Blog

Let say, for some reason, you process a huge load of images that contain some sort of logo (or even products). And you want to know which images are related to a specific companies. This is very common problem in AdTech and/or Data Mining companies.

Let’s imagine you have a user generated content in your application, so you want to know what’s inside the images, and if you have ads running (Bingo!), you can target a user based on the images they liked, commented on, published etc.

Continue reading “Logo Recognition iOS Application Using Machine Learning and Flask API”

Lobe, owned by Microsoft, is a free, no-code tool to train machine learning models without technical skills. Only image classification is supported as of this writing, and an object detection model training is coming soon according to Lobe’s homepage. You can download it here by entering your basic info. It’s 608 mb.

Continue reading “Train a Face-Mask Detection Model in Under 5 Minutes using Lobe.ai”

Innovation starts with solving personal problems. Every chess player writes down their moves on a chess scoresheet during a tournament game to analyze soon after. The annoying part is you have to record your moves once during the game, and then again into a computer to analyze the moves you played.

On top of this, it’s super easy to keep highly disorganized computer files (keeping track of moves in our minds, unfortunately, doesn’t translate well to keeping track of papers in real life). Instead, we store loose scoresheets in the musty depths of a backpack — crumpled up to oblivion.

Continue reading “Scannable Chess Scoresheets with a Convolutional Neural Network and OpenCV”

Over the last few years, generative models have been on the rise thanks to breakthrough innovations, especially in the domain of deep learning. We are now on the verge of solving complex tasks that seemed impossible 10 years ago.

There are countless applications for these techniques, so in this mini-series, we’ll focus on what they could bring to our handheld companions. In the first part let’s take a look at a few applications in image generation and transformation.

Continue reading “Using Generative Deep Learning Models On-Device”

In this article, we’ll use unowned references to break retain cycles in the object memory graph, learn how to handle memory in closures, and explore closure capture lists.

Unlike weak references, unowned references are used with non-optional types. Hence, it can’t go away if the reference type it’s pointing to goes away; instead it traps.

Continue reading “Advanced Memory Management in Swift”

Android’s Jetpack Compose is a modern toolkit for building native UIs. It’s simplified and is designed to accelerate UI development on Android while requiring less code

With Jetpack compose you don’t need to write an XML —calling a Jetpack Compose function will do the magic and create the element that you want.

Continue reading “Building UIs Using Android Jetpack Compose”

Using Google’s ML Kit one can build an application that can be consumed in more than 50 languages. For example, you can have users select the language they prefer and translate the app’s content into that language.

The translation is quite fast because it happens on the user’s device. The ML Kit translation models are built to translate to and from English.

Continue reading “Translate text with ML Kit on Android”

Those of you that have used meditation or breathing apps before might be familiar with this situation: You’re supposed to follow a simple breathing pattern. Inhale for four seconds, hold, exhale for four seconds. Sounds easy, but it can actually be pretty hard.

Soon after starting the exercise your mind starts drifting and you forget about that deep breath. But while you’re distracted, the exercise in your app keeps going until you’ve added another day to your mindfulness streak.

Continue reading “Real-Time Breath Tracking via AirPods”

Once your machine learning model is ready, you have to deploy it to a device. One of the ways that can be done is by shipping the model with the application. A challenge with this method is that whenever your model changes, you will need to ship a new APK to the app stores.

Obviously, this takes a long time because every app update needs to be verified by the app store. Now, imagine if it was possible to update the model over the air without the need to ship a new application. In this article, we will see how that can be done using Firebase Machine Learning.

Continue reading “Custom TensorFlow Lite model on Android using Firebase ML”