Table of content
If you're new to EfficientNets, here is an explanation straight from the official TensorFlow implementation:
EfficientNets are a family of image classification models, which achieve state-of-the-art accuracy, yet being an order-of-magnitude smaller and faster than previous models. EfficientNets are based on AutoML and Compound Scaling. In particular, AutoML Mobile framework have been used to develop a mobile-size baseline network, named as EfficientNet-B0; Then, the compound scaling method is used to scale up this baseline to obtain EfficientNet-B1 to B7.
EfficientNets achieve state-of-the-art accuracy on ImageNet with an order of magnitude better efficiency:
In high-accuracy regime, EfficientNet-B7 achieves state-of-the-art 84.4% top-1 / 97.1% top-5 accuracy on ImageNet with 66M parameters and 37B FLOPS, being 8.4x smaller and 6.1x faster on CPU inference than previous best Gpipe.
In middle-accuracy regime, EfficientNet-B1 is 7.6x smaller and 5.7x faster on CPU inference than ResNet-152, with similar ImageNet accuracy.
Compared with the widely used ResNet-50, EfficientNet-B4 improves the top-1 accuracy from 76.3% of ResNet-50 to 82.6% (+6.3%), under similar FLOPS constraint.
- Two lines to create model:
from efficientnet import EfficientNetB0 model = EfficientNetB0(weights='imagenet')
Loading saved model:
from efficientnet import load_model model = load_model('path/to/model.h5')
Available architectures and pretrained weights (converted from original repo):
"*" - topK accuracy score for converted models (imagenet
Weights for B4-B7 are not released yet (issue).
- keras >= 2.2.0 (tensorflow)
$ pip install -U git+https://github.com/qubvel/efficientnet
$ pip install -U efficientnet