ISubGVQA.datasets.scene_graph
=============================

.. py:module:: ISubGVQA.datasets.scene_graph


Classes
-------

.. autoapisummary::

   ISubGVQA.datasets.scene_graph.GQASceneGraphs


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

.. py:class:: GQASceneGraphs

   A class to handle GQA Scene Graphs for Visual Question Answering (VQA).
   Attributes:
   -----------
   tokenizer : spacy.tokenizer
       Tokenizer for processing text data.
   vocab_sg : torchtext.vocab.Vocab
       Vocabulary for scene graph encoding.
   vectors : torch.Tensor
       Pre-trained GloVe vectors for the vocabulary.
   scene_graphs_train : dict
       Scene graphs for the training set.
   scene_graphs_valid : dict
       Scene graphs for the validation set.
   scene_graphs_testdev : dict
       Scene graphs for the test development set.
   scene_graphs : dict
       Combined scene graphs from training, validation, and test development sets.
   rel_mapping : dict
       Mapping for relationships.
   obj_mapping : dict
       Mapping for objects.
   attr_mapping : dict
       Mapping for attributes.
   Methods:
   --------
   __init__():
       Initializes the GQASceneGraphs object, builds the vocabulary, and loads scene graphs.
   query_and_translate(queryID: str):
       Queries and translates a scene graph based on the given query ID.
   build_scene_graph_encoding_vocab():
       Builds the vocabulary for scene graph encoding using pre-defined text lists and GloVe vectors.
   convert_one_gqa_scene_graph(sg_this: dict):
       Converts a single GQA scene graph into a PyTorch Geometric data format.


   .. py:attribute:: tokenizer


   .. py:attribute:: scene_graphs_train


   .. py:attribute:: scene_graphs_valid


   .. py:attribute:: scene_graphs_testdev


   .. py:attribute:: scene_graphs


   .. py:attribute:: rel_mapping


   .. py:attribute:: obj_mapping


   .. py:attribute:: attr_mapping


   .. py:method:: query_and_translate(queryID: str)


   .. py:method:: build_scene_graph_encoding_vocab()


   .. py:method:: convert_one_gqa_scene_graph(sg_this)