EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling
Google AI Blog
Posted by Mingxing Tan, Staff Software Engineer and Quoc V. Le, Principal Scientist, Google AI Convolutional neural networks (CNNs) are c...
EfficientNets: a family of more efficient & accurate image classification models. Found by architecture search and scaled up by one weird trick. Link:
EfficientNet is an open source library that uses a new compound model scaling method and leverages recent progress in #AutoML to improve #neuralnetwork scaling techniques, achieving state-of-the-art accuracy with up to 10x better efficiency. Learn more ↓
See also a trend in learning neural net architectures (eg AutoML) for accuracy as well as resources with NASNet being a first small step in that direction, and more recently EfficientNets
My work on improving MobileNet_v2 training efficiency will also improve the newer EfficientNet models. EfficientNets achieve "state-of-the-art accuracy with up to 10x better efficiency"