Cifar-10 Image Classification with Convolutional Neural Networks For Embedded Systems
Çalık, Rasim Caner
Demirci, Muhammed Fatih
MetadataShow full item record
Convolutional Neural Networks (CNN) have been successfully applied to image classification problems.Although powerful, they require a large amount of memory. The purpose of this paper is to perform image classification using CNNs on the embedded systems, where only a limited amount of memory is available. Our experimental analysis shows that 85.9% image classification accuracy is obtained by our framework while requiring 2GB memory only, making our framework ideal to be used in embedded systems.