Download
This repository contains a Keras (and TensorFlow Keras) reimplementation of EfficientNet, a lightweight convolutional neural network architecture achieving state-of-the-art accuracy with an order of magnitude fewer parameters and FLOPS, on both ImageNet and five other commonly used transfer learning datasets. 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.
Features
- We use neural architecture search to design a new baseline network and scale it up to obtain a family of models
- Much better accuracy and efficiency than previous ConvNets
- EfficientNets rely on AutoML and compound scaling to achieve superior performance without compromising resource efficiency
- EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet
- Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100
- EfficientNets achieve state-of-the-art accuracy on ImageNet with an order of magnitude better efficiency
Project Samples
