Recently Google AI Research published a paper titled “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks”. In this paper the authors propose a new architecture which achieves state of the art classification accuracy on ImageNet while being 8.4x smaller and 6.1x faster on inference than the best existing CNN. It achieves high level of acacuracy on many other datasets like CIFAR-100, Flowers and Cars. Good results on multiple dataset shows that the architecture can be used f...