DeepLearningKit - an GPU Optimized Deep Learning Framework for Apple's iOS, OS X and tvOS developed in Metal and Swift
This framework addresses the problem of deploying deep learning models efficiently on Apple devices for developers, though it is incremental as it builds on existing methods for mobile and desktop integration.
The authors introduced DeepLearningKit, an open-source framework that enables the use of pretrained deep learning models on Apple platforms (iOS, OS X, tvOS) by leveraging Metal for GPU optimization and Swift for integration, aiming to support models from popular frameworks like Caffe and TensorFlow.
In this paper we present DeepLearningKit - an open source framework that supports using pretrained deep learning models (convolutional neural networks) for iOS, OS X and tvOS. DeepLearningKit is developed in Metal in order to utilize the GPU efficiently and Swift for integration with applications, e.g. iOS-based mobile apps on iPhone/iPad, tvOS-based apps for the big screen, or OS X desktop applications. The goal is to support using deep learning models trained with popular frameworks such as Caffe, Torch, TensorFlow, Theano, Pylearn, Deeplearning4J and Mocha. Given the massive GPU resources and time required to train Deep Learning models we suggest an App Store like model to distribute and download pretrained and reusable Deep Learning models.