Spaces:
Running
Running
| title: README | |
| emoji: π | |
| colorFrom: green | |
| colorTo: purple | |
| sdk: static | |
| pinned: false | |
| tag: python, c++, x86, deep learning, Neural networks, Edge AI, DL-inference | |
| # OpenVINO Toolkit | |
| ### Make AI inference faster and easier to deploy! | |
|  | |
| Learning and practicing AI is not easy, deploying AI in real applications is challenging and hard. We realized that and created | |
| OpenVINO β an open-source toolkit for bringing AI models to life on the most widespread and available platforms like x86 CPUs | |
| and integrated Intel GPUs. One can use OpenVINO to optimize own model for high performance with the most advanced model optimization | |
| capabilities and run those through OpenVINO runtime on various devices. We are driven by the idea to make it easy for a regular person | |
| to learn and use AI with minimal investments and unlock innovation with the use of AI to a wide audience. Not only we allow AI inference | |
| on the most widespread and popular platforms, but also we provide pre-trained models, educational and visual demos, image annotation | |
| tools and model training templates to get you up to speed. Along with good use-case coverage and simple/educational API, OpenVINO | |
| is also a toolkit of choice for AI in production by plenty of companies, it is a fully production-ready software solution. | |