ABSTRACT
Dog Breed classification is a particular application of Deep Neural Network. Convolutional Neural Network is one of deep learning classification technique which demands a huge number of images as training data as well as a significant amount of time to train the data and attain improved classification accuracy. We use Transfer to get around this significant amount of time. A set of images of the breed and humans is used to classify and learn the characteristics of a dog’s breed. We are using various pre-trained models like VGG16, Xception, and Inception V3 and Densenet121 to train and test on “Stanford Dogs dataset” dataset. The purpose of this paper is to describe a study that employs a Convolutional Neural Network to categorise various dog breeds.
