Enhance your Snapchat AR Lenses with machine learning. Today we’re thrilled to announce our platform’s support for building and implementing custom machine learning models in SnapML.
[SnapML] a game-changer…This now becomes the easiest way for ML developers to put their work in front of a large audience. I would say it’s analogous to how YouTube democratized video publishing.
Since the introduction of Core ML and TensorFlow Lite in late 2017, the intersection of mobile experiences and machine learning has been focused primarily on native app experiences. That equation has changed, however, with the recent unveiling of the newest platform for mobile machine learning: SnapML in Lens Studio.
But there remains a core roadblock to the true democratization of this cutting-edge technology—without significant ML know-how, creators, designers, and others are left with a confusing ML development ecosystem and without a feasible way to build truly custom SnapML-powered Lenses.
That’s where Fritz AI enters the picture. Today we’re thrilled to announce our platform’s support for building and implementing custom machine learning models in SnapML. With this set of capabilities, Fritz AI users can open doors to new horizons of creativity and immersion.
Leveraging our end-to-end development platform, creators, designers, developers, and more can quickly infuse custom machine learning models into Snapchat Lenses.
Building and implementing a custom image segmentation model for use in a Snapchat Lens. In my last post, I covered some of the difficulties of working with custom neural networks in Lens Studio.
In this article, I will show you how easily you can create a custom machine learning-powered Lens with almost no code. As a proof of concept, I chose to create a Lens that will recognize and classify Bulldogs.
Exploring SnapML: Working with Custom Neural Networks in Lens Studio. Key considerations to keep in mind when working with custom neural networks in SnapML and Lens Studio.
Build your own custom artistic Lens with SnapML and Style Transfer. Artistic style transfer is one of the most intuitive and accessible computer vision tasks out there.
You got intrigued by the machine learning world and wanted to get started as soon as possible, read all the articles, watched all the videos, but still isn’t sure about where to start, welcome to the club.