awesome-openvino

A streamlit interface with NuExtract-1.5-tiny and openvino-genai to extract data from plain text into structured custom json formats. The Repo also gives a small tutorial on how to convert NuExtract-1.5-tiny into OpenVINO IR format.

Make videos with AI images from YouTube videos.

An adaptation of the excellent Track Anything project which is in turn based on Meta's Segment Anything and XMem.

The integration of LLMs with sentiment analysis models, further optimised by OpenVINO.

FastSD CPU is a faster version of Stable Diffusion on CPU. Based on Latent Consistency Models and Adversarial Diffusion Distillation.

A beautiful Chat Interface, with interactive tuning parameters, powered by Optimum-Intel[openvino], Streamlit and the small but powerful Gemma2-2b-instruct model by Google. The model is an int4 quantized version, hosted on Hugging Face Hub.

Dives into vision-language models for Robotics applications using ROS 2 and Intel OpenVINO toolkit.

This post discusses Intel's new Neural Processing Unit (NPU) chips, which provide a significant performance boost for AI and machine learning tasks compared to regular CPUs, and provides steps for testing its capabilities using OpenVINO.

JAX (Just an Artificial Intelligence Extended) is an optimized version of the openSUSE Linux image to work with openVINO. This platform was designed to facilitate the access and development of AI applications.

allows to perform deep neural networks inference on NVIDIA GPUs using CUDA, using OpenVINO API.

This is a repository for an object detection inference API using OpenVINO, supporting both Windows and Linux operating systems

Dog Breed Classification and Body Localization.

Efficient Inference and Quantization of CGD for Image Retrieval.

The project begins by YOLOv8-pose detecting human body positions and extracting skeletal information from images. Based on the skeletal poses, it assesses the elbow angles and the distance between hands and mouths for each individual. If successful, the RTDETR model is employed to detect cigarettes at the mouth zone.

Chinese image-text similarity matching tasks, leverage OpenVINO and the Towhee embedding library.

implements different Computer Vision Deep Learning Models as a service.

Educational meterials about AI and Edge Computing Practice GNU IMAGE MANIPULATION PROGRAM

A published

OpenVINO backend for ExecuTorch enabling optimized PyTorch edge inference on CPU, GPU, and NPU targets.

Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, NumPy and OpenVINO. User can switch on OpenVINO backend for models inference using Keras API.

Community project extending LangChain with OpenVINO support for LLMs, embeddings, Whisper, and Vision-Language Models.

Officially supported LangChain backend for running LLMs, embeddings, and rerankers with OpenVINO, suitable for RAG and Agent pipelines on CPU, GPU, and NPU.

Run PyTorch models natively on OpenVINO using

Hugging Face integration layer for OpenVINO supporting Transformers, Diffusers, and SentenceTransformers with INT4/INT8 quantization via NNCF.

An Elderly Indoor Care Chatbot with an object detection algorithm.

Vision-Oriented MultiModal AI.

Integration of a chat bot with an object detection algorithm.

LLM Japanese chatbot demo program using Intel OpenVINO toolkit.

a port of GPT-Neo that uses OpenVINO.

The Resume-Based Interview Preparation Tool is a software application designed to streamline the interview process by helping interviewers generate relevant and meaningful questions based on a candidate's resume or portfolio page.