Skip to content

romulus0914/EfficientNet-PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

EfficientNet-Pytorch

A PyTorch implementation of EfficientNet

Overview

A PyTorch implementation of EfficientNet architecture: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Based on MobileNet-V2 and found by MNAS, EfficientNet-B0 is the baseline model to be scaled up. EfficientNet-(B1, B2, B3, B4, B5, B6, B7) are scaled up in width(channels), depth(layers), and resolution(image size). Results: EfficientNet-B7 achieves state-of-the-art 84.4% top-1 / 97.1% top-5 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet.

EfficientNet Architecture

Architecture

EfficientNet Results

Params Flops

Disclaimer

Modified from official code EfficientNets.

About

A PyTorch implementation of EfficientNet

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages