EfficientNet

This model was released on 2019-05-28 and added to Hugging Face Transformers on 2023-02-20.

EfficientNet

Overview

The EfficientNet model was proposed in EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan and Quoc V. Le. EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, yet being an order-of-magnitude smaller and faster than previous models.

The abstract from the paper is the following:

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters.

This model was contributed by adirik. The original code can be found here.

EfficientNetConfig

[[autodoc]] EfficientNetConfig

EfficientNetImageProcessor

[[autodoc]] EfficientNetImageProcessor - preprocess

EfficientNetImageProcessorFast

[[autodoc]] EfficientNetImageProcessorFast - preprocess

EfficientNetModel

[[autodoc]] EfficientNetModel - forward

EfficientNetForImageClassification

[[autodoc]] EfficientNetForImageClassification - forward