crosslingual_dataset
====================

.. py:module:: topmost.data.crosslingual_dataset



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



.. autoapisummary::


   topmost.data.crosslingual_dataset._BilingualDataset


   topmost.data.crosslingual_dataset.CrosslingualDataset





.. py:class:: _BilingualDataset(bow_en, bow_cn)

   Bases: :py:obj:`torch.utils.data.Dataset`


   .. py:attribute:: bow_en


   .. py:attribute:: bow_cn


   .. py:attribute:: bow_size_en


   .. py:attribute:: bow_size_cn


   .. py:method:: __len__()


   .. py:method:: __getitem__(index)


.. py:class:: CrosslingualDataset(dataset_dir, lang1, lang2, dict_path, device='cpu', batch_size=200, as_tensor=True)

   .. py:attribute:: batch_size
      :value: 200



   .. py:attribute:: train_size_en
      :value: 0



   .. py:attribute:: train_size_cn
      :value: 0



   .. py:attribute:: vocab_size_en
      :value: 0



   .. py:attribute:: vocab_size_cn
      :value: 0



   .. py:attribute:: pretrained_WE_en


   .. py:attribute:: pretrained_WE_cn


   .. py:attribute:: Map_en2cn


   .. py:attribute:: Map_cn2en


   .. py:method:: move_to_device(bow, device)


   .. py:method:: read_data(dataset_dir, lang)


   .. py:method:: parse_dictionary(dict_path)


   .. py:method:: get_Map(trans_matrix, bow)