
[논문 리뷰] EfficientNet : Rethinking Model Scaling for Convolutional Neural Networks
·
논문리뷰/Computer Vision
paper EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksConvolutional 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 narxiv.orgAbstract기존 CNN은 한정된 자원에서 개발하고, 자원이 충분해지면 성능 개선을 위한 scal..