Posted on

Neural Network Essentials

Neural networks are the core of all AI algorithms, and today, deep neural networks are used in tasks ranging from image recognition and object detection to natural language processing and generation. After dissecting the basic building blocks that form a neural network and the principles of how they work, this Refcard delves into neural architecture types and their respective uses, neural network chips, and model optimization techniques at a high level.
Posted on

How to Integrate HUAWEI ML Kit’s Image Super-Resolution Capability

Have you ever been sent compressed images that have poor definition? Even when you zoom in, the image is still blurry. I recently received a ZIP file of travel photos from a trip I went on with a friend. After opening it, I found to my dismay that each image was either too dark, too dim, or too blurry. How am I going to show off with such terrible photos? So, I sought help from the Internet, and luckily, I came across HUAWEI ML Kit's image super-resolution capability. The amazing thing is that this SDK is free of charge and can be used with all Android phones. 

Background

ML Kit's image super-resolution capability is backed by a deep neural network and provides two super-resolution capabilities for mobile apps:

Posted on

Raspberry Pi, OpenCV, Deep Neural Networks, and — Of Course— a Bit of Clojure

Learn more about Raspberry Pi, OpenCV, deep neural networks, and Clojure.

I had to write a simple IoT prototype recently that counted the number of people in a queue in real-time. Of course, I could have hired someone to do that and just keep counting people, or ... I could write a program in Clojure using a Raspberry Pi to detect the number of heads via a video stream.

You may also like: IoT OpenCV Scripting With Clojure on a Raspberry Pi

We learned recently that when using inlein, you can easily write scripts in Clojure with dependencies and run them just about anywhere, at a quite decent speed.