InspireFace v1.2.3

The current version is a stable one. Some bugs have been fixed and the function of multi-channel model download has been added to the Python-SDK.

Change Log

1. Add an interface for configuring image processing parameters.
2. Optimize jni code to make android thread-safe.
3. Add a new model download source for Python-sdk.
4. Fix some bugs on the interfaces

Supported Platforms and Architectures

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.

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 EmotionNew					-
Embedding Management		-	-	-	-	-

• Some models and features that do not support NPU or GPU will automatically use CPU for computation when running the program.

Model Package

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

InspireFace v1.2.2

The current version adds new facial emotion recognition algorithm functionality, includes additional Python APIs, and fixes some legacy bugs.

Change Log

1. Add a facial emotion recognition algorithm.
2. Add some new python api interfaces.
3. Fix some compilation issues

Supported Platforms and Architectures

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.

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 EmotionNew					-
Embedding Management		-	-	-	-	-

• Some models and features that do not support NPU or GPU will automatically use CPU for computation when running the program.

Model Package

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

InspireFace v1.2.1

The current version has fixed some bugs and optimized the facial key points and tracking algorithms. Apis have been added to C++, and they can be obtained in the header file.

Change Log

1. Optimize a more stable facial landmark tracking algorithm.
2. Fix some bugs that occur when calling the API.
3. Continuously enrich the product description documentation.
4. Add the api header file of C++.
5. Add the interface of the facial landmark model for switching models.

Supported Platforms and Architectures

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.

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
Embedding Management		-	-	-	-	-

• 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.

Model Package

Name	Supported Devices	Note	Last Update	Link
Pikachu	CPU	Lightweight edge-side models	Feb 20, 2025	Download
Megatron	CPU, GPU	Mobile and server models	Feb 20, 2025	Download
Megatron_TRT	GPU	CUDA-based server models	Mar 16, 2025	Download
Gundam-RV1109	RKNPU	Supports RK1109 and RK1126	Feb 20, 2025	Download
Gundam-RV1106	RKNPU	Supports RV1103 and RV1106	Feb 20, 2025	Download
Gundam-RK356X	RKNPU	Supports RK3566 and RK3568	Feb 20, 2025	Download
Gundam-RK3588	RKNPU	Supports RK3588	Mar 16, 2025	Download

InspireFace v1.2.0

The current version has gradually improved support for Rockchip devices. We have implemented RGA hardware-accelerated image processing on devices that support RKNPU2, significantly increasing processing speed. At the same time, we support running on Android platforms (RK356X/RK3588) while also integrating with the jitpack platform. We have improved support for CUDA-accelerated inference on NVIDIA devices. You can download the latest models through the table at the following link.

Change Log

1. Added support for CUDA-accelerated inference on NVIDIA devices.
2. Added support for and released the NPU version for RK356X and RK3588.
3. Adaptation for Android platform compatibility with RK3568 and RK3588.
4. Release Android SDK into the jitpack platform.
5. Fixed some bugs that may occur across platforms.
6. Updated Benchmark test table.

Supported Platforms and Architectures

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.

No.	Platform	Architecture (CPU)	Device (Special)	Supported	Passed Tests	Release (Online)
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	Android (Rockchip)	ARMv8	RK3566/RK3568
16		ARMv8	RK3588
17	HarmonyOS	ARMv8	-	-	-	-
18	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.

Model Package

Name	Supported Devices	Note	Last Update	Link
Pikachu	CPU	Lightweight edge-side models	Feb 20, 2025	Download
Megatron	CPU, GPU	Mobile and server models	Feb 20, 2025	[Download](https://github.com/HyperInspire/InspireFace...

InspireFace v1.1.13

In the current version, we support Rockchip RV1106 and RK356x devices (RV1103 support is possible but unverified). We have implemented RGA hardware acceleration for image processing on devices with RKNPU2 support, significantly improving processing speed. Additionally, we provide an optimized Android SDK with JNI integration and a simple demo. Corresponding resource files are available for these platforms.

• Supports the python library automatic upgrade model.
• Fixed some bugs.
• Update t3 series model: Formalizes the structure of the description file.
• Updated with the latest face landmark model.

InspireFace v1.1.12

In the current version, we support Rockchip RV1106 and RK356x devices (RV1103 support is possible but unverified). We have implemented RGA hardware acceleration for image processing on devices with RKNPU2 support, significantly improving processing speed. Additionally, we provide an optimized Android SDK with JNI integration and a simple demo. Corresponding resource files are available for these platforms.

• Open the parameter interface of some trackers.
• Add a similarity conversion tool.
• Update t3 series model: Formalizes the structure of the description file.

InspireFace v1.1.11

In the current version, we support Rockchip RV1106 and RK356x devices (RV1103 support is possible but unverified). We have implemented RGA hardware acceleration for image processing on devices with RKNPU2 support, significantly improving processing speed. Additionally, we provide an optimized Android SDK with JNI integration and a simple demo. Corresponding resource files are available for these platforms.

• Fixed some bugs running on RV1106/1103 and RK356x devices.
• Fixed a bug where the database persistence save path was invalid.

InspireFace v1.1.10

In the current version, we support Rockchip RV1106 and RK356x devices (RV1103 support is possible but unverified). We have implemented RGA hardware acceleration for image processing on devices with RKNPU2 support, significantly improving processing speed. Additionally, we provide an optimized Android SDK with JNI integration and a simple demo. Corresponding resource files are available for these platforms.

• Add support for NPU acceleration inference on RK356X platforms
• Make keypoint detection optional by default, auto-enabling only in tracking mode
• Fix face bounding box displacement issue in detection mode

InspireFace v1.1.9

In the current version, we have adapted and tested for Rockchip's RV1106 device and provided corresponding resource files (it may support RV1103, but we haven't verified it with actual devices). We believe we will soon adapt to other Rockchip device models, such as RV356x and RV3588. Meanwhile, we are implementing RGA image hardware acceleration processing adaptation for devices supporting RKNPU2, which has improved the image processing speed on RK devices. We have improved the Android SDK based on Java Native Interface (JNI), optimized its size, and provided a simple demo.

• Add NPU inference support for Rockchip rv1106;
• Add new models to the Model Zoo;
• Fixed some bugs that were causing crashes;
• Added RGA acceleration support for some image processing interfaces on Rockchip devices with RKNPU2;
• Added a simple Android example demo;
• Added library support for Linux and macOS on x86 and arm64 platforms in PyPI, enabling rapid deployment;
• Release of precompiled libraries for macOS.

InspireFace v1.1.8

Adapted the optional image processing engines within the SDK, providing a more lightweight InspireCV while retaining OpenCV from previous versions; The SDK has been streamlined by removing some third-party dependencies, making it more lightweight.

1. Added and set as default a more lightweight image processing engine;
2. Modified the vector management engine of the Feature-Hub module to sqlite-vec, improving search efficiency;
3. Replaced internal data structures with generic abstract classes to ensure generalization;
4. Achieved overall SDK size reduction, resulting in a more lightweight library through compilation;
5. Implemented PyPI package management and enhanced the implementation of Python native interfaces.