Mirror of tunmxy/InspireFace from ModelScope. All credit to the original authors. Not an official release from them. No license was declared at the source; all rights remain with the original authors.

InspireFace

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.

• Repository address:
  • Stable
  • Develop

Key Features

• Face Detection & Tracking - High-precision face detection and real-time tracking
• Face Recognition - Face feature extraction and comparison
• Landmark Detection - Accurate facial landmark localization
• Face Attributes - Age, gender, and emotion recognition
• Liveness Detection - Silent and cooperative liveness detection
• Mask Detection - Face mask detection capability
• Quality Assessment - Face quality evaluation
• Pose Estimation - Face pose angle estimation

Project Origin

InspireFace is derived from the InsightFace project, specifically from the C++ package implementation.

Original Repository: https://github.com/deepinsight/insightface/tree/master/cpp-package/inspireface

Supported Platforms and Architectures

No.	Platform	Architecture	Device	Supported	Passed Tests
1	Linux(CPU)	ARMv7	-
2		ARMv8	-
3		x86/x86_64	-
4	Linux(Rockchip)	ARMv7	RV1109/RV1126
5		ARMv7	RV1103/RV1106
6		ARMv8	RK3566/RK3568
7		ARMv8	RK3588		-
8	Linux(MNN_CUDA)	x86/x86_64	NVIDIA-GPU
9	Linux(CUDA)	x86/x86_64	NVIDIA-GPU
10	MacOS	Intel	CPU/Metal/ANE
11		Apple Silicon	-
12	iOS	ARM	CPU/Metal/ANE
13	Android	ARMv7	-
14		ARMv8	-
15		x86_64	-
16	Android(Rockchip)	ARMv8	RK3566/RK3568
17		ARMv8	RK3588

Features Support Matrix

Feature	CPU	RKNPU(RV1109/1126)	RKNPU(RV1103/1106)	RKNPU(RK3566/3568/3588)	ANE(MacOS/iOS)	GPU(TensorRT)
Face Detection
Landmark
Face Embeddings					-
Face Comparison		-	-	-	-	-
Face Recognition					-
Alignment		-	-	-	-	-
Tracking
Mask Detection		-			-	-
Silent Liveness		-			-	-
Face Quality
Pose Estimation
Face Attribute		-			-
Cooperative Liveness
Face Emotion					-
Embedding Management		-	-	-	-	-

Note: Some models and features that do not support NPU or GPU will automatically use CPU for computation.

Model Packages

For different scenarios, we provide several model packages, each containing multiple models and configurations:

Name	Supported Devices	Note	Last Update
Pikachu	CPU	Lightweight edge-side models	Jun 22, 2025
Megatron	CPU, GPU	Mobile and server models	Jun 15, 2025
Megatron_TRT	GPU	CUDA-based server models	Jun 15, 2025
Gundam-RV1109	RKNPU	Supports RK1109 and RK1126	Jun 15, 2025
Gundam-RV1106	RKNPU	Supports RV1103 and RV1106	Jul 6, 2025
Gundam-RK356X	RKNPU	Supports RK3566 and RK3568	Jun 15, 2025
Gundam-RK3588	RKNPU	Supports RK3588	Jun 15, 2025