This notebook demonstrates Fast Neural Style Transfer on ONNX models with OpenVINO. Style Transfer models mix the content of an image with the style of another image.
For this notebook, we use five pretrained models, for the following styles: Mosaic, Rain Princess, Candy, Udnie and Pointilism. The models are from the ONNX Model Repository and are based on the research paper Perceptual Losses for Real-Time Style Transfer and Super-Resolution by Justin Johnson, Alexandre Alahi and Li Fei-Fei.
In this notebook, we:
- load an ONNX model in Inference Engine and do inference on this model,
- show inference results on five neural style transfer models,
- save the transformed images and provide a download link.
The ONNX models are downloaded in the notebook, and a sample image is provided. See this short video for instructions on how to upload your own images to Jupyter Lab.
If you have not done so already, please follow the Installation Guide to install all required dependencies.