EfficientNet

The EfficientNet model is based on the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.

Model builders

The following model builders can be used to instanciate an EfficientNet model, with or without pre-trained weights. All the model builders internally rely on the torchvision.models.efficientnet.EfficientNet base class. Please refer to the source code for more details about this class.

efficientnet_b0(*[, weights, progress])	EfficientNet B0 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b1(*[, weights, progress])	EfficientNet B1 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b2(*[, weights, progress])	EfficientNet B2 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b3(*[, weights, progress])	EfficientNet B3 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b4(*[, weights, progress])	EfficientNet B4 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b5(*[, weights, progress])	EfficientNet B5 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b6(*[, weights, progress])	EfficientNet B6 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.
efficientnet_b7(*[, weights, progress])	EfficientNet B7 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.