Skip to content

Latest commit

 

History

History
17 lines (9 loc) · 999 Bytes

README.md

File metadata and controls

17 lines (9 loc) · 999 Bytes

Style Transfer for ml5/tf.js and video using Paperspace Gradient

This notebook can be used to train a style transfer model, convert it to a ml5 compatible one and/or use it to perform video style transfer all using Paperspace Gradient notebooks.

Paperspace Gradient offers a free GPU instance with their notebooks that you can run up to 6 hours at a time. You just need a free account. It is one of the easiest and most accessible ways to do machine learning, especially if you do not have a top-end GPU.

This notebook is based on the Google Colab notebook, provided by ml5 and adapted so it works with Gradient.

It excludes downloading of the 14GB+ COCO image dataset, since it is already provided by Paperspace.

NOTE: For this notebook to work, the Paperspace Docker image must be TensorFlow 1.14.

Enjoy!


Made by @zalashub. Feel free to contact me with any questions. :)