batched_resnet

torch_uncertainty.models.batched_resnet(in_channels, num_classes, arch, num_estimators, conv_bias=True, dropout_rate=0, width_multiplier=1.0, groups=1, style='imagenet', normalization_layer=<class 'torch.nn.modules.batchnorm.BatchNorm2d'>, repeat_strategy='paper')

BatchEnsemble of ResNet.

Parameters:

• in_channels (int) – Number of input channels.

• num_classes (int) – Number of classes to predict.

• arch (int) – The architecture of the ResNet.

• num_estimators (int) – Number of estimators in the ensemble.

• conv_bias (bool) – Whether to use bias in convolutions. Defaults to True.

• dropout_rate (float) – Dropout rate. Defaults to 0.

• width_multiplier (float) – Width multiplier. Defaults to 1.0.

• groups (int) – Number of groups within each estimator.

• style (bool, optional) – Whether to use the ImageNet structure. Defaults to True.

• normalization_layer (nn.Module, optional) – Normalization layer.

• repeat_strategy (Literal["legacy", "paper"], optional) –

  The repeatrepeat_strategy (“legacy”|”paper”, optional): The repeat strategy to use during training:

  • ”legacy”: Repeat inputs for each estimator during both training and evaluation.

  • ”paper”(default): Repeat inputs for each estimator only during evaluation.

Returns:

A BatchEnsemble-style ResNet.

Return type:

_BatchedResNet