Trueface SDK Reference - Stable¶

Welcome to the Trueface SDK. The SDK allows you to integrate Trueface’s AI models directly into your application while ensuring maximum performance and flexibility. Start by downloading the correct version of the SDK for your target platform and desired language. Next, refer to the General section for guidance on how to initialize the SDK.

Downloads¶

Stable release version 0.14.6699

Choosing Your Release Type¶

Alpha contains the absolute latest features (updated daily), 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.

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.

If you require a previous version of the documentation or SDK downloads, refer to the Previous Stable Releases tab on the left.

x86-64 C++¶

Target platform	SHA256
C++ x86-64 CPU Linux	`a1894be0eb...`
C++ x86-64 GPU CUDA-10.1 Linux (Ubuntu)	`ad940bfa8e...`
C++ x86-64 CPU macOS	`e818d4e618...`
C++ x86-64 CPU Windows (Release, MT)	`d1985321c4...`

x86-64 Python bindings¶

Python bindings Documentation

Python bindings documentation can be found here

Target platform	SHA256
Python 3.6 64Bit CPU Linux	`615670adca...`
Python 3.6 64Bit GPU CUDA-10.1 Linux (Ubuntu)	`0790d9b3d0...`
Python 3.7 64Bit CPU Linux	`6b8b09426f...`
Python 3.7 64Bit CPU macOS	`d4cc22a231...`
Python 3.7 64Bit GPU CUDA-10.1 Linux (Ubuntu)	`99d6c1acd3...`
Python 3.8 64Bit CPU Linux	`0ed4afc115...`
Python 3.8 64Bit CPU macOS	`731af239d9...`
Python 3.8 64Bit GPU CUDA-10.1 Linux (Ubuntu)	`098fb513b3...`

ARM C++¶

Target platform	SHA256
Aarch64 CPU Linux	`6153c1db9a...`
Arm32 CPU Linux	`5e016738a2...`

For embedded devices with limited disk space, use the following libraries which have the full model disabled to reduce binary size.

Target platform	SHA256
Aarch64 CPU lite Linux	`78563099bc...`
Arm32 CPU lite Linux	`097eeea033...`

ARM Python Bindings¶

Python bindings Documentation

Python bindings documentation can be found here

Target platform	SHA256
Python 3.6 64Bit CPU Linux Aarch64	`6919c46858...`
Python 3.6 32Bit CPU Linux Arm32	`05082c4c7d...`
Python 3.7 64Bit CPU Linux Aarch64	`798fa579f7...`
Python 3.7 32Bit CPU Linux Arm32	`aa0f42d3da...`

Mobile¶

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:

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

Windows SDK¶

Our team does the majority of development and testing in a Linux environment. The Windows SDK may therefore contain more bugs than the other platform releases and may be lacking in a few features. The current known issues and limitations are as follows:

PostgreSQL database management system is currently not supported.
Any file including winerror.h must have #undef NO_ERROR as the NO_ERROR defined in winerror.h conflicts with Trueface::ErrorCodes::NO_ERROR.

As of this time, we are only supporting a release configured version of the library (and not a debug version). Additionally, the library has been built with /MT so be sure to set the flag appropriately.

Sample Apps¶

Sample Apps which demonstrate full working applications.

C++ (Stable) - Contents:

Index