pyiqa.archs.inception
=====================

.. py:module:: pyiqa.archs.inception

.. autoapi-nested-parse::

   File from: https://github.com/mseitzer/pytorch-fid









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

.. py:data:: FID_WEIGHTS_URL

.. py:class:: InceptionV3(output_blocks=(DEFAULT_BLOCK_INDEX, ), resize_input=True, normalize_input=True, requires_grad=False, use_fid_inception=True)

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


   Pretrained InceptionV3 network returning feature maps


   .. py:method:: forward(inp, resize_input=False, normalize_input=False)

      Get Inception feature maps
      :param inp: Input tensor of shape Bx3xHxW. Values are expected to be in
                  range (0, 1)
      :type inp: torch.autograd.Variable

      :returns: * *List of torch.autograd.Variable, corresponding to the selected output*
                * *block, sorted ascending by index*



.. py:function:: fid_inception_v3()

   Build pretrained Inception model for FID computation
   The Inception model for FID computation uses a different set of weights
   and has a slightly different structure than torchvision's Inception.
   This method first constructs torchvision's Inception and then patches the
   necessary parts that are different in the FID Inception model.


.. py:class:: FIDInceptionA(in_channels, pool_features)

   Bases: :py:obj:`torchvision.models.inception.InceptionA`


   InceptionA block patched for FID computation


   .. py:method:: forward(x)


.. py:class:: FIDInceptionC(in_channels, channels_7x7)

   Bases: :py:obj:`torchvision.models.inception.InceptionC`


   InceptionC block patched for FID computation


   .. py:method:: forward(x)


.. py:class:: FIDInceptionE_1(in_channels)

   Bases: :py:obj:`torchvision.models.inception.InceptionE`


   First InceptionE block patched for FID computation


   .. py:method:: forward(x)


.. py:class:: FIDInceptionE_2(in_channels)

   Bases: :py:obj:`torchvision.models.inception.InceptionE`


   Second InceptionE block patched for FID computation


   .. py:method:: forward(x)