ASPCS
 
Back to Volume
Paper: Machine Learning Using the NVidia Jetson Nano
Volume: 532, ASTRONOMICAL DATA ANALYSIS SOFTWARE AND SYSTEMS XXX
Page: 215
Authors: Kent, B. R.
Abstract: The Nvidia Jetson Nano is a small embedded compute board with four CPU cores and a 128-core Maxwell generation GPU. We utilize the PyTorch framework to train a convolutional neural network image classifier using a small imaging subset of the VLA Sky Survey that is split into both testing and validation collections. We construct a simple shape classification scheme and report on the loss function for the network that can be run on the Nano hardware.
Back to Volume