Author: Fritz

In this tutorial, we’ll continue learning the various use-cases of the TensorFlow.js library. Our previous tutorial used this library for real-time human pose estimation. Here, we’re going to detect hand gestures using the library.

In this tutorial, we’re going to focus our pose algorithm on a smaller area—human hands. We are going to detect the hand poses and gestures using the TensorFlow.js library. Like in the previous tutorial, we are going to make use of a webcam for gesture detection and canvas for drawing or displaying the result of the detection.

Continue reading How to detect a “thumbs-up” in the browser with TensorFlow.js

Machine learning is a buzzword nowadays. There are plenty of theories going around, but it’s hard to see real applications that can be built by an indie developer.

Developing an end-to-end machine learning system requires a wide range of expertise in areas like linear algebra, vector calculus, statistics, and optimization.

Therefore, from a developer’s perspective, there’s a high learning curve that stands in the way, but the latest tools take care of most of the work for developers, leaving them free to code.

Continue reading “How to retrain ResNet in Keras and use it in an iOS App via Core ML”

The power of React Native as a framework continues to increase over time. For those who are unfamiliar, React Native is a cross-platform framework developed by Facebook. It’s open source and lets you build mobile applications using JavaScript as its core.

Thanks to Nicolas Gallagher’s open source project React Native for Web, now you can use React Native API components to build a web application that uses React DOM as its core. React Native already makes it convenient to write mobile apps for two platforms: iOS and Android. And now the web is slowly entering the picture. 🤩

Continue reading How to Build a Web App with React Native

The deployment of a machine learning (ML) model to production starts with actually building the model, which can be done in several ways and with many tools.

The approach and tools used at the development stage are very important at ensuring the smooth integration of the basic units that make up the machine learning pipeline. If these are not put into consideration before starting a project, there’s a huge chance of you ending up with an ML system having low efficiency and high latency.

Continue reading Deploying Machine Learning Models on Google Cloud Platform (GCP)

Hi there, this is the 3rd part of a 3 part series, for better understanding kindly read my first and second articles here:

In part 3, we’ll be taking the model we built in parts 1 and 2 and exploring how to implement it on a Raspberry Pi 3.

Raspberry Pi is a low-cost micro computer that can be plugged into a computer monitor or TV alongside a keyboard and mouse to simulate a full PC experience.

Continue reading End-to-End Object Detection Using EfficientDet on Raspberry Pi 3 (Part 3)

In certain cases, there are requirements where a certain page in your application can only be viewed in a particular orientation, i.e. portrait/landscape. Dealing with this issue in native Android/iOS is like a walk in the park, but doing this in a cross-platform framework can be confusing!

Want to find the easiest way out of it? This tutorial is intended to show you how to force an orientation on a single page while developing with Xamarin. Let’s get to it!

Continue reading Force an orientation on a single page in Xamarin.Forms

Machine learning as a field is full of technical terms, making it difficult for beginners to get started. One might see things like “deep learning,” “the kernel trick,” “regularization,” “overfitting,” “semi-supervised learning,” “cross-validation,” etc. But what in the world do they mean?

One of the core tasks in building any machine learning model is to evaluate its performance. It’s fundamental, and it’s also really hard.

Continue reading Evaluation Metrics for Machine Learning Models

In today’s world, mobile devices are an essential part of our daily lives—we use them as we walk, run, drive, and when doing many other activities.

Understanding what users are doing when holding their phones can allow your apps to adapt intuitively based on those user actions. And for some apps, it might be a requirement to identify when a user starts or stops a particular activity. For example, an app can start music in the background if a user starts running, or it can calculate the number of calories burned.

Continue reading Detect Users’ Activity in Android Using the Transition API

This post is a beginner’s guide for understanding the inner workings of doc2vec for NLP tasks.

There are two primary architectures for implementing doc2vec: namely Distributed Memory Model of Paragraph Vectors (PV-DM) and Distributed Bag-of-Words version of Paragraph Vector (PV-DBOW).

In this article, we’ll dive into how doc2vec is related to word2vec and explore both of their architectures while also getting some hands-on experience with them.

Continue reading Getting started with Doc2Vec

We’ve seen this feature in countless smartphone ads. The quick scene has someone traveling to a foreign country, having a local say something into their smartphone, and then smile as it provides the translation for them. Usually it takes up just seconds of the ad before they move onto a new camera feature or something.

What they don’t show is the aftermath as that smile turns into panic. For soon after, the user realizes they’re nowhere near their hotel’s free WiFi. They begin to calculate how much their international data charge will be by the time they finally translate the local’s instructions to the best food in town. Who knows if they’ll be able to afford it by then?

Continue reading Data-Free Speech Translator using SFSpeechRecognizer and ML Kit on iOS