Distributing a Neural Network on Axis Cameras
Datorseende blir allt bättre, men med dess precision tillkommer en beräkningskostnad. Detta arbete undersöker hur man kan använda svagare men fler datorer, exempelvis kameror, för att implementera dagens kraftfulla algoritmer.This document describes the methods and results of our Master’s Thesis, car- ried out at Axis Communications AB. A central problem with deep neural networks is that they contain a large num- ber of parameters and heavy computations. To cope with this, our idea was to split the network into chunks large enough that they require their own core, yet small enough to not violate our memory constraints.
