A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

Transfer learning is a machine technique that uses previously acquired knowledge from source domain to enhance in target by reusing learned weights. This ubiquitous because of its great advantages achieving high performance while saving training time, memory, and effort network design. In this paper, we investigate how select the best pre-trained model meets requirements for image classification tasks. our study, refined output layers general parameters apply eleven processing models, on ImageNet, five different datasets. We measured accuracy, accuracy density, size evaluate models both sessions one episode with ten episodes.