Learning and implementing different AI-powered apps using the TensorFlow.js library empowers you to do so many amazing things with ML in the browser.
This tutorial is the latest in my series using TensorFlow.js for machine learning and implementing those models in React apps. Here, we’ll learn about another TensorFlow library that helps with body segmentation.
Continue reading “Body Segmentation in the Browser with TensorFlow.js”
Visual scripting is one of the ways that you can add interactivity to your lenses. It is node-based, enabling you to see the logic as you are creating. You also don’t need to write code.
In this article, you will see how responses can be executed when certain events are enabled using node-based visual scripting.
Let say you have an image, and you want to distinguish objects of interest— or in other words, find suitable local characteristics to distinguish them from other objects or from the background. This is called image segmentation or semantic segmentation.
When we segment a target object, we know which pixel belongs to which object. The image is divided into regions and the discontinuities serve as borders between the regions. One can also analyze the shape of objects using various morphological operators.
Style transfer is a very popular deep learning task that lets you change an image’s composition by applying the visual style of another image.
From building artistic photo editors to giving a new look to your game designs through state-of-the-art themes, there are plenty of amazing things you can build with neural style transfer models. It’s also can be handy or data augmentation.
Continue reading “Running Create ML Style Transfer Models in an iOS Camera Application”
When he first conceived of Momento, founder Genday Okrain set out to build an experience that would allow users to look back on memories since-passed. The result was a mobile app that could transform photos, live photos, and videos into shareable GIFs.
When Snapchat’s Lens Studio released SnapML as a core part of their 3rd major platform update (3.0) back in June of 2020, our antennae immediately raised at the introduction of a new mobile platform for machine learning models.
We seized the opportunity, got to work, and less than a year later, a collection of our machine learning models have been baked into Lens Studio 3.4, the latest release of Snapchat’s flagship design tool. That’s right—Lens Creators can now directly access ML models designed and built specifically for Lens Studio by our team of experts!
Continue reading “Fritz AI Models Included in Lens Studio 3.4 Asset Library”
What a year for natural language processing! We’ve seen great improvement in terms of accuracy and learning speed, and more importantly, large networks are now more accessible thanks to Hugging Face and their wonderful Transformers library, which provides a high-level API to work with BERT, GPT, and many more language model variants.
Continue reading “Hands-on with Hugging Face’s new tokenizers library”
Someone once told me than any time you answer a question more than once, you should just blog about it. To anyone just starting out in data science, here’s how I began my journey: like everyone else, I Googled it.
If you do, you’ll be presented with millions of resources, and I guarantee you won’t know where to start. The amount of available information is overwhelming.
Continue reading “New to data science? Here are a few places to start”
If you’ve tried deploying your trained deep learning models on Android, you must have heard about TensorFlow Lite, the lite version of TensorFlow built for mobile deployment.
As a quick overview, it supports most of the basic operators; in simple terms, you can use it to do classification, object detection, semantic segmentation, and most of the text synthesis operations.
Continue reading “Profiling TensorFlow Lite models for Android”
In this article, let’s look at how you can use TensorFlow Model Maker to create a custom text classification model. Currently, the TF Lite model maker supports image classification, question answering, and text classification models. It uses transfer learning for shortening the amount of time required to build TF Lite models.
Continue reading “TensorFlow Lite Text Classification Models with Model Maker”
