# References:
#   https://github.com/facebookresearch/dino/blob/master/vision_transformer.py
#   https://github.com/rwightman/pytorch-image-models/tree/master/timm/layers/mlp.py


from typing import Callable, List, Optional


from torch import Tensor, nn

from hf_src.utils import cat_keep_shapes, uncat_with_shapes


class ListForwardMixin(object):
    def forward(self, x: Tensor):
        raise NotImplementedError

    def forward_list(self, x_list: List[Tensor]) -> List[Tensor]:
        x_flat, shapes, num_tokens = cat_keep_shapes(x_list)
        x_flat = self.forward(x_flat)
        return uncat_with_shapes(x_flat, shapes, num_tokens)


class Mlp(nn.Module, ListForwardMixin