Method forward

architecture/attention_processor.py:556–600

r""" The forward method of the `Attention` class. Args: hidden_states (`torch.Tensor`): The hidden states of the query. encoder_hidden_states (`torch.Tensor`, *optional*): The hidden states of the encoder. attention

(
        self,
        hidden_states: torch.Tensor,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        **cross_attention_kwargs,
    )

            return self.processor

    def forward(
        self,
        hidden_states: torch.Tensor,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        **cross_attention_kwargs,
    ) -> torch.Tensor:
        r"""
        The forward method of the `Attention` class.

        Args:
            hidden_states (`torch.Tensor`):
                The hidden states of the query.
            encoder_hidden_states (`torch.Tensor`, *optional*):
                The hidden states of the encoder.
            attention_mask (`torch.Tensor`, *optional*):
                The attention mask to use. If `None`, no mask is applied.
            **cross_attention_kwargs:
                Additional keyword arguments to pass along to the cross attention.

        Returns:
            `torch.Tensor`: The output of the attention layer.
        """
        # The `Attention` class can call different attention processors / attention functions
        # here we simply pass along all tensors to the selected processor class
        # For standard processors that are defined here, `**cross_attention_kwargs` is empty

        attn_parameters = set(inspect.signature(self.processor.__call__).parameters.keys())
        quiet_attn_parameters = {"ip_adapter_masks", "ip_hidden_states"}
        unused_kwargs = [
            k for k, _ in cross_attention_kwargs.items() if k not in attn_parameters and k not in quiet_attn_parameters
        ]
        if len(unused_kwargs) > 0:
            logger.warning(
                f"cross_attention_kwargs {unused_kwargs} are not expected by {self.processor.__class__.__name__} and will be ignored."
            )
        cross_attention_kwargs = {k: w for k, w in cross_attention_kwargs.items() if k in attn_parameters}

        return self.processor(
            self,
            hidden_states,
            encoder_hidden_states=encoder_hidden_states,
            attention_mask=attention_mask,
            **cross_attention_kwargs,
        )

    def batch_to_head_dim(self, tensor: torch.Tensor) -> torch.Tensor:
        r"""