Skip to the main content

Professional paper

https://doi.org/10.19279/TVZ.PD.2020-8-1-18

KLASIFIKACIJA AUTOMOBILA KORISTEĆI TRANSFERIRANO UČENJE NA RESNET ARHITEKTURI NEURONSKE MREŽE

Stjepan Ložnjak ; Zagreb University of Applied Sciences, Zagreb, Croatia, Student
Tin Kramberger ; Zagreb University of Applied Sciences, Zagreb, Croatia
Ivan Cesar ; Zagreb University of Applied Sciences, Zagreb, Croatia
Renata Kramberger ; Zagreb University of Applied Sciences, Zagreb, Croatia


Full text: english pdf 2.021 Kb

page 59-64

downloads: 344

cite


Abstract

Classification is one of the most common problems that neural networks are used for. In the case of higher resolution image classification, convolutional neural networks are commonly used. Due to the reason that convolutional neural networks are so often used in classification, there are many pretrained models that can be adapted for new domains using a technique called transfer learning. This paper shows how excellent results in classification accuracy can be achieved by applying transfer learning to pretrained convolution neural network. This paper presents the results of the learning transfer of the ResNet-152 convolution neural network on the Stanford Cars dataset. The results show accuracy over 88% only by training the last fully connected layer.

Keywords

Transfer learning; ResNet; Stanford Car dataset

Hrčak ID:

242768

URI

https://hrcak.srce.hr/242768

Publication date:

17.6.2020.

Article data in other languages: croatian

Visits: 1.571 *