Blog

The Not Hotdog app from HBO’s Silicon Valley has become one of the most iconic joke apps in tech. Like most things in the show, there is grain of truth to the fictitious app that makes it actually plausible.

With Not Hotdog, HBO went a step further—they actually built the thing. If you ever need help to figure out if something is a hotdog, head over the app store.

Continue reading “[Hacker Noon] Building Not Hotdog with Turi Create and Core ML — in an afternoon”

Once your TensorFlow model is ready, you can easily deploy it to a mobile application. This is done by converting it to the TF Lite format. If you are working on a common task such as image classification and object detection, you can easily grab a pre-trained model from TensorFlow Hub.

In this piece, we’ll use a pre-trained model to illustrate how one can deploy their model on an Android device.

Continue reading “Machine Learning in Android using TensorFlow Lite”

Humans have two eyes, which allow us to see two viewpoints of a scene. Using the complementary information from these two viewpoints, we are able to perceive depth in the world around us.

Researchers have been trying to utilize the complementary information present in two viewpoints for a long time — this can be seen in a wide variety of industrial applications, such as robotics and self-driving cars, where multiple cameras are used.

Continue reading “Holopix50k: A Large-Scale, In-the-Wild Stereo Image Dataset”

Artistic style transfer is one of the most intuitive and accessible computer vision tasks out there. Though there’s a lot happening under the hood of a style transfer model, functionally, it’s quite simple.

Style transfer takes two images — a content image and a style reference image — and blends them so that the resulting output image retains the core elements of the content image, but appears to be “painted” in the style of the style reference image.

Continue reading “Working with SnapML Templates in Lens Studio: Style Transfer”

Just last month (June 2020) Snapchat released a major update for its Lens creation software — Lens Studio 3.0. Out of all the new things that came along with the release, one feature that stood apart was SnapML.

SnapML allows lens creators to use their own custom machine learning models inside filters. Snapchat filters already use ML for a variety of things like face tracking, surface tracking, segmentation, facial gestures, and more.

Continue reading “Working with SnapML Templates in Lens Studio: An Overview”

In a previous tutorial, the Levenshtein distance is implemented to measure the distance between 2 words based on a vector.

This tutorial builds on that implementation to create an Android app that automatically gives suggestions to the user as he/she is typing. The distances between the input text and an English dictionary of 20,000 words are calculated. The words with the lowest distances are suggested to the user to automatically complete the text.

Continue reading “Text Auto-completion on Android Using the Levenshtein Distance”

Machine learning and deep learning are enabling amazing applications all around us. However, traditional models of deep neural networks are designed to take advantage of the vast memory and raw computing power of centralized servers.

In this article, we examine how the concept of ‘transfer learning’ may usher in deep learning efficiently on the edge, and more specifically, inside your smartphone.

Continue reading “Transfer Learning for Mobile ML”