src/fairseq/fairseq/modules/longformer_multihead_attention.py [136:180]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        nn.init.xavier_uniform_(self.out_proj.weight)

        if self.out_proj.bias is not None:
            nn.init.constant_(self.out_proj.bias, 0.)
        if self.bias_k is not None:
            nn.init.xavier_normal_(self.bias_k)
        if self.bias_v is not None:
            nn.init.xavier_normal_(self.bias_v)

    def forward(
        self,
        query,
        key: Optional[Tensor],
        value: Optional[Tensor],
        key_padding_mask: Optional[Tensor] = None,
        incremental_state: Optional[Dict[str, Dict[str, Optional[Tensor]]]] = None,
        need_weights: bool = True,
        static_kv: bool = False,
        attn_mask: Optional[Tensor] = None,
        before_softmax: bool = False,
        need_head_weights: bool = False,
    ) -> Tuple[Tensor, Optional[Tensor]]:
        """Input shape: Time x Batch x Channel

        Args:
            key_padding_mask (ByteTensor, optional): mask to exclude
                keys that are pads, of shape `(batch, src_len)`, where
                padding elements are indicated by 1s.
            need_weights (bool, optional): return the attention weights,
                averaged over heads (default: False).
            attn_mask (ByteTensor, optional): typically used to
                implement causal attention, where the mask prevents the
                attention from looking forward in time (default: None).
            before_softmax (bool, optional): return the raw attention
                weights and values before the attention softmax.
            need_head_weights (bool, optional): return the attention
                weights for each head. Implies *need_weights*. Default:
                return the average attention weights over all heads.
        """
        if need_head_weights:
            need_weights = True

        tgt_len, bsz, embed_dim = query.size()
        assert embed_dim == self.embed_dim
        assert list(query.size()) == [tgt_len, bsz, embed_dim]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/fairseq/fairseq/modules/multihead_attention.py [98:141]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        nn.init.xavier_uniform_(self.out_proj.weight)
        if self.out_proj.bias is not None:
            nn.init.constant_(self.out_proj.bias, 0.)
        if self.bias_k is not None:
            nn.init.xavier_normal_(self.bias_k)
        if self.bias_v is not None:
            nn.init.xavier_normal_(self.bias_v)

    def forward(
        self,
        query,
        key: Optional[Tensor],
        value: Optional[Tensor],
        key_padding_mask: Optional[Tensor] = None,
        incremental_state: Optional[Dict[str, Dict[str, Optional[Tensor]]]] = None,
        need_weights: bool = True,
        static_kv: bool = False,
        attn_mask: Optional[Tensor] = None,
        before_softmax: bool = False,
        need_head_weights: bool = False,
    ) -> Tuple[Tensor, Optional[Tensor]]:
        """Input shape: Time x Batch x Channel

        Args:
            key_padding_mask (ByteTensor, optional): mask to exclude
                keys that are pads, of shape `(batch, src_len)`, where
                padding elements are indicated by 1s.
            need_weights (bool, optional): return the attention weights,
                averaged over heads (default: False).
            attn_mask (ByteTensor, optional): typically used to
                implement causal attention, where the mask prevents the
                attention from looking forward in time (default: None).
            before_softmax (bool, optional): return the raw attention
                weights and values before the attention softmax.
            need_head_weights (bool, optional): return the attention
                weights for each head. Implies *need_weights*. Default:
                return the average attention weights over all heads.
        """
        if need_head_weights:
            need_weights = True

        tgt_len, bsz, embed_dim = query.size()
        assert embed_dim == self.embed_dim
        assert list(query.size()) == [tgt_len, bsz, embed_dim]
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -