Method __init__

src/croco/models/blocks.py:270–312

(
        self,
        dim,
        num_heads,
        mlp_ratio=4.0,
        qkv_bias=False,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        act_layer=nn.GELU,
        norm_layer=nn.LayerNorm,
        norm_mem=True,
        rope=None,
    )

class DecoderBlock(nn.Module):

    def __init__(
        self,
        dim,
        num_heads,
        mlp_ratio=4.0,
        qkv_bias=False,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        act_layer=nn.GELU,
        norm_layer=nn.LayerNorm,
        norm_mem=True,
        rope=None,
    ):
        super().__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention(
            dim,
            rope=rope,
            num_heads=num_heads,
            qkv_bias=qkv_bias,
            attn_drop=attn_drop,
            proj_drop=drop,
        )
        self.cross_attn = CrossAttention(
            dim,
            rope=rope,
            num_heads=num_heads,
            qkv_bias=qkv_bias,
            attn_drop=attn_drop,
            proj_drop=drop,
        )
        self.drop_path = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
        self.norm2 = norm_layer(dim)
        self.norm3 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(
            in_features=dim,
            hidden_features=mlp_hidden_dim,
            act_layer=act_layer,
            drop=drop,
        )
        self.norm_y = norm_layer(dim) if norm_mem else nn.Identity()

    def forward(self, x, y, xpos, ypos):
        x = x + self.drop_path(self.attn(self.norm1(x), xpos))