efficientnet_b2

torchvision.models.efficientnet_b2(*, weights: Optional[EfficientNet_B2_Weights] = None, progress: bool = True, **kwargs: Any) → EfficientNet

EfficientNet B2 model architecture from the EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks paper.

Parameters:

• weights (EfficientNet_B2_Weights, optional) – The pretrained weights to use. See EfficientNet_B2_Weights below for more details, and possible values. By default, no pre-trained weights are used.

• progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.

• **kwargs – parameters passed to the torchvision.models.efficientnet.EfficientNet base class. Please refer to the source code for more details about this class.

class torchvision.models.EfficientNet_B2_Weights(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)