Can I read EfficientNet - Rethinking Model Scaling For Convolutional Neural Networks on EtoBox?

EfficientNet - Rethinking Model Scaling For Convolutional Neural Networks by mike is a document available to read on EtoBox.

What is EfficientNet - Rethinking Model Scaling For Convolutional Neural Networks about?

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 sys- tematically study model scaling and identify that carefully balancing network depth, width, and res- olution 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 coeff

Author

mike

Language

EN