Basic Neural Network Subroutines: Using The Accelerate Framework's Convolution Filters
Last Revision: | Version 1.0, 2016-09-13 First release |
Build Requirements: | Xcode 8.0 or later; OS X 10.12 SDK or later |
Runtime Requirements: | OS X 10.12 or later |
BasicNeuralNetworkSubroutines (BNNS) is a new addition to the Accelerate framework. It provides optimized low-level functions dedicated to Machine Learning algorithms. Convolution filters are the main consumer of energy in Deep Neural Networks for image processing. This sample shows how to create and apply a convolution filter on a stack of images.
Copyright © 2016 Apple Inc. All Rights Reserved. Terms of Use | Privacy Policy | Updated: 2016-09-13