Author: Fritz

Nowadays, building a machine learning app isn’t considered nearly as difficult as it used to be. We have numerous cloud providers offering services that enable us to use their ML service to train and deploy models to a variety of environments and devices.

In this tutorial, we’re going to use TensorFlow.js to classify an apple as rotten or fresh using a fruit image dataset from Kaggle. We’re going to train our model using Microsoft Custom Vision from the Azure software family. Lastly, we’ll implement a simple Node.js application in order to handle the classification task directly on the browser.

Continue reading Image Classification Made Easy in the Browser with TensorFlow.js

Machine learning is rapidly moving from manually designed models to automated data pipelines using tools such as auto-sklearn, MLbox, and TPOT. In using these automated tools, the aim is to simplify the model selection process and come up with the best data set features for our model.

Continue reading Introduction to Automated Feature Engineering Using Deep Feature Synthesis (DFS)

In this article, we’ll explore a range of debugging techniques that can be used while developing in Android Studio. As developers, we all know that there are days where you spend way more time in your debugger than you do in your code editor.

If you don’t know what debugging actually is then check out the link below:

Continue reading Tips & Tricks for Debugging in Android Studio

You may recall that Apple acquired the machine learning and artificial intelligence startup Turi a few years ago for upwards of $200M; it offers powerful tools to create advanced machine learning models in a short amount of time.

In this tutorial, you’ll be learning to install Turi Create on your Mac, create a Python script, and use that script to train a Core ML model that you can drag directly into your Xcode projects and quickly implement in your apps.

Continue reading Training a Core ML Model with Turi Create to Classify Dog Breeds

My initial interest in mobile machine learning came from a somewhat strange place. In short, a friend of mine approached me with an idea for an application that would apply a NSFW filter to online videos. This led to a two-week deep dive into the tools to make this happen:

The framework to be used to train the model (TensorFlow, Keras, Turi Create, etc.) The platform to launch this framework for training purposes (Google Colab, FloydHub, Conda, etc.) The programs to be used to markup photos (RectLabel, LabelImg) Python scripts to be used to convert these annotations in the format required by the framework

In the end, I collected a dataset of 100 photos which I found on the Internet (don’t ask), and I succeeded in training my first object detection model ready for mobile.

Continue reading “Train and Ship a Core ML Object Detection Model for iOS in 4 Hours — Without a Line of Code”

Speech recognition is invading our lives. It’s built into our phones (Siri), our game consoles (Kinect), our smartwatches (Apple Watch), and even our homes (Amazon Echo). But speech recognition has been around for decades, so why is it just now hitting the mainstream?

The reason is that deep learning finally made speech recognition accurate enough to be useful outside of carefully-controlled environments. In this blog post, we’ll learn how to perform speech recognition with 3 different implementations of popular deep learning frameworks.

Continue reading The 3 Deep Learning Frameworks For End-to-End Speech Recognition That Power Your Devices

Thus far in our series on SwiftUI, our demo project consists of a dynamic profile page that’s ready to take in any Person and display their attributes. In this tutorial, we’ll get to actually make a list of folks that we can scroll through using a List and, when we select one, navigate to their detailed profile page!

Continue reading SwiftUI: Lists, Navigation, and Detail Views

This tutorial is a step-by-step guide for building an artificial neural network (ANN) using OpenCV for Android devices. An ANN for creating a 2-input XOR gate is built and trained on a desktop computer and then saved for later use in an Android app.

The IDE used in this tutorial for building the desktop app is NetBeans and the OS is Windows. This tutorial discusses the steps for using OpenCV in NetBeans.

Continue reading Running Artificial Neural Networks in Android using OpenCV

Android provides many ways of storing an application’s data. One of these ways is called SharedPreferences. SharedPreferences allow you to save and retrieve data in the form of a key-value pair. It’s beneficial to use SharedPreferences APIs only when you have a relatively small collection of key-values that you’d like to save. Each SharedPreferences file is managed by the framework and can be private or shared.

Continue reading SharedPreferences in Android