TResNet
2000년 도입 · 논문 1편에서 사용
A TResNet is a variant on a ResNet that aim to boost accuracy while maintaining GPU training and inference efficiency. They contain several design tricks including a SpaceToDepth stem, Anti-Alias downsampling, In-Place Activated BatchNorm, Blocks selection and squeeze-and-excitation layers.
출처: TResNet: High Performance GPU-Dedicated Architecture
소개 논문: TResNet: High Performance GPU-Dedicated Architecture
Convolutional Neural Networks · Computer Vision