dasf.ml.dl.models
=================

.. py:module:: dasf.ml.dl.models


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/dasf/ml/dl/models/devconvnet/index


Classes
-------

.. autoapisummary::

   dasf.ml.dl.models.TorchPatchDeConvNet
   dasf.ml.dl.models.TorchPatchDeConvNetSkip
   dasf.ml.dl.models.TorchSectionDeConvNet
   dasf.ml.dl.models.TorchSectionDeConvNetSkip


Package Contents
----------------

.. py:class:: TorchPatchDeConvNet(n_classes=4, learned_billinear=False, clip=0.1, class_weights=None)

   Bases: :py:obj:`NNModule`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing to nest them in
   a tree structure. You can assign the submodules as regular attributes::

       import torch.nn as nn
       import torch.nn.functional as F

       class Model(nn.Module):
           def __init__(self):
               super().__init__()
               self.conv1 = nn.Conv2d(1, 20, 5)
               self.conv2 = nn.Conv2d(20, 20, 5)

           def forward(self, x):
               x = F.relu(self.conv1(x))
               return F.relu(self.conv2(x))

   Submodules assigned in this way will be registered, and will have their
   parameters converted too when you call :meth:`to`, etc.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   Initializes internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: unpool


   .. py:attribute:: conv_block1


   .. py:attribute:: conv_block2


   .. py:attribute:: conv_block3


   .. py:attribute:: conv_block4


   .. py:attribute:: conv_block5


   .. py:attribute:: conv_block6


   .. py:attribute:: conv_block7


   .. py:attribute:: deconv_block8


   .. py:attribute:: unpool_block9


   .. py:attribute:: deconv_block10


   .. py:attribute:: unpool_block11


   .. py:attribute:: deconv_block12


   .. py:attribute:: unpool_block13


   .. py:attribute:: deconv_block14


   .. py:attribute:: unpool_block15


   .. py:attribute:: deconv_block16


   .. py:attribute:: unpool_block17


   .. py:attribute:: deconv_block18


   .. py:attribute:: seg_score19


   .. py:method:: forward(x)

      Same as :meth:`torch.nn.Module.forward()`.

      Args:
          *args: Whatever you decide to pass into the forward method.
          **kwargs: Keyword arguments are also possible.

      Return:
          Your model's output



   .. py:method:: init_vgg16_params(vgg16, copy_fc8=True)


   .. py:method:: load()

      This is just a no-op load method. 



.. py:class:: TorchPatchDeConvNetSkip(n_classes=4, learned_billinear=False, clip=0.1, class_weights=None)

   Bases: :py:obj:`NNModule`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing to nest them in
   a tree structure. You can assign the submodules as regular attributes::

       import torch.nn as nn
       import torch.nn.functional as F

       class Model(nn.Module):
           def __init__(self):
               super().__init__()
               self.conv1 = nn.Conv2d(1, 20, 5)
               self.conv2 = nn.Conv2d(20, 20, 5)

           def forward(self, x):
               x = F.relu(self.conv1(x))
               return F.relu(self.conv2(x))

   Submodules assigned in this way will be registered, and will have their
   parameters converted too when you call :meth:`to`, etc.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   Initializes internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: unpool


   .. py:attribute:: conv_block1


   .. py:attribute:: conv_block2


   .. py:attribute:: conv_block3


   .. py:attribute:: conv_block4


   .. py:attribute:: conv_block5


   .. py:attribute:: conv_block6


   .. py:attribute:: conv_block7


   .. py:attribute:: deconv_block8


   .. py:attribute:: unpool_block9


   .. py:attribute:: deconv_block10


   .. py:attribute:: unpool_block11


   .. py:attribute:: deconv_block12


   .. py:attribute:: unpool_block13


   .. py:attribute:: deconv_block14


   .. py:attribute:: unpool_block15


   .. py:attribute:: deconv_block16


   .. py:attribute:: unpool_block17


   .. py:attribute:: deconv_block18


   .. py:attribute:: seg_score19


   .. py:method:: forward(x)

      Same as :meth:`torch.nn.Module.forward()`.

