Using PyTorch, ONNX, WebAssembly, and the sclbl-webnode to deploy object recognition models directly in the browser.
Object recognition on the edge
Maurits Kaptein · August 10, 2020
Honestly? I don’t know. But I do think WebAssembly is a good target for ML/AI deployment (in the browser and beyond).
From model fitting to production in seconds
Maurits Kaptein · June 18, 2020The shortest tutorial for deploying ML & AI models efficiently.
Stop training more models, start deploying them
Maurits Kaptein · June 16, 2020We are hardly living up to the promises of AI in healthcare. It’s not because of our training, it’s because of our deployment.
MNIST number recognition on an ESP32
Robin van Emden · January 2, 2020A machinelearning framework isn’t complete without its MNIST number classification demo. Still, we think ours is pretty unique: Once converted to a Scailable WebAssembly task, our MNIST model runs on almost any type of device.
Apples and Oranges: Benchmarking Scailable
Robin van Emden · December 18, 2019In a new demo, we demonstrate how Scailable allows you to efficiently put models into production with just one additional line of code.