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 1.1.19673

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) and you always require the latest SDK version, then 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	Notes	SHA256
C++ x86-64 CPU Linux, Ubuntu 18.04 and CentOS 8	Compiled with gcc 7.5.0, GLIBC 2.27, tested on Ubuntu 18.04 and CentOS 8.	`8948483adb...`
C++ x86-64 CPU Linux, Ubuntu 20.04	Compiled with gcc 9.3.0, GLIBC 2.31, tested on Ubuntu 20.04.	`43c615b702...`
C++ x86-64 GPU CUDA-11.2 Linux, Ubuntu 18.04 and CentOS 8	Must install GPU dependencies. Compiled with gcc 7.5.0, GLIBC 2.27, Cuda 11.2, tested on Ubuntu 18.04 and CentOS 8.	`35feca4317...`
C++ x86-64 GPU CUDA-11.2 Linux, Ubuntu 20.04	Must install GPU dependencies. Compiled with gcc 9.3.0, GLIBC 2.31, Cuda 11.2, tested on Ubuntu 20.04.	`16b3e5fc51...`
C++ x86-64 CPU macOS	Compiled with AppleClang 11.	`a60185d04d...`
C++ x86-64 CPU Windows	Must install Windows dependencies. Compiled with MSVC 19.28.29913.0 in Release mode.	`be44fc3b33...`

x86-64 Python bindings¶

Python bindings Documentation

Python bindings documentation can be found here

Target platform	Notes	SHA256
Python 3.6 64Bit CPU Linux	For CentOS, must run `dnf install -y libgomp`. Tested on Ubuntu 18.04, Ubuntu 20.04, and CentOS 8.	`3432907a6d...`
Python 3.7 64Bit CPU Linux	For CentOS, must run `dnf install -y libgomp`. Tested on Ubuntu 18.04, Ubuntu 20.04, and CentOS 8.	`1699e5293b...`
Python 3.7 64Bit CPU macOS		`332a08738a...`
Python 3.8 64Bit CPU Linux	For CentOS, must run `dnf install -y libgomp`. Tested on Ubuntu 18.04, Ubuntu 20.04, and CentOS 8.	`b1e418df92...`
Python 3.8 64Bit CPU macOS		`1f0e77557e...`
Python 3.8 64Bit GPU CUDA-11.2 Linux, Ubuntu 20.04	Must install GPU dependencies. Tested on Ubuntu 20.04.	`aac929cfe1...`
Python 3.8 64Bit GPU CUDA-11.2 Linux, Ubuntu 18.04	Must install GPU dependencies. Tested on Ubuntu 18.04.	`aac929cfe1...`

ARM C++¶

Target platform	Notes	SHA256
Aarch64 CPU Linux	Compiled with aarch64-linux-gnu-g++ 7.5.0, GLIBC 2.27, tested on Ubuntu 18.04.	`691d056437...`
Aarch64 GPU CUDA-10.2 Linux, Ubuntu 18.04	Must install GPU dependencies. Compiled with aarch64-linux-gnu-g++ 7.5.0, GLIBC 2.27, CUDA-10.2, tested on Ubuntu 18.04.	`4928f50691...`
Aarch32 CPU Linux	Compiled with arm-linux-gnueabihf-g++ 7.5.0, GLIBC 2.27, tested on Ubuntu 18.04.	`5d8ab1a063...`

ARM Python Bindings¶

Python bindings Documentation

Python bindings documentation can be found here

Target platform	Notes	SHA256
Python 3.6 64Bit CPU Linux Aarch64	Tested on Ubuntu 18.04.	`5211a59a35...`
Python 3.6 64Bit GPU CUDA-10.2 Linux Aarch64	Must install GPU dependencies. Tested on Ubuntu 18.04.	`4928f50691...`
Python 3.6 32Bit CPU Linux Aarch32	Tested on Ubuntu 18.04.	`7b892e4116...`
Python 3.7 64Bit CPU Linux Aarch64	Tested on Ubuntu 18.04.	`4b62c78281...`
Python 3.7 32Bit CPU Linux Aarch32	Tested on Ubuntu 18.04.	`1f7f79e6da...`

iOS¶

iOS SDK Documentation

iOS SDK documentation can be found here

Target platform
iOS

Android¶

Android SDK Documentation

Android SDK documentation can be found here

Target platform
Android

NodeJS¶

The NodeJS SDK can be downloaded from npm by running npm install @trueface/trueface-sdk-javascript or by visiting this link.

The NodeJS documentation can be found here.

GPU SDK Dependencies¶

While the CPU SDK is dependency free (only requires OpenMP for Linux and Windows), the GPU SDK does have a few dependencies which must be installed.

