:py:mod:`medcat.utils.meta_cat.models`
======================================

.. py:module:: medcat.utils.meta_cat.models


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

Classes
~~~~~~~

.. autoapisummary::

   medcat.utils.meta_cat.models.LSTM
   medcat.utils.meta_cat.models.BertForMetaAnnotation




Attributes
~~~~~~~~~~

.. autoapisummary::

   medcat.utils.meta_cat.models.logger


.. py:data:: logger

   

.. py:class:: LSTM(embeddings, config)


   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().__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.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   .. py:method:: __init__(embeddings, config)

      Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:method:: forward(input_ids, center_positions, attention_mask = None, ignore_cpos = False)



.. py:class:: BertForMetaAnnotation(config)


   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().__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.

   .. note::
       As per the example above, an ``__init__()`` call to the parent class
       must be made before assignment on the child.

   :ivar training: Boolean represents whether this module is in training or
                   evaluation mode.
   :vartype training: bool

   .. py:attribute:: _keys_to_ignore_on_load_unexpected
      :type: List[str]
      :value: ['pooler']

      

   .. py:method:: __init__(config)

      Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:method:: forward(input_ids = None, attention_mask = None, token_type_ids = None, position_ids = None, head_mask = None, inputs_embeds = None, labels = None, center_positions = [], ignore_cpos = None, output_attentions = None, output_hidden_states = None, return_dict = None)

      labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
          Labels for computing the token classification loss. Indices should be in ``[0, ..., config.num_labels -
          1]``.

      :param input_ids: The input IDs. Defaults to None.
      :type input_ids: Optional[torch.LongTensor]
      :param attention_mask: The attention mask. Defaults to None.
      :type attention_mask: Optional[torch.FloatTensor]
      :param token_type_ids: Type IDs of the tokens. Defaults to None.
      :type token_type_ids: Optional[torch.LongTensor]
      :param position_ids: Position IDs. Defaults to None.
      :type position_ids: Optional[torch.LongTensor]
      :param head_mask: Head mask. Defaults to None.
      :type head_mask: Optional[torch.FloatTensor]
      :param inputs_embeds: Input embeddings. Defaults to None.
      :type inputs_embeds: Optional[torch.FloatTensor]
      :param labels: Labels. Defaults to None.
      :type labels: Optional[torch.LongTensor]
      :param center_positions: Cennter positions. Defaults to None.
      :type center_positions: Optional[Any]
      :param output_attentions: Output attentions. Defaults to None.
      :type output_attentions: Optional[bool]
      :param ignore_cpos: If center positions are to be ignored.
      :param output_hidden_states: Output hidden states. Defaults to None.
      :type output_hidden_states: Optional[bool]
      :param return_dict: Whether to return a dict. Defaults to None.
      :type return_dict: Optional[bool]

      :Returns: **TokenClassifierOutput** -- The token classifier output.