:py:mod:`anomalib.models.reverse_distillation.components.bottleneck`
====================================================================

.. py:module:: anomalib.models.reverse_distillation.components.bottleneck

.. autoapi-nested-parse::

   Torch model defining the bottleneck layer.



Module Contents
---------------

Classes
~~~~~~~

.. autoapisummary::

   anomalib.models.reverse_distillation.components.bottleneck.OCBE



Functions
~~~~~~~~~

.. autoapisummary::

   anomalib.models.reverse_distillation.components.bottleneck.conv3x3
   anomalib.models.reverse_distillation.components.bottleneck.conv1x1
   anomalib.models.reverse_distillation.components.bottleneck.get_bottleneck_layer



.. py:function:: conv3x3(in_planes: int, out_planes: int, stride: int = 1, groups: int = 1, dilation: int = 1) -> torch.nn.Conv2d

   3x3 convolution with padding.


.. py:function:: conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> torch.nn.Conv2d

   1x1 convolution.


.. py:class:: OCBE(block: Type[Union[torchvision.models.resnet.Bottleneck, torchvision.models.resnet.BasicBlock]], layers: int, groups: int = 1, width_per_group: int = 64, norm_layer: Optional[Callable[Ellipsis, torch.nn.Module]] = None)

   Bases: :py:obj:`torch.nn.Module`

   One-Class Bottleneck Embedding module.

   :param block: Expansion value is extracted from this block.
   :type block: Bottleneck
   :param layers: Numbers of OCE layers to create after multiscale feature fusion.
   :type layers: int
   :param groups: Number of blocked connections from input channels to output channels.
                  Defaults to 1.
   :type groups: int, optional
   :param width_per_group: Number of layers in each intermediate convolution layer. Defaults to 64.
   :type width_per_group: int, optional
   :param norm_layer: Batch norm layer to use. Defaults to None.
   :type norm_layer: Optional[Callable[..., nn.Module]], optional

   .. py:method:: _make_layer(self, block: Type[Union[torchvision.models.resnet.Bottleneck, torchvision.models.resnet.BasicBlock]], planes: int, blocks: int, stride: int = 1, dilate: bool = False) -> torch.nn.Sequential


   .. py:method:: forward(self, features: List[torch.Tensor]) -> torch.Tensor

      Forward-pass of Bottleneck layer.

      :param features: List of features extracted from the encoder.
      :type features: List[Tensor]

      :returns: Output of the bottleneck layer
      :rtype: Tensor



.. py:function:: get_bottleneck_layer(backbone: str, **kwargs) -> OCBE

   Get appropriate bottleneck layer based on the name of the backbone.

   :param backbone: Name of the backbone.
   :type backbone: str

   :returns: One-Class Bottleneck Embedding module.
   :rtype: Bottleneck_layer