dacapo.experiments.model
========================

.. py:module:: dacapo.experiments.model


Classes
-------

.. autoapisummary::

   dacapo.experiments.model.Model


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

.. py:class:: Model(architecture: dacapo.experiments.architectures.architecture.Architecture, prediction_head: torch.nn.Module, eval_activation: torch.nn.Module | None = None)



   A trainable DaCapo model. Consists of an ``Architecture`` and a
   prediction head. Models are generated by ``Predictor``s.

   May include an optional eval_activation that is only executed when the model
   is in eval mode. This is particularly useful if you want to train with something
   like BCELossWithLogits, since you want to avoid applying softmax while training,
   but apply it during evaluation.

   .. attribute:: architecture

      The architecture of the model.

      :type: Architecture

   .. attribute:: prediction_head

      The prediction head of the model.

      :type: torch.nn.Module

   .. attribute:: chain

      The architecture followed by the prediction head.

      :type: torch.nn.Sequential

   .. attribute:: num_in_channels

      The number of input channels.

      :type: int

   .. attribute:: input_shape

      The shape of the input tensor.

      :type: Coordinate

   .. attribute:: eval_input_shape

      The shape of the input tensor during evaluation.

      :type: Coordinate

   .. attribute:: num_out_channels

      The number of output channels.

      :type: int

   .. attribute:: output_shape

      The shape of the output

      :type: Coordinate

   .. attribute:: eval_activation

      The activation function to apply during evaluation.

      :type: torch.nn.Module | None

   .. method:: forward(x

      torch.Tensor) -> torch.Tensor:
      Forward pass of the model.

   .. method:: compute_output_shape(input_shape

      Coordinate) -> Tuple[int, Coordinate]:
      Compute the spatial shape of this model, when fed a tensor of the given spatial shape as input.

   .. method:: scale(voxel_size

      Coordinate) -> Coordinate:
      Scale the model by the given voxel size.

   .. note:: The output shape is the spatial shape of the model, i.e., not accounting for channels and batch dimensions.


   .. py:attribute:: num_out_channels
      :type:  int


   .. py:attribute:: num_in_channels
      :type:  int


   .. py:attribute:: architecture


   .. py:attribute:: prediction_head


   .. py:attribute:: chain


   .. py:attribute:: input_shape


   .. py:attribute:: eval_input_shape


   .. py:attribute:: eval_activation


   .. py:method:: forward(x)

      Forward pass of the model.

      :param x: The input tensor.
      :type x: torch.Tensor

      :returns: The output tensor.
      :rtype: torch.Tensor

      .. rubric:: Examples

      >>> model = Model(architecture, prediction_head)
      >>> model.forward(x)
      torch.Tensor

      .. note:: The eval_activation is only applied during evaluation. This is particularly useful if you want to train with something like BCELossWithLogits, since you want to avoid applying softmax while training, but apply it during evaluation.



   .. py:method:: compute_output_shape(input_shape: funlib.geometry.Coordinate) -> Tuple[int, funlib.geometry.Coordinate]

      Compute the spatial shape (i.e., not accounting for channels and
      batch dimensions) of this model, when fed a tensor of the given spatial
      shape as input.

      :param input_shape: The shape of the input tensor.
      :type input_shape: Coordinate

      :returns: The number of output channels and the spatial shape of the output.
      :rtype: Tuple[int, Coordinate]

      :raises AssertionError: If the input_shape is not a Coordinate.

      .. rubric:: Examples

      >>> model = Model(architecture, prediction_head)
      >>> model.compute_output_shape(input_shape)
      (1, Coordinate(1, 1, 1))

      .. note:: The output shape is the spatial shape of the model, i.e., not accounting for channels and batch dimensions.



   .. py:method:: scale(voxel_size: funlib.geometry.Coordinate) -> funlib.geometry.Coordinate

      Scale the model by the given voxel size.

      :param voxel_size: The voxel size to scale the model by.
      :type voxel_size: Coordinate

      :returns: The scaled model.
      :rtype: Coordinate

      :raises AssertionError: If the voxel_size is not a Coordinate.

      .. rubric:: Examples

      >>> model = Model(architecture, prediction_head)
      >>> model.scale(voxel_size)
      Coordinate(1, 1, 1)

      .. note:: The output shape is the spatial shape of the model, i.e., not accounting for channels and batch dimensions.