Skafos makes it simple to build ML-powered apps, whether you are prototyping or delivering to millions of devices.Sign up free!
Personalize user choices, identify their actions, or even the things that they say. Classify whole images, objects inside images, or even just their look and feel. Skafos is the fastest way to the best parts of machine learning.
- Learn how machine learning works in your app by using an example ML-powered app and iterate.
- Install our framework to remove the tedious and time-consuming work.
Skafos manages your model deployments through automated background updates to the devices and apps using your models.
- Push updates as often as you need.
- Don’t fight app store reviews just to make adjustments to your models and overall user experience.
- Manage model versions in one easy-to-use dashboard.
- Bring your data, or your model, or both
- One user or millions, we grow with you
Getting Turi Create to train a model, with a GPU, on Colab was no small feat. In the rest of this post I will share how I was able to conquer the beast and train an Image Classification model on a Tesla T4 GPU. At the end, I link you directly to the code so you can play around for yourself.
This post is the 3rd installment in a series devoted to activity classification leveraging machine learning and on-device sensor data. In part 1, I shared about the tedious data collection process. Then in part 2, I showed you how to put the data to good use, training an activity classification model with Apple’s Turi Create. This last post will take you through an example iOS application (for iPhone) that leverages the machine learning model you’ve prepared and Skafos.ai for delivery.
This tutorial walks you through the process of taking data from Google’s Open Images Dataset and adjusting the bounding box coordinate system for use within the Turi Create Framework. We will do this using a nifty toolkit called OIDv4 Toolkit to retrieve the data we need.