Class Block

encoders/dinov2/layers/block.py:49–120

class Block(nn.Module):
    def __init__(
        self,
        dim: int,
        num_heads: int,
        mlp_ratio: float = 4.0,
        qkv_bias: bool = False,
        proj_bias: bool = True,
        ffn_bias: bool = True,
        drop: float = 0.0,
        attn_drop: float = 0.0,
        init_values=None,
        drop_path: float = 0.0,
        act_layer: Callable[..., nn.Module] = nn.GELU,
        norm_layer: Callable[..., nn.Module] = nn.LayerNorm,
        attn_class: Callable[..., nn.Module] = Attention,
        ffn_layer: Callable[..., nn.Module] = Mlp,
    ) -> None:
        super().__init__()
        # print(f"biases: qkv: {qkv_bias}, proj: {proj_bias}, ffn: {ffn_bias}")
        self.norm1 = norm_layer(dim)
        self.attn = attn_class(
            dim,
            num_heads=num_heads,
            qkv_bias=qkv_bias,
            proj_bias=proj_bias,
            attn_drop=attn_drop,
            proj_drop=drop,
        )
        self.ls1 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
        self.drop_path1 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()

        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = ffn_layer(
            in_features=dim,
            hidden_features=mlp_hidden_dim,
            act_layer=act_layer,
            drop=drop,
            bias=ffn_bias,
        )
        self.ls2 = LayerScale(dim, init_values=init_values) if init_values else nn.Identity()
        self.drop_path2 = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()

        self.sample_drop_ratio = drop_path

    def forward(self, x: Tensor) -> Tensor:
        def attn_residual_func(x: Tensor) -> Tensor:
            return self.ls1(self.attn(self.norm1(x)))

        def ffn_residual_func(x: Tensor) -> Tensor:
            return self.ls2(self.mlp(self.norm2(x)))

        if self.training and self.sample_drop_ratio > 0.1:
            # the overhead is compensated only for a drop path rate larger than 0.1
            x = drop_add_residual_stochastic_depth(
                x,
                residual_func=attn_residual_func,