Back to directory

OpenVINO Toolkit - Open Model Zoo

A collection of optimized, pre-trained deep-learning models and demo applications for the OpenVINO Toolkit, intended to speed up development of high-performance inference applications instead of training models from scratch.

OpenVINO Toolkit - Open Model Zoo

Open Model Zoo provides optimized deep-learning models and demo applications that show how to use them with the OpenVINO Toolkit, an inference engine for Intel hardware. It includes both Intel's own pre-trained models and public pre-trained models, a model-downloader and related automation tools, demos that show how to use the models, and an accuracy-checker tool for validating model accuracy.

The project is now in maintenance mode as a source of new models, with newer model tutorials published as Jupyter notebooks instead. It is licensed under the Apache License, Version 2.0, and by default collects software usage data to help improve OpenVINO, which can be turned off with a command-line flag.

More in Models

See all 405
  • mini-AGI

    github.com

    A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.

  • An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.

  • peekaboolean

    github.com

    A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.