Method forward

semantic_sam/modules/attention.py:426–487

r""" Args: query, key, value: map a query and a set of key-value pairs to an output. See "Attention Is All You Need" for more details. key_padding_mask: if provided, specified padding elements in the key will be ignored by the attention. When given a binar

(self, query: Tensor, key: Tensor, value: Tensor, key_padding_mask: Optional[Tensor] = None,
                need_weights: bool = True, attn_mask: Optional[Tensor] = None)

        super(MultiheadAttention, self).__setstate__(state)

    def forward(self, query: Tensor, key: Tensor, value: Tensor, key_padding_mask: Optional[Tensor] = None,
                need_weights: bool = True, attn_mask: Optional[Tensor] = None) -> Tuple[Tensor, Optional[Tensor]]:
        r"""
    Args:
        query, key, value: map a query and a set of key-value pairs to an output.
            See "Attention Is All You Need" for more details.
        key_padding_mask: if provided, specified padding elements in the key will
            be ignored by the attention. When given a binary mask and a value is True,
            the corresponding value on the attention layer will be ignored. When given
            a byte mask and a value is non-zero, the corresponding value on the attention
            layer will be ignored
        need_weights: output attn_output_weights.
        attn_mask: 2D or 3D mask that prevents attention to certain positions. A 2D mask will be broadcasted for all
            the batches while a 3D mask allows to specify a different mask for the entries of each batch.

    Shapes for inputs:
        - query: :math:`(L, N, E)` where L is the target sequence length, N is the batch size, E is
          the embedding dimension.
        - key: :math:`(S, N, E)`, where S is the source sequence length, N is the batch size, E is
          the embedding dimension.
        - value: :math:`(S, N, E)` where S is the source sequence length, N is the batch size, E is
          the embedding dimension.
        - key_padding_mask: :math:`(N, S)` where N is the batch size, S is the source sequence length.
          If a ByteTensor is provided, the non-zero positions will be ignored while the position
          with the zero positions will be unchanged. If a BoolTensor is provided, the positions with the
          value of ``True`` will be ignored while the position with the value of ``False`` will be unchanged.
        - attn_mask: if a 2D mask: :math:`(L, S)` where L is the target sequence length, S is the
          source sequence length.

          If a 3D mask: :math:`(N\cdot\text{num\_heads}, L, S)` where N is the batch size, L is the target sequence
          length, S is the source sequence length. ``attn_mask`` ensure that position i is allowed to attend
          the unmasked positions. If a ByteTensor is provided, the non-zero positions are not allowed to attend
          while the zero positions will be unchanged. If a BoolTensor is provided, positions with ``True``
          is not allowed to attend while ``False`` values will be unchanged. If a FloatTensor
          is provided, it will be added to the attention weight.

    Shapes for outputs:
        - attn_output: :math:`(L, N, E)` where L is the target sequence length, N is the batch size,
          E is the embedding dimension.
        - attn_output_weights: :math:`(N, L, S)` where N is the batch size,
          L is the target sequence length, S is the source sequence length.
        """
        if not self._qkv_same_embed_dim:
            return multi_head_attention_forward(
                query, key, value, self.embed_dim, self.num_heads,
                self.in_proj_weight, self.in_proj_bias,
                self.bias_k, self.bias_v, self.add_zero_attn,
                self.dropout, self.out_proj.weight, self.out_proj.bias,
                training=self.training,
                key_padding_mask=key_padding_mask, need_weights=need_weights,
                attn_mask=attn_mask, use_separate_proj_weight=True,
                q_proj_weight=self.q_proj_weight, k_proj_weight=self.k_proj_weight,
                v_proj_weight=self.v_proj_weight)
        else:
            return multi_head_attention_forward(
                query, key, value, self.embed_dim, self.num_heads,
                self.in_proj_weight, self.in_proj_bias,
                self.bias_k, self.bias_v, self.add_zero_attn,