EffNet: An Efficient Structure for Convolutional Neural Networks

Code

• github.com/andrijdavid/EffNet
  pytorch★ 0
• github.com/MindCode-4/code-6/tree/main/effnet-an-efficient-structure
  mindspore★ 0
• github.com/MindCode-4/code-11/tree/main/dropblock-a-regularization-method
  mindspore★ 0

Abstract

With the ever increasing application of Convolutional Neural Networks to customer products the need emerges for models to efficiently run on embedded, mobile hardware. Slimmer models have therefore become a hot research topic with various approaches which vary from binary networks to revised convolution layers. We offer our contribution to the latter and propose a novel convolution block which significantly reduces the computational burden while surpassing the current state-of-the-art. Our model, dubbed EffNet, is optimised for models which are slim to begin with and is created to tackle issues in existing models such as MobileNet and ShuffleNet.

Reproductions