:py:mod:`ggt.models`
====================

.. py:module:: ggt.models


Submodules
----------
.. toctree::
   :titlesonly:
   :maxdepth: 1

   ggt/index.rst
   ggt_no_gcov/index.rst
   vgg/index.rst
   vgg16_w_stn_at_drp/index.rst
   vgg16_w_stn_drp/index.rst
   vgg16_w_stn_drp_2/index.rst
   vgg16_w_stn_oc_drp/index.rst


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

Classes
~~~~~~~

.. autoapisummary::

   ggt.models.vgg16_w_stn_drp
   ggt.models.vgg16_w_stn_drp_2
   ggt.models.vgg16_w_stn_at_drp
   ggt.models.vgg16_w_stn_oc_drp



Functions
~~~~~~~~~

.. autoapisummary::

   ggt.models.vgg16
   ggt.models.model_stats
   ggt.models.model_factory
   ggt.models.save_trained_model



.. py:function:: vgg16(cutout_size, channels, n_out=1, pretrained=True)


.. py:class:: vgg16_w_stn_drp(cutout_size, channels, n_out=1, pretrained=True, dropout=False, dropout_rate=0.5)

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

   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(Model, self).__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.

   .. py:method:: spatial_transform(x)


   .. py:method:: forward(x)



.. py:class:: vgg16_w_stn_drp_2(cutout_size, channels, n_out=1, pretrained=True, dropout=False, dropout_rate=0.5)

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

   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(Model, self).__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.

   .. py:method:: spatial_transform(x)


   .. py:method:: forward(x)



.. py:class:: vgg16_w_stn_at_drp(cutout_size, channels, n_out=1, pretrained=True, dropout=False, dropout_rate=0.5)

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

   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(Model, self).__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.

   .. py:method:: spatial_transform(x)


   .. py:method:: forward(x)



.. py:class:: vgg16_w_stn_oc_drp(cutout_size, channels, n_out=1, pretrained=True, dropout=False, dropout_rate=0.5)

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

   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(Model, self).__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.

   .. py:method:: spatial_transform(x)


   .. py:method:: forward(x)



.. py:function:: model_stats(model)


.. py:function:: model_factory(modeltype)


.. py:function:: save_trained_model(model, slug)