Silero VAD: pre-trained enterprise-grade Voice Activity Detector

An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.

YoloDotNet - A C# .NET 8.0 project for Classification, Object Detection, OBB Detection, Segmentation and Pose Estimation in both images and videos.

🚀 A high performance real-time object detection solution using YOLO11 ⚡️ powered by ONNX-Runtime

Edge Inference in Browser with Transformer NLP model

Rust wrapper for Microsoft's ONNX Runtime (version 1.8)

Face recognition and analytics library based on deep neural networks and ONNX runtime

The Triton backend for the ONNX Runtime.

A curated list of awesome inference deployment framework of artificial intelligence (AI) models. OpenVINO, TensorRT, MediaPipe, TensorFlow Lite, TensorFlow Serving, ONNX Runtime, LibTorch, NCNN, TNN, MNN, TVM, MACE, Paddle Lite, MegEngine Lite, OpenPPL, Bolt, ExecuTorch.

Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.

基于Real-ESRGAN的图片AI超分辨率安卓APP

ONNX Runtime for the Robot Operating System (ROS), works on ROS1 and ROS2

SOTA image super-resolution in JavaScript/Wasm using an ONNX-ported SwinIR model

Deep Learning Inference benchmark. Supports OpenVINO™ toolkit, TensorFlow, TensorFlow Lite, ONNX Runtime, OpenCV DNN, MXNet, PyTorch, Apache TVM, ncnn, PaddlePaddle, etc.

Easy-to-use danbooru anime image classification model

Easily run YOLOv11 object detection models in a TypeScript Bun environment. No Python, PyTorch, or heavy dependencies needed.

基于 ResNet 的花卉分类识别系统。

Renesas RZ/G AI BSP

Babylon.cpp is a C and C++ library for grapheme to phoneme conversion and text to speech synthesis. For phonemization a ONNX runtime port of the DeepPhonemizer model is used. For speech synthesis VITS models are used. Piper models are compatible after a conversion script is run.

This project includes implementations of YOLOv8, RT-DETR-V2(RTDETR), MobileSAM, and NanoSAM on TensorRT, ONNX Runtime, and RKNN, along with support for asynchronous inference workflows. It provides a user-friendly deep learning deployment tool for seamless algorithm migration across different inference frameworks.