EfficientNets: a family of more efficient & accurate image classification models. Found by architecture search and scaled up by one weird trick. Link: Github: Blog:
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 tensorflow: pytorch:
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"