pCAMP: Performance Comparison of Machine Learning Packages on the Edges
This addresses the problem of selecting appropriate machine learning tools for edge computing, but it is incremental as it focuses on benchmarking existing packages.
The paper compared the performance of several machine learning packages (TensorFlow, Caffe2, MXNet, PyTorch, and TensorFlow Lite) on edge devices by evaluating latency, memory footprint, and energy consumption with two neural network types, providing a reference for users to select hardware-software combinations.
Machine learning has changed the computing paradigm. Products today are built with machine intelligence as a central attribute, and consumers are beginning to expect near-human interaction with the appliances they use. However, much of the deep learning revolution has been limited to the cloud. Recently, several machine learning packages based on edge devices have been announced which aim to offload the computing to the edges. However, little research has been done to evaluate these packages on the edges, making it difficult for end users to select an appropriate pair of software and hardware. In this paper, we make a performance comparison of several state-of-the-art machine learning packages on the edges, including TensorFlow, Caffe2, MXNet, PyTorch, and TensorFlow Lite. We focus on evaluating the latency, memory footprint, and energy of these tools with two popular types of neural networks on different edge devices. This evaluation not only provides a reference to select appropriate combinations of hardware and software packages for end users but also points out possible future directions to optimize packages for developers.