The collection of pre-trained, state-of-the-art models for C++.
ailia SDK is a cross-platform high speed inference SDK. The ailia SDK provides a consistent C++ API on Windows, Mac, Linux, iOS, Android and Jetson. It supports Unity, Python and JNI for efficient AI implementation. The ailia SDK makes great use of the GPU via Vulkan and Metal to serve accelerated computing.
The ailia SDK can be installed from a git submodule.
git submodule init
git submodule update
On macOS, the bundled .dylib files come with the com.apple.quarantine attribute, which causes Gatekeeper to reject them with errors such as libailia_voice.dylib is damaged. Strip the attribute by running the helper script after git submodule update:
./xattr.sh
Download the ailia SDK license file with the following command. The license file is valid for one month.
cd ailia
python3 download_license.py
Alternatively, the license file can be obtained by requesting the evaluation version of the ailia SDK.
cmake, opencv and Visual Studio 2019 or newer are required.
Please set the OpenCV path to the environment variable.
- OpenCV_DIR: C:\opencv\build
Xcode Commandline Tools are required, they can be installed by running the command.
xcode-select --install
cmake and OpenCV is required, it can be installed by running the command.
brew install cmake
brew install opencv
cmake and OpenCV is required, it can be installed by running the command.
apt install cmake
apt install libopencv-dev
Please run the following command in the root folder of your local repository.
cmake .
cmake --build .
To build only the audio/NLP samples (e.g. whisper and gpt-sovits-v2-pro) without OpenCV, pass -DWITH_OPENCV=OFF.
cmake -DWITH_OPENCV=OFF .
cmake --build .
Move to the model folder, execute sh or bat, then the model file will be downloaded and the model will run.
In the case of Windows, please copy dll files such as ailia.dll to the execution directory.
cd object_detection/yolox
./yolox.bat
cd object_detection/yolox
./yolox.sh
You can use the web camera by adding the -v 0 option.
cd object_detection/yolox
./yolox.sh -v 0
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| silero-vad | Silero VAD | Pytorch | 1.2.15 and later |
| clap | CLAP | Pytorch | 1.3.0 and later |
| whisper | Whisper | Pytorch | 1.2.16 and later |
| gpt-sovits | GPT-SoVITS | Pytorch | 1.4.0 and later |
| gpt-sovits-v2-pro | GPT-SoVITS | Pytorch | 1.4.0 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| U-2-Net | U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection | Pytorch | 1.2.2 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| resnet50 | Deep Residual Learning for Image Recognition | Chainer | 1.2.0 and later |
| clip | CLIP | Pytorch | 1.2.9 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| yolov3-face | YOLO: Real-Time Object Detection | ONNX Runtime | 1.2.1 and later |
| retinaface | RetinaFace: Single-stage Dense Face Localisation in the Wild. | Pytorch | 1.2.5 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| arcface | pytorch implement of arcface | Pytorch | 1.2.1 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| face_alignment | 2D and 3D Face alignment library build using pytorch | Pytorch | 1.2.1 and later |
| mediapipe_iris | irislandmarks.pytorch | Pytorch | 1.2.2 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| fugumt-en-ja | Fugu-Machine Translator | Pytorch | 1.2.9 and later |
| fugumt-ja-en | Fugu-Machine Translator | Pytorch | 1.2.10 and later |
| bert_maskedlm | huggingface/transformers | Pytorch | 1.2.5 and later |
| sentence_transformers | sentence transformers | Pytorch | 1.2.7 and later |
| t5_whisper_medical | error correction of medical terms using t5 | Pytorch | 1.2.13 and later |
| multilingual-e5 | multilingual-e5-base | Pytorch | 1.2.15 and later |
| g2p_en | g2p_en | Pytorch | 1.2.14 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| gemma4 | Gemma 4n (E2B) text chat (gguf) | gguf | 1.4.1 and later |
| gemma4-multimodal | Gemma 4n (E2B) multimodal (gguf + mmproj) | gguf | 1.4.1 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| yolov3-tiny | YOLO: Real-Time Object Detection | ONNX Runtime | 1.2.1 and later |
| m2det | M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network | Pytorch | 1.2.3 and later |
| yolox | YOLOX | Pytorch | 1.2.6 and later |
| yolox_tflite | YOLOX | Pytorch | 1.1.0 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| bytetrack | ByteTrack | Pytorch | 1.2.6 and later |
| Name | Detail | Exported From | Supported Ailia Version |
|---|---|---|---|
| lightweight-human-pose-estimation | Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper. | Pytorch | 1.2.1 and later |