.. TruefaceSDK documentation master file, created by sphinx-quickstart on Mon Sep 16 22:16:39 2019. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. Trueface SDK Reference - Stable ====================== Downloads ############################# Version ``SDK_VERSION`` *Alpha* contains the absolute latest features, but may also contain bugs. *Beta* contains fewer bugs while still having relatively new features. *Stable* will contain the fewest bugs but will take the longest to get new features. You will generally want to choose the Beta or Stable releases. - `Alpha `_ - `Beta `_ - `Stable `_ Note, if downloading the SDK in an automated manner (ex. building docker images) then you will want to replace the postfix in the download link (SDK version) with ``_latest.zip`` instead. So for example, ``https://reference.trueface.ai/cpp/staging/latest/uploads/truefaceSDK_v0.10.5483.zip`` would become ``https://reference.trueface.ai/cpp/staging/latest/uploads/truefaceSDK_latest.zip``. x86-64 C++ ********** .. list-table:: :header-rows: 1 * - Target platform - SHA256 * - `C++ x86-64 CPU Linux `_ - ``SHA256_x86_cpu_linux_cpp...`` * - `C++ x86-64 GPU CUDA-10.1 Linux (Ubuntu) `_ - ``SHA256_x86_gpu_linux_cpp...`` * - `C++ x86-64 CPU macOS `_ - ``SHA256_x86_cpu_macos_cpp...`` x86-64 Python bindings ********************** | **Python bindings Documentation** | Python bindings documentation can be found `here `_ .. list-table:: :header-rows: 1 * - Target platform - SHA256 * - `Python 3.6 64Bit CPU Linux `_ - ``SHA256_x86_cpu_linux_python3_6...`` * - `Python 3.6 64Bit GPU CUDA-10.1 Linux (Ubuntu) `_ - ``SHA256_x86_gpu_linux_python3_6...`` * - `Python 3.7 64Bit CPU Linux `_ - ``SHA256_x86_cpu_linux_python3_7...`` * - `Python 3.7 64Bit CPU macOS `_ - ``SHA256_x86_cpu_macos_python3_7...`` * - `Python 3.7 64Bit GPU CUDA-10.1 Linux (Ubuntu) `_ - ``SHA256_x86_gpu_linux_python3_7...`` * - `Python 3.8 64Bit CPU Linux `_ - ``SHA256_x86_cpu_linux_python3_8...`` * - `Python 3.8 64Bit CPU macOS `_ - ``SHA256_x86_cpu_macos_python3_8...`` * - `Python 3.8 64Bit GPU CUDA-10.1 Linux (Ubuntu) `_ - ``SHA256_x86_gpu_linux_python3_8...`` ARM C++ ******* .. list-table:: :header-rows: 1 * - Target platform - SHA256 * - `Aarch64 CPU Linux `_ - ``SHA256_aarch64_cpu_linux...`` * - `Arm32 CPU Linux `_ - ``SHA256_arm32_cpu_linux...`` For embedded devices with limited disk space, use the following libraries which have the full model disabled to reduce binary size. .. list-table:: :header-rows: 1 * - Target platform - SHA256 * - `Aarch64 CPU lite Linux `_ - ``SHA256_aarch64_cpu_lite_linux...`` * - `Arm32 CPU lite Linux `_ - ``SHA256_arm32_cpu_lite_linux...`` ARM Python Bindings ******************* | **Python bindings Documentation** | Python bindings documentation can be found `here `_ .. list-table:: :header-rows: 1 * - Target platform - SHA256 * - `Python 3.6 64Bit CPU Linux Aarch64 `_ - ``SHA256_python36_aarch64...`` * - `Python 3.6 32Bit CPU Linux Arm32 `_ - ``SHA256_python36_arm32...`` * - `Python 3.7 64Bit CPU Linux Aarch64 `_ - ``SHA256_python37_aarch64...`` * - `Python 3.7 32Bit CPU Linux Arm32 `__ - ``SHA256_python37_arm32...`` Mobile ****** .. list-table:: :header-rows: 1 * - Target platform - SHA256 * - `Android `_ - N/A GPU SDK Dependencies ==================== While the CPU SDK is completely dependency free, the GPU SDK does have a few dependencies which must be installed. First, you must have CUDA 10.1 (runtime) installed on your Ubuntu device. Alternatively, you can use `this `_ docker image. The other required dependencies are: - ``libomp.so`` - ``libopenblas.so.0`` - ``libcudnn.so.7`` These can be installed by running the following commands: .. code-block:: bash apt-get install -y libomp-dev libopenblas-dev software-properties-common wget OS=ubuntu1804 wget https://developer.download.nvidia.com/compute/cuda/repos/${OS}/x86_64/cuda-${OS}.pin mv cuda-${OS}.pin /etc/apt/preferences.d/cuda-repository-pin-600 apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/${OS}/x86_64/7fa2af80.pub add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/${OS}/x86_64/ /" apt-get update apt-get install -y libcudnn7 Sample Apps =========== `Sample Apps `_ which demonstrate full working applications. Getting Started =============== Start by downloading the correct version of the SDK. Next, the SDK must be initialized. Refer to the general section for the various configuration options. .. toctree:: :maxdepth: 2 :caption: C++ (Stable) - Contents: usage/general usage/license usage/image usage/face usage/identification usage/object usage/spoof usage/pose usage/liveness usage/mask usage/eyeglasses usage/environment usage/faq usage/changelog * :ref:`genindex`