Method __init__

diff2flow/models/unet/attention.py:285–317

(self, in_channels, n_heads, d_head,
                 depth=1, dropout=0., context_dim=None,
                 disable_self_attn=False, use_linear=False,
                 use_checkpoint=True)

    NEW: use_linear for more efficiency instead of the 1x1 convs
    """
    def __init__(self, in_channels, n_heads, d_head,
                 depth=1, dropout=0., context_dim=None,
                 disable_self_attn=False, use_linear=False,
                 use_checkpoint=True):
        super().__init__()
        if exists(context_dim) and not isinstance(context_dim, list):
            context_dim = [context_dim]
        self.in_channels = in_channels
        inner_dim = n_heads * d_head
        self.norm = Normalize(in_channels)
        if not use_linear:
            self.proj_in = nn.Conv2d(in_channels,
                                     inner_dim,
                                     kernel_size=1,
                                     stride=1,
                                     padding=0)
        else:
            self.proj_in = nn.Linear(in_channels, inner_dim)

        self.transformer_blocks = nn.ModuleList(
            [BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim[d],
                                   disable_self_attn=disable_self_attn, checkpoint=use_checkpoint)
                for d in range(depth)]
        )
        if not use_linear:
            self.proj_out = zero_module(nn.Conv2d(inner_dim,
                                                  in_channels,
                                                  kernel_size=1,
                                                  stride=1,
                                                  padding=0))
        else:
            self.proj_out = zero_module(nn.Linear(in_channels, inner_dim))
        self.use_linear = use_linear

    def forward(self, x, context=None):
        # note: if no context is given, cross-attention defaults to self-attention