ISubGVQA.models.mgat_v2_conv
============================

.. py:module:: ISubGVQA.models.mgat_v2_conv


Classes
-------

.. autoapisummary::

   ISubGVQA.models.mgat_v2_conv.MaskingGATv2Conv


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

.. py:class:: MaskingGATv2Conv(in_channels: Union[int, Tuple[int, int]], out_channels: int, heads: int = 1, concat: bool = True, negative_slope: float = 0.2, dropout: float = 0.0, add_self_loops: bool = True, edge_dim: Optional[int] = None, fill_value: Union[float, torch.Tensor, str] = 'mean', bias: bool = True, share_weights: bool = False, masking_threshold: Optional[int] = None, use_instr: bool = False, use_topk: bool = False, concat_instr: bool = False, use_all_instrs: bool = False, sampler_type: str = None, sample_k: int = None, nb_samples: int = 1, alpha=1.0, beta=10.0, tau=1.0, **kwargs)

   Bases: :py:obj:`torch_geometric.nn.conv.MessagePassing`


   .. py:attribute:: _alpha
      :type:  torch_geometric.typing.OptTensor


   .. py:attribute:: in_channels


   .. py:attribute:: out_channels


   .. py:attribute:: heads
      :value: 1



   .. py:attribute:: concat
      :value: True



   .. py:attribute:: negative_slope
      :value: 0.2



   .. py:attribute:: dropout
      :value: 0.0



   .. py:attribute:: add_self_loops
      :value: True



   .. py:attribute:: edge_dim
      :value: None



   .. py:attribute:: fill_value
      :value: 'mean'



   .. py:attribute:: share_weights
      :value: False



   .. py:attribute:: use_instr
      :value: False



   .. py:attribute:: concat_instr
      :value: False



   .. py:attribute:: use_all_instrs
      :value: False



   .. py:attribute:: att


   .. py:attribute:: mask


   .. py:attribute:: masking


   .. py:method:: reset_parameters()


   .. py:method:: forward(x: Union[torch.Tensor, torch_geometric.typing.PairTensor], edge_index: torch_geometric.typing.Adj, batch: Union[torch.Tensor, torch_geometric.typing.PairTensor], edge_attr: torch_geometric.typing.OptTensor = None, instruction: torch_geometric.typing.OptTensor = None, imle_att: torch_geometric.typing.OptTensor = None, return_attention_weights: bool = None, return_masks: bool = None, all_instrs=None)


   .. py:method:: message(x_j: torch.Tensor, x_i: torch.Tensor, edge_attr: torch_geometric.typing.OptTensor, edge_mask, index: torch.Tensor, ptr: torch_geometric.typing.OptTensor, size_i: Optional[int]) -> torch.Tensor


   .. py:method:: __repr__() -> str