported. Although there is a plan in place to provide compatibility with macOS as well.
- Build project
- Release
bazel build //... - Debug
bazel build -c dbg //...
- Release
- Run Unit Tests
bazel test //... --test_output=all
Install all the required dependencies:
sudo apt-get install -y build-essential gcc g++ lcov make cmake
sudo apt-get install -y openjdk-11-jdk openjdk-11-jre
sudo apt-get install -y libtool clang-format clang-tidy clangd
sudo apt-get install -y git curl
sudo apt-get install -y wget
sudo apt-get install -y libuv1-dev libssl-dev
sudo apt-get install -y libgtkglext1 libgtkglext1-dev libgtk-3-dev libgtk2.0-dev
sudo apt-get install -y libavcodec-dev libavformat-dev libswscale-dev libavresample-dev libavutil-dev
sudo apt-get install -y libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev
To build libtensorflow_cc.so
~/$ git clone https://github.com/tensorflow/tensorflow.git
~/$ git checkout v2.3.0
~/$ cd tensorflow
~tensorflow/$ bazel build -c opt --config=monolithic //tensorflow:libtensorflow_cc.so //tensorflow:install_headers
~tensorflow/$ cd bazel-bin/tensorflow
~tensorflow/bazel-bin/tensorflow$ mkdir -p libtensorflow_cc-2.3.0-linux/include libtensorflow_cc-2.3.0-linux/lib
~tensorflow/bazel-bin/tensorflow$ cp -R include/* libtensorflow_cc-2.3.0-linux/include
~tensorflow/bazel-bin/tensorflow$ cp -P libtensorflow_cc.so libtensorflow_cc.so.2 libtensorflow_cc.so.2.3.0 libtensorflow_cc-2.3.0-linux/lib/
~tensorflow/bazel-bin/tensorflow$ tar cvzf libtensorflow_cc-2.3.0-linux.tar.gz libtensorflow_cc-2.3.0-linuxPackage libtensorflow_cc-2.3.0-linux.tar.gz contains required tensorflow libraries.
Download pre-built binaries (Linux/macOS): https://github.com/jinay1991/perception/releases/
To build libtensorflowlite.so
~/$ git clone https://github.com/tensorflow/tensorflow.git
~/$ git checkout v2.3.0
~/$ cd tensorflow
~tensorflow/$ bazel build -c opt --config=monolithic //tensorflow/lite:libtensorflowlite.so
~tensorflow/$ cd bazel-bin/tensorflow/lite
~tensorflow/bazel-bin/tensorflow$ mkdir -p libtensorflowlite-2.3.0-linux/include libtensorflowlite-2.3.0-linux/lib
~tensorflow/bazel-bin/tensorflow$ cp --parents -r ~tensorflow/lite/**/**/*.h libtensorflowlite-2.3.0-linux/include
~tensorflow/bazel-bin/tensorflow$ cp -P libtensorflowlite.so libtensorflowlite-2.3.0-linux/lib/
~tensorflow/bazel-bin/tensorflow$ tar cvzf libtensorflowlite-2.3.0-linux.tar.gz libtensorflowlite-2.3.0-linuxPackage libtensorflowlite-2.3.0-linux.tar.gz contains required tensorflowlite libraries.
Download pre-built binaries (Linux/macOS): https://github.com/jinay1991/perception/releases/
Install OpenCV v4.x
On macOS, run brew install opencv.
On Ubuntu or other linux systems, run following commands to build OpenCV from source and install.
export OPENCV_VERSION="4.2.0"
wget https://github.com/opencv/opencv/archive/${OPENCV_VERSION}.zip && \
unzip ${OPENCV_VERSION}.zip && rm -rf ${OPENCV_VERSION}.zip && \
mkdir -p opencv-${OPENCV_VERSION}/build
cd opencv-${OPENCV_VERSION}/build && \
cmake -DCMAKE_INSTALL_PREFIX=../install -DBUILD_TESTS=OFF -DBUILD_PERF_TESTS=OFF -DBUILD_opencv_apps=OFF -DBUILD_EXAMPLES=OFF -DCMAKE_BUILD_TYPE=Release -DWITH_1394=OFF -DWITH_GSTREAMER=ON -DWITH_FFMPEG=ON -DWITH_GTK=ON .. && \
make -j8 && make install && \
cd ../install && tar cvzf libopencv_dev-4.5.0-linux.tar.gz \
Download pre-built binaries (Linux): https://github.com/jinay1991/perception/releases/
Currently project works (tested) on following Operating Systems:
- macOS Catalina > v10.15
- Ubuntu 18.04
- Docker Engine v2.1.0 (stable)
Repository uses some of the third party library as follows, which are being downloaded and linked with Bazel Rules defined in WORKSPACE and bazel/ of this repository.