- Published on
Highlights
Luke Wood: Software Generalist & Machine Learning Specialist
![wizardwars.online](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2Fworlds-overlaid.jpg&w=1200&q=75)
wizardwars.online
wizardwars.online is a real-time multiplayer web game written entirely in TypeScript. Some highlights are the custom game engine, use of the Colyseus framework for authoritative multiplayer games, distributed physics computation and prediction, and a full React based rendering system.
![Marine Animal Object Detection with KerasCV](/videos/leopards-good.gif)
Marine Animal Object Detection with KerasCV
Use deep learning to detect marine animals including sharks, turtles, penguins, puffins, jellyfish and more!
![Teach StableDiffusion new concepts via Textual Inversion](/_next/image?url=%2Fstatic%2Fimages%2Fprojects%2Fgandalf.png&w=1200&q=75)
Teach StableDiffusion new concepts via Textual Inversion
Learning new visual concepts with KerasCV's StableDiffusion implementation.
![The Definitive Guide to Object Detection](/_next/image?url=%2Fimages%2Fprojects%2Fod-api.png&w=1200&q=75)
The Definitive Guide to Object Detection
My "definitive guide" to object detection is live on keras.io! This tutorial is a bit more like a textbook chapter than a typical keras.io tutorial, but by the end of it you will have an extremely strong sense of how to tackle object detection problems with deep learning.
![The Definitive Guide to Image Classification](/_next/image?url=%2Fimages%2Fprojects%2Fclassification.png&w=1200&q=75)
The Definitive Guide to Image Classification
My "definitive guide" to image classification is live on keras.io! This tutorial is a bit more like a textbook chapter than a typical keras.io tutorial, but by the end of it you will have an extremely strong sense of how to tackle classification problems with deep learning.
![KerasCV](/static/images/projects/keras-cv-augmentations.gif)
KerasCV
KerasCV is the official Keras repository of computer vision extensions to the Keras API (layers, metrics, losses, models, data-augmentation) that applied computer vision engineers can leverage to quickly assemble production-grade, state-of-the-art training and inference pipelines.
Blog
- Approximate non one to one mapping using mixture density networks.
- Published on
Construct a powerful object detection pipeline to detect marine animals- Published on
Learn about the tradeoffs of reducing losses using `sum()`, and reducing losses using `mean()`.- Published on
Overview of a common pitfall Keras users hit when writing subclass models- Published on
Overview of the first ever official Keras object detection API.