Processing a couple of gigabytes of data on one’s laptop is usually an uphill task, unless the laptop has high RAM and a whole lot of compute power.
That notwithstanding, data scientists still have to look for alternative solutions to deal with this problem. Some of the hacks involve tweaking Pandas to enable it to process huge datasets, buying a GPU machine, or purchasing compute power on the cloud. In this piece, we’ll see how we can use Dask to work with large datasets on our local machines.
You’ve got a great product, and you want to match this up with the way your mobile application looks and feels. This kind of consistency matters for creating engaging user experiences. And let’s say, in this app, you need to use maps in a way that fits your brand.
Luckily, there’s a way to easily create custom styles on Google Maps. With custom styling, you can change the look and feel of your map according to your desired needs.
Image colorization may have been reserved for those with artistic talent in the past, but now anyone with basic programming knowledge can get in on the action. Thanks to projects like DeOldify, we can colorize black and white images and video with minimal setup! The project even includes pre-trained weights, so you don’t need to spend time training on your machine.
Continue reading DeOldify: Visualizing Image Colorization with Hyper-Realistic Artwork
Traditionally, AI solutions have needed a large amount of parallel computational processing power. So for a long time, a requirement of AI-based service was server-based Internet connectivity. But solutions that require real-time action need on-device computation—this is where edge AI enters the picture.
You can use GPU-based devices, but it makes the process costly, and with this come the problems of bloated size and high energy consumption. But more and more, edge AI is becoming an essential part of the ongoing deep learning revolution, both in terms of research and innovation.
Continue reading Edge TPU: Hands-On with Google’s Coral USB Accelerator
Successful machine learning models are developed to serve and bring value to an end user. Whether the end user is a customer or domain expert, the full value of data science is only realized by operationalizing the workflow and exposing model predictions and insights to the end user. End users consume and interact with models in different contexts—via a web application, mobile application, or a command line API request.
Continue reading Deploying a Text Classification Model Using Flask and Vue.js
Advancements in the power of machine learning have brought with them major data privacy concerns. This is especially true when it comes to training machine learning models with data obtained from the interaction of users with devices such as smartphones.
So the big question is, how do we train and improve these on-device machine learning models without sharing personally-identifiable data? That is the question that we’ll seek to answer in this look at a technique known as federated learning.
Slow build speed is a huge momentum buster. It’s kind of like driving down the road and constantly hitting speed bump after speed bump. Build speed is critical to your productivity, and over the past few years, the Android team has consistently focused on improving build speed performance.
After implementing the tips in this article, we’ll be able to speed up development build times by 3x, 4x—sometimes even up to 10x. All by simply applying a set of best practices.
Continue reading 10 Tips to Speed Up Android Gradle Build Times
Every data science task needs data. Specifically, data that’s clean and understandable by the system it’s being fed into. When it comes to images, a computer needs to see what human eyes see.
For example, humans have the ability to identify and classify objects. Similarly, we can use computer vision to interpret visual data that it receives. That’s where image annotation comes into the picture.
Continue reading Data Annotation Fundamentals (Part 1) — Image Annotation
NumPy supports different ways of generating arrays, and this tutorial is going to explore one way of do so, using the np.linspace() function. It returns evenly-spaced numbers and can generate arrays of any dimensionality.
The following sections are covered in the tutorial:
linspace() is a function that is not only available in NumPy but also available in other tools such as MATLAB. By searching about it, you can find the regular answer which defines linspace() as a function to generate evenly spaced numbers.
Computer vision, at its core, is about understanding images. The field has seen rapid growth over the last few years, especially due to deep learning and the ability to detect obstacles, segment images, or extract relevant context from a given scene.
Using computer vision, we can build autonomous cars, smart buildings, fashion recommender systems, augmented reality tools…the possibilities are endless.
Continue reading Computer Vision and Deep Learning: From Image to Video Analysis
