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

The Triton backend for the ONNX Runtime.

A free python library that provides a simple interface to solve FunCaptcha challenges.

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

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

PhishTackle-API is a powerful machine learning-driven API designed to combat phishing attacks by analysing email content and URLs. Using machine learning algorithms, this API offers superior phishing detection to enhance your email security. Integrate PhishTackle-API into your applications to help detect and prevent phishing threats.

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

Use YOLOv8 in real-time, for object detection, instance segmentation, pose estimation and image classification, via ONNX Runtime.

Machine learning for code reviews!

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.

Easy to install image and video colorization using onnx converted deoldify model

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

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

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

Investigating a neural network response to input parameters using sensitivity analysis techniques.

基于Real-ESRGAN的图片AI超分辨率安卓APP

🍡 Toolkit for Distinguishing Anime from Real Images With No Torch.

Classification wrappers for 4 Deep Learning Embedded Runtimes for Music Information Retrieval, plus utilities to convert a TensorFlow Model

Faster large mini-batch distributed training w/o. squeezing devices