TransformerEncoderLayer 标准的transformer encoder层

class TransformerEncoderLayer(Module):
    r"""TransformerEncoderLayer is made up of self-attn and feedforward network.
    This standard encoder layer is based on the paper "Attention Is All You Need".
    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
    Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
    Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
    in a different way during application.

    Args:
        d_model: the number of expected features in the input (required).
        nhead: the number of heads in the multiheadattention models (required).
        dim_feedforward: the dimension of the feedforward network model (default=2048).
        dropout: the dropout value (default=0.1).
        activation: the activation function of the intermediate layer, can be a string
            ("relu" or "gelu") or a unary callable. Default: relu
        layer_norm_eps: the eps value in layer normalization components (default=1e-5).
        batch_first: If ``True``, then the input and output tensors are provided
            as (batch, seq, feature). Default: ``False``.
        norm_first: if ``True``, layer norm is done prior to attention and feedforward
            operations, respectivaly. Otherwise it's done after. Default: ``False`` (after).

    Examples::
        >>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
        >>> src = torch.rand(10, 32, 512)
        >>> out = encoder_layer(src)

    Alternatively, when ``batch_first`` is ``True``:
        >>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8, batch_first=True)
        >>> src = torch.rand(32, 10, 512)
        >>> out = encoder_layer(src)
    """
    __constants__ = ['batch_first', 'norm_first']

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation=F.relu,
                 layer_norm_eps=1e-5, batch_first=False, norm_first=False,
                 device=None, dtype=None) -> None:
        factory_kwargs = {'device': device, 'dtype': dtype}
        super(TransformerEncoderLayer, self).__init__()
        self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout, batch_first=batch_first,
                                            **factory_kwargs)
        # Implementation of Feedforward model
        self.linear1 = Linear(d_model, dim_feedforward, **factory_kwargs)
        self.dropout = Dropout(dropout)
        self.linear2 = Linear(dim_feedforward, d_model, **factory_kwargs)

        self.norm_first = norm_first
        self.norm1 = LayerNorm(d_model, eps=layer_norm_eps, **factory_kwargs)
        self.norm2 = LayerNorm(d_model, eps=layer_norm_eps, **factory_kwargs)
        self.dropout1 = Dropout(dropout)
        self.dropout2 = Dropout(dropout)

        # Legacy string support for activation function.
        if isinstance(activation, str):
            self.activation = _get_activation_fn(activation)
        else:
            self.activation = activation

    def __setstate__(self, state):
        if 'activation' not in state:
            state['activation'] = F.relu
        super(TransformerEncoderLayer, self).__setstate__(state)

    def forward(self, src: Tensor, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None) -> Tensor:
        r"""Pass the input through the encoder layer.

        Args:
            src: the sequence to the encoder layer (required).
            src_mask: the mask for the src sequence (optional).
            src_key_padding_mask: the mask for the src keys per batch (optional).

        Shape:
            see the docs in Transformer class.
        """

        # see Fig. 1 of https://arxiv.org/pdf/2002.04745v1.pdf

        x = src
        if self.norm_first:
            x = x + self._sa_block(self.norm1(x), src_mask, src_key_padding_mask)
            x = x + self._ff_block(self.norm2(x))
        else:
            x = self.norm1(x + self._sa_block(x, src_mask, src_key_padding_mask))
            x = self.norm2(x + self._ff_block(x))

        return x

    # self-attention block
    def _sa_block(self, x: Tensor,
                  attn_mask: Optional[Tensor], key_padding_mask: Optional[Tensor]) -> Tensor:
        x = self.self_attn(x, x, x,
                           attn_mask=attn_mask,
                           key_padding_mask=key_padding_mask,
                           need_weights=False)[0]
        return self.dropout1(x)

    # feed forward block
    def _ff_block(self, x: Tensor) -> Tensor:
        x = self.linear2(self.dropout(self.activation(self.linear1(x))))
        return self.dropout2(x)