This is the fifth blog post in my AutoML Vision Edge series. The post will help you run AutoML Edge models on Docker containers. If you haven’t been following this blog post series till now, here’s a quick recap:
We started the series by learning how we can train and run inference on an edge-ready ML model in hours using Google Cloud’s AutoML.
Continue reading AutoML Vision Edge: Deploying and Running TensorFlow Models using Docker Containers
Though I support learning machine learning from scratch, I’m always interested in validating the classic Cost + Effort < Output.
Machine learning is interesting conceptually, but at the same time, it’s hard to understand for a beginner. A lot of effort is needed to master and understand the foundational mathematics and logic. But luckily, there are a number of tools available online to decrease these efforts exponentially. One of them is Google Cloud AutoML.
Synthesizing and editing video portraits—i.e., videos framed to show a person’s head and upper body—is an important problem in computer graphics, with applications in video editing and movie postproduction, visual effects, visual dubbing, virtual reality, and telepresence, among others.
The problem of synthesizing a photo-realistic video portrait of a target actor that mimics the actions of a source actor—and especially where the source and target actors can be different subjects—is still an open problem.
Recently, Apple showcased its new iPhone lineup, launching the iPhone XS, XS max, and XR. The most remarkable feature Apple included in this new line of devices is their smartest and most powerful chip ever — the A12 Bionic SoC (system on a chip).
Apple claims it has an 8-core Neural Engine dedicated to advanced, real-time machine learning applications. Similarly, Google has improved the Neural Net API in its Android framework in the latest OS: 9.0 Pie. Both of these features are responsible for something called hardware acceleration.
Continue reading “Hardware acceleration for machine learning on Apple and Android devices”
There’s a saying that goes like this: A picture is worth a thousand words, while an animation is worth a thousand pictures (which in turn means that it is worth a million words 😉)!
This is especially true in mobile applications, where effective animations can communicate to users what an app (or certain features within an app) is supposed to do. This is always a tough task, but tougher when we only rely on text or static images.
Continue reading Using Lottie on Android to display dynamic animations in your apps
In this research guide, we’ll look at deep learning papers aimed at synthesizing video frames within an existing video. This could be in between video frames, known as interpolation, or after them, known as extrapolation.
The better part of this guide will cover interpolation. Interpolation is useful in software editing tools as well as in generating video animations. It can also be used to generate clear video frames in sections where a video is blurred.
Continue reading Research Guide for Video Frame Interpolation with Deep Learning
Apple uses natural language processing techniques in many ways on iOS. Thanks to NLP, iOS can auto-fix typos, and Siri can understand what we’re saying. At WWDC 2018, Apple brought these capabilities to developers via a tool called Create ML. This tool has enabled developers to easily create text classification models (among numerous other kinds of models).
In its most general sense, the word dispatch describes the act of sending something somewhere for a particular purpose. In computer science, this term is used to indicate the same concept in different contexts, like to dispatch a call to a function, dispatch an event to a listener, dispatch an interrupt to a handler, or dispatch a process to the CPU.
Optical character recognition (OCR) is a method that helps machines recognize texts. Traditional OCR uses patterns and correlation to differentiate words from other elements. However, these techniques don’t tend to produce results with high accuracy for complex text or in-motion streams. For these tasks, you’re better served using deep learning models. In that spirit, in this article we’ll explore three deep learning models for OCR.
Continue reading Optical Character Recognition Using Deep Learning Techniques
In recent years, research related to vision-based 3D image processing has become increasingly active, given its many applications in virtual reality (VR) and augmented reality (AR). Despite years of studies, however, there are still images that machines struggle to understand—one of those is images of human hands.
Hand image understanding targets the problem of recovering the spatial configuration of hands from natural RGB or/and depth images. This task has many applications, such as human-machine interaction and virtual/augmented reality, among others.
Continue reading HAMR — 3D Hand Shape and Pose Estimation from a Single RGB Image
