PyTorch Mobile Machine Learning Framework Announced
- By Becky Nagel
- October 10, 2019
On Thursday the developers of PyTorch announced PyTorch Mobile, which they say will allow for "end-to-end workflow from Python to deployment on iOS and Android."
PyTorch Mobile is part of PyTorch 1.3, which currently is an "experimental release" that the organization will be "building on over the next couple of months." PyTorch 1.2 was released in August.
New features coming will include preprocessing and integration APIs, support for ARM CPUs and QNNPACK (a quantized neural network package designed for PyTorch), build-level optimization, and performance enhancements for mobile CPUs/GPUs.
Android builds will use the Maven plug-in and iOS will use CocoaPods with Swift.
There are currently quickstart Hello World guides available for Android and iOS for developers who want to get their hands on the project now.
The open source PyTorch machine learning framework -- particularly popular for deep learning academic projects -- competes mainly with Google's open source TensorFlow framework for the hearts and minds of machine learning developers. TensorFlow offers TensorFlow Lite for IoT and mobile devices. In fact, in The Gradient's 2019 machine learning framework study, released Thursday, author Howard He cites PyTorch's lack of mobile support as one reason TensorFlow remains more popular in production/industry environments (versus academia). That study can be found here.
The organization released a tool for working with large graphing projects within PyTorch in July.
Becky Nagel is the vice president of Web & Digital Strategy for 1105's Converge360 Group, where she oversees the front-end Web team and deals with all aspects of digital strategy. She also serves as executive editor of the group's media Web sites, and you'll even find her byline on PureAI.com, the group's newest site for enterprise developers working with AI. She recently gave a talk at a leading technical publishers conference about how changes in Web technology may impact publishers' bottom lines. Follow her on twitter @beckynagel.