Stable Diffusion web UI
Desktop2Stereo: 2D desktop to 3D for VR/AR (Support AMD/NVIDIA/Intel/Qualcomm GPUs and Apple Silicon Chips, powered by Depth AI Models)
EmbeddedLLM: API server for Embedded Device Deployment. Currently support CUDA/OpenVINO/IpexLLM/DirectML/CPU
export any your YOLOv7 model to TensorFlow, TensorFlowJs, ONNX, OpenVINO, RKNN,...
Unified deployment pipeline
RL Forex Bot with PPO AI-powered trading bot using PPO, dynamic position sizing, AMD GPU acceleration (DirectML/OpenCL), and MetaTrader 5 integration.
Automatically remove the mosaics in images and videos with any GPU. Offers DirectML for AMD instead of only CUDA like most other programs.
AI-powered image editor with InstructPix2Pix. Modern glassmorphism UI, AMD DirectML support, batch generation, and more.
It is the compatibility engine behind the SOTA LabVIEW Deep Learning Toolkit, ensuring that every ONNX operator behaves consistently across hardware targets. It validates each node against multiple execution providers to guarantee reliable and predictable AI deployment.
🧪 Test ONNX Runtime Execution Provider coverage with real-world operator support mappings for effective AI deployment insights.
actively maintained python package to easily retrain OpenAI's GPT-2 text-generating model on new texts using tensorflow v1 (with AMD / Intel GPU using directml)
📸 Recognize student faces in class using Python, OpenCV, and ONNX for attendance tracking via webcam and SQLite database.
PyTorch Generative model for generating clothing from Fashion MNIST with reproducible training/evaluation
Lightweight offline AI assistant for Windows 11 with voice and GUI support. Built with HuggingFace, Tkinter, and DirectML for fast local inference.
Sistema de presença por reconhecimento facial com captura guiada estilo Face ID, ONNX (SFace), GPU via DirectML e banco SQLite.
low-latency real-time object detection and tracking pipeline built in Python, featuring zero-allocation preprocessing, optimized GDI-based screen capture, and GPU-accelerated inference via ONNX Runtime with TensorRT and CUDA backends. Designed for high-FPS, production-grade performance experimentation.
A robust benchmarking framework for evaluating GPU/CPU performance from NVIDIA, AMD, Intel, DirectML, using PyTorch, TensorRT, TensorFlow, Pytest, and Allure Reporting Dashboards, and leveraging CI/CD, Docker, and Kubernestes.
Add a description, image, and links to the directml topic page so that developers can more easily learn about it.
To associate your repository with the directml topic, visit your repo's landing page and select "manage topics."