      Args:
          *args: Whatever you decide to pass into the forward method.
          **kwargs: Keyword arguments are also possible.

      Return:
          Your model's output



   .. py:method:: init_vgg16_params(vgg16, copy_fc8=True)


   .. py:method:: load()

      This is just a no-op load method. 



.. py:class:: TorchSectionDeConvNet(n_classes=4, learned_billinear=False, clip=0.1, class_weights=False)

   Bases: :py:obj:`NNModule`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing to nest them in
   a tree structure. You can assign the submodules as regular attributes::

       import torch.nn as nn
       import torch.nn.functional as F

       class Model(nn.Module):
           def __init__(self):
               super().__init__()
               self.conv1 = nn.Conv2d(1, 20, 5)
               self.conv2 = nn.Conv2d(20, 20, 5)

           def forward(self, x):
               x = F.relu(self.conv1(x))
               return F.relu(self.conv2(x))

   Submodules assigned in this way will be registered, and will have their
   parameters converted too when you call :meth:`to`, etc.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   Initializes internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: unpool


   .. py:attribute:: conv_block1


   .. py:attribute:: conv_block2


   .. py:attribute:: conv_block3


   .. py:attribute:: conv_block4


   .. py:attribute:: conv_block5


   .. py:attribute:: conv_block6


   .. py:attribute:: conv_block7


   .. py:attribute:: deconv_block8


   .. py:attribute:: unpool_block9


   .. py:attribute:: deconv_block10


   .. py:attribute:: unpool_block11


   .. py:attribute:: deconv_block12


   .. py:attribute:: unpool_block13


   .. py:attribute:: deconv_block14


   .. py:attribute:: unpool_block15


   .. py:attribute:: deconv_block16


   .. py:attribute:: unpool_block17


   .. py:attribute:: deconv_block18


   .. py:attribute:: seg_score19


   .. py:method:: forward(x)

      Same as :meth:`torch.nn.Module.forward()`.

      Args:
          *args: Whatever you decide to pass into the forward method.
          **kwargs: Keyword arguments are also possible.

      Return:
          Your model's output



   .. py:method:: init_vgg16_params(vgg16, copy_fc8=True)


   .. py:method:: load()

      This is just a no-op load method. 



.. py:class:: TorchSectionDeConvNetSkip(n_classes=4, learned_billinear=False, clip=0.1, class_weights=None)

   Bases: :py:obj:`NNModule`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing to nest them in
   a tree structure. You can assign the submodules as regular attributes::

       import torch.nn as nn
       import torch.nn.functional as F

       class Model(nn.Module):
           def __init__(self):
               super().__init__()
               self.conv1 = nn.Conv2d(1, 20, 5)
               self.conv2 = nn.Conv2d(20, 20, 5)

           def forward(self, x):
               x = F.relu(self.conv1(x))
               return F.relu(self.conv2(x))

   Submodules assigned in this way will be registered, and will have their
   parameters converted too when you call :meth:`to`, etc.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   Initializes internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: unpool


   .. py:attribute:: conv_block1


   .. py:attribute:: conv_block2


   .. py:attribute:: conv_block3


   .. py:attribute:: conv_block4


   .. py:attribute:: conv_block5


   .. py:attribute:: conv_block6


   .. py:attribute:: conv_block7


   .. py:attribute:: deconv_block8


   .. py:attribute:: unpool_block9


   .. py:attribute:: deconv_block10


   .. py:attribute:: unpool_block11


   .. py:attribute:: deconv_block12


   .. py:attribute:: unpool_block13


   .. py:attribute:: deconv_block14


   .. py:attribute:: unpool_block15


   .. py:attribute:: deconv_block16


   .. py:attribute:: unpool_block17


   .. py:attribute:: deconv_block18


   .. py:attribute:: seg_score19


   .. py:method:: forward(x)

      Same as :meth:`torch.nn.Module.forward()`.

      Args:
          *args: Whatever you decide to pass into the forward method.
          **kwargs: Keyword arguments are also possible.

      Return:
          Your model's output



   .. py:method:: init_vgg16_params(vgg16, copy_fc8=True)


   .. py:method:: load()

      This is just a no-op load method.