EfficientNet is a family of convolutional neural networks.
EfficientNet models efficiently scale up in terms of layer depth, layer width, input resolution, and a combination of all of these factors.
EfficientNet convolutional neural networks form features from images that we can then pass into a classifier.
EfficientNet forms the backbone of EfficientDet, an object detection model family.
EfficientNet is implemented in Keras here, which is abstracted, so we can load a custom dataset and train EfficientNet all in a few lines of code.