Method forward

modules/commons/common_layers.py:236–420

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 a

(
            self,
            query, key, value,
            key_padding_mask=None,
            incremental_state=None,
            need_weights=True,
            static_kv=False,
            attn_mask=None,
            before_softmax=False,
            need_head_weights=False,
            enc_dec_attn_constraint_mask=None,
            reset_attn_weight=None
    )

            nn.init.xavier_normal_(self.bias_v)

    def forward(
            self,
            query, key, value,
            key_padding_mask=None,
            incremental_state=None,
            need_weights=True,
            static_kv=False,
            attn_mask=None,
            before_softmax=False,
            need_head_weights=False,
            enc_dec_attn_constraint_mask=None,
            reset_attn_weight=None
    ):
        """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]

        if self.enable_torch_version and incremental_state is None and not static_kv and reset_attn_weight is None:
            if self.qkv_same_dim:
                return F.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,
                                                      self.training, key_padding_mask, need_weights,
                                                      attn_mask)
            else:
                return F.multi_head_attention_forward(query, key, value,
                                                      self.embed_dim, self.num_heads,
                                                      torch.empty([0]),
                                                      self.in_proj_bias, self.bias_k, self.bias_v,
                                                      self.add_zero_attn, self.dropout,
                                                      self.out_proj.weight, self.out_proj.bias,
                                                      self.training, key_padding_mask, need_weights,
                                                      attn_mask, use_separate_proj_weight=True,
                                                      q_proj_weight=self.q_proj_weight,
                                                      k_proj_weight=self.k_proj_weight,