{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n# Neural Style Transfer without ``pystiche``\n\nThis example showcases how a basic Neural Style Transfer (NST), i.e. image-based\noptimization, could be performed without ``pystiche``.\n\n
This is an *example how to implement an NST* and **not** a\n *tutorial on how NST works*. As such, it will not explain why a specific choice was\n made or how a component works. If you have never worked with NST before, we\n **strongly** suggest you to read the `gist` first.
The images used in this example are licensed under the permissive\n `Pixabay License
If you want to start from a white noise image instead use\n\n .. code-block:: python\n\n input_image = torch.rand_like(content_image)