ISubGVQA.models.question_decoder
================================

.. py:module:: ISubGVQA.models.question_decoder


Classes
-------

.. autoapisummary::

   ISubGVQA.models.question_decoder.QuestionDecoder


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

.. py:class:: QuestionDecoder(n_instructions, ninp, nhead, nhid, nlayers, dropout=0.1)

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


   .. py:attribute:: model_type
      :value: 'Transformer'



   .. py:attribute:: num_queries


   .. py:attribute:: query_embed


   .. py:attribute:: coarse_decoder


   .. py:method:: generate_square_subsequent_mask(sz)

      Generate a square mask for the sequence. The masked positions are filled with float('-inf').
      Unmasked positions are filled with float(0.0).
      https://pytorch.org/docs/stable/_modules/torch/nn/modules/transformer.html#Transformer.generate_square_subsequent_mask



   .. py:method:: forward(memory)