Style Transfer using Spell with Yining Shi

From the creator

In this live stream, Yining Shi demonstrates how to train a "Style Transfer Model" using Spell (Sign up here: https://spell.run/codingtrain). After training the model, Yining writes code to process new images in the browser with ml5.js. #ThisDotStyle #StyleTransfer #MachineLearning This stream is sponsored by Spell. 4:28 - What is a Style Transfer 22:47 - Training a Style Transfer Model with Spell 56:48 - Converting model to ml5.js 1:18:35 - End of Presentation/Q&A 🔗 Style Transfer Example: https://yining1023.github.io/styleTransfer_spell/ 🔗 Detailed Instructions: https://github.com/yining1023/styleTransfer_spell/ 🔗 ml5.js: https://ml5js.org/ 🔗 p5.js: https://p5js.org 🔗 Fast Style Transfer in TensorFlow by Logan Engstrom: https://github.com/lengstrom/fast-style-transfer/ 🔗 Machine Learning 101: https://spell.run/docs/core_concepts/#machine-learning-101 🔗 What Neural Networks See by Gene Kogan: https://experiments.withgoogle.com/what-neural-nets-see 🔗 Fast style transfer in deeplearn.js by Reiichiro Nakano: https://github.com/reiinakano/fast-style-transfer-deeplearnjs 🎥 Introduction to Spell: https://youtu.be/ggBOAPtFjYU 🎥 Text Generation using Spell with Nabil Hassein: https://youtu.be/0IeqAd2H57g 🎥 Two Minute Papers: https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg Work Cited: 📙 A Neural Algorithm of Artistic Style [Leon A. Gatys, Alexander S. Ecker, Matthias Bethge] 📙 Perceptual Losses for Real-Time Style Transfer and Super-Resolution [Justin Johnson, Alexandre

Published 2018-09-21 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.