Latest

Luke Wood: Software Generalist & Machine Learning Specialist

bulletz.io

bulletz.io

bulletz.io is an open source real time multiplayer 2D shooter. To celebrate bulletz.io reaching 10k unique users, I have open sourced the codebase. Check it out on GitHub!

Learn more →
Ever seen an astronaut riding a horse? Understanding and applying text to image generation models

Ever seen an astronaut riding a horse? Understanding and applying text to image generation models

Conference presentation at Devoxx. This talk walks through the architecture and theory enabling these models to generate novel yet coherent images.

Learn more →
A walk through latent space with Stable Diffusion

A walk through latent space with Stable Diffusion

Explore the latent manifold of Stable Diffusion using latent space walking. By Ian Stenbit, Francois Chollet, Luke Wood

Learn more →
Train an Object Detection Model on Pascal VOC 2007 using KerasCV

Train an Object Detection Model on Pascal VOC 2007 using KerasCV

Use KerasCV to train a RetinaNet on Pascal VOC 2007.

Learn more →
wizardwars.online

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.

Learn more →
Efficient Graph-Friendly COCO Metric Computation for Train-Time Model Evaluation

Efficient Graph-Friendly COCO Metric Computation for Train-Time Model Evaluation

Pre-print publication written alongside Francois Chollet on a novel algorithm to closely approximate Mean Average Precision within the constraints of the TensorFlow graph. The algorithm used in the publication is used in the KerasCV COCO metric implementation, and can be used to perform train time evaluation with any KerasCV object detection model.

Learn more →
KerasCV

KerasCV

Author, #1 contributor, and lead of 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. KerasCV has over 32 contributors, and four full time team members.

Learn more →
Parametric Spectral Filters

Parametric Spectral Filters

Primary author of 2021 ICASSP Publication: Parametric Spectral Filters for Fast Converging, Scalable Convolutional Neural Networks. Please see GitHub repo for full information.

Learn more →