CUDA 11.2 - Ubuntu 18.04
Start by installing the NVIDIA drivers on your machine by following the instructions here.
Next, you will need to install CUDA 11.2 and CuDNN 8 by following the instructions here and here.
Alternatively, you can use the nvidia/cuda:11.2.0-cudnn8-runtime-ubuntu18.04 docker image.
Finally, run the following commands:

apt-get install -y libomp-dev libopenblas-dev libgomp1

Next, navigate to this link, create an account or login with your existing account, then click on TensorRT 8.2 GA Update 1. From there, go ahead an download TensorRT 8.2 GA Update 1 for Linux x86_64 and CUDA 11.0, 11.1, 11.2, 11.3, 11.4 and 11.5 TAR Package. Once downloaded, extract the package by running tar -xzf ./TensorRT-8.2.2.1.Linux.x86_64-gnu.cuda-11.4.cudnn8.2.tar.gz then add the full path to the TensorRT-8.2.2.1/lib directory to your LD_LIBRARY_PATH environment variable (ex. export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path/to/tensorrt/dir/lib. If you want this change to persist, you should add the command to your ~/.bashrc.).

CUDA 11.2 - Ubuntu 20.04
Start by installing the NVIDIA drivers on your machine by following the instructions here.
Next, you will need to install CUDA 11.2 and CuDNN 8 by following the instructions here and here.
Alternatively, you can use the nvidia/cuda:11.2.0-cudnn8-runtime-ubuntu20.04 docker image.
Finally, run the following commands:

apt-get install -y libomp-dev libopenblas-dev libgomp1
ln -s /usr/lib/x86_64-linux-gnu/libomp.so.5 /usr/lib/x86_64-linux-gnu/libomp.so

Next, navigate to this link, create an account or login with your existing account, then click on TensorRT 8.2 GA Update 1. From there, go ahead an download TensorRT 8.2 GA Update 1 for Linux x86_64 and CUDA 11.0, 11.1, 11.2, 11.3, 11.4 and 11.5 TAR Package. Once downloaded, extract the package by running tar -xzf ./TensorRT-8.2.2.1.Linux.x86_64-gnu.cuda-11.4.cudnn8.2.tar.gz then add the full path to the TensorRT-8.2.2.1/lib directory to your LD_LIBRARY_PATH environment variable (ex. export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path/to/tensorrt/dir/lib. If you want this change to persist, you should add the command to your ~/.bashrc.).

AArch64 CUDA 10.2 - Ubuntu 18.04

The NVIDIA Jetson OS comes with the required version of CUDA, cudnn, and TensorRT pre-installed. Therefore, only the following commands must be run:

apt-get install -y libopenblas-dev

If you see that your system has libnvinfer.so.7 installed instead of the required libnvinfer.so.8, then you’ll need to update the image running on your Jetson.

Windows SDK¶

For a full tutorial on how to install the Windows SDK, please consult this video.

Our team does the majority of development and testing in a Unix 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:

Any file including winerror.h must have #undef NO_ERROR as the NO_ERROR defined in winerror.h conflicts with Trueface::ErrorCodes::NO_ERROR.
TFV5 inference is slower than FULL model inference and is under investigation.
Trueface::SDK::identifyTopCandidate() and Trueface::SDK::identifyTopCandidates() will only use a single thread for search and will therefore be slower than searches run on Unix platforms. However, Trueface::SDK::batchIdentifyTopCandidate() is capable of using multiple threads.

Dependencies which must be installed. These dependencies will automatically be installed by installing Git for Windows:

libintl-8.dll
libcrypto-1_1-x64.dll
libsll-1_1-x64.dll

As of this time, we are only supporting a release configured version of the library (and not a debug version). The library is built as a dynamic library; therefore, you must link against libtf.lib when compiling your application and must ensure that libtf.dll is in the same directory as your executable.

We advise using “Git Bash” when compiling and and running your application to ensure the dependency libraries are properly found.

Getting Started Tutorials¶

Every SDK download package comes bundled with sample code (C++ and Python) demonstrating proper usage of the SDK for various tasks such as face detection, face recognition, object detection, mask detection, and more. Start by understanding how the sample code works by reading the comments in the code.

Sample Apps¶

Sample Apps demonstrate full working applications. These extend the scope of the sample code which comes shipped with the SDK.

Reporting SDK Bugs and Documentation Errors¶

If you encounter a bug in the SDK, please send an email to support@trueface.ai. Please include at minimum the following:

SDK version
SDK target (ex. Python 3.7 64Bit CPU Linux)
Expected behaviour
Observed behaviour
A minimal reproducible code example showing how to replicate the bug
Any input images used

The more information you provide, the faster we can diagnose the issue and push out a fix.

If you happen to find a mistake (spelling, syntax error, etc.) in the latest Alpha, Beta, or Stable documentation, please email support@trueface.ai with a screenshot of the mistake, documentation version number (same as SDK version), and the release type (Alpha, Beta, or Stable). We will push out a fix as soon as we can.

C++ (Stable) - Contents:

Index