Get Started

InspireFace is a cross-platform face recognition SDK developed in C/C++, supporting multiple operating systems and various backend types for inference, such as CPU, GPU, and NPU.

If you require further information on tracking development branches, CI/CD processes, or downloading pre-compiled libraries, please visit our development repository.

Please contact contact@insightface.ai for commercial support, including obtaining and integrating higher accuracy models, as well as custom development.

Supported

We have completed the adaptation and testing of the software across various operating systems and CPU architectures. This includes compatibility verification for platforms such as Linux, macOS, iOS, and Android, as well as testing for specific hardware support to ensure stable operation in diverse environments.

Platform	Architecture (CPU)	Device (Special)	Supported	Passed Tests	Release (Online)
Linux (CPU)	ARMv7	-
	ARMv8	-
	x86/x86_64	-
Linux (Rockchip)	ARMv7	RV1109/RV1126
	ARMv7	RV1103/RV1106
	ARMv8	RK3566/RK3568
	ARMv8	RK3588		-
Linux (MNN_CUDA)	x86/x86_64	NVIDIA-GPU			-
Linux (CUDA)	x86/x86_64	NVIDIA-GPU
MacOS	Intel	CPU/Metal/ANE
	Apple Silicon	-
iOS	ARM	CPU/Metal/ANE
Android	ARMv7	-
	ARMv8	-
Android (Rockchip)	ARMv8	RK3566/RK3568
	ARMv8	RK3588
HarmonyOS	ARMv8	-	-	-	-
Linux (Jetson series)	ARMv8	Jetson series	-	-	-

• Device: Some special device support, primarily focused on computing power devices.
• Supported: The solution has been fully developed and successfully verified on offline devices.
• Passed Tests: The feature has at least passed unit tests on offline devices.
• Release: The solution is already supported and has been successfully compiled and released through GitHub Actions.

How to Get SDK

If you are using C/C++ with InspireFace, you can download the corresponding library files from the Release Pages. If you are using Android or Python, you can try simpler installation methods.

# Prepare your inspireface-sdk directory in advance
set(INSPIREFACE_DIR your_dir/InspireFace)
include_directories(${INSPIREFACE_DIR}/include)
link_directories(${INSPIREFACE_DIR}/lib)

# Link to your project
target_link_libraries(YourProject InspireFace)

// build.gradle
allprojects {
    repositories {
       ...
       maven { url 'https://jitpack.io' }
    }
}

dependencies {
    implementation 'com.github.HyperInspire:inspireface-android-sdk:1.2.0'
}

pip install -U inspireface

How to Get Model

For different scenarios, we currently provide several Packs, each containing multiple models and configurations.

Compile

If you want to compile InspireFace, you can check the more detailed section.