Aplicação da Arquitetura YOLOv11 Nano na Classificação de Raças de Cães

This study evaluates the effectiveness of the YOLOv11 Nano neuralnetwork architecture for dog breed classification. YOLOv11 Nano isa small convolutional neural network (CNN) model specifically designedfor image classification task, particularly suited for objectswith similar characteristics, such as dog breeds. The proposed architecturepresents results comparable to previously applied networks,such as NASNet-A Mobile, and slightly underperforms in comparisonto Inception-ResNet-V2, despite its substantially smaller model size. Acomprehensive evaluation was conducted, incorporating pre-trainedmodels alongside optimization strategies, including data augmentationand K-Fold cross-validation. The results highlight the potential ofYOLOv11 Nano for the dog breed classification task, offering a balancebetween accuracy and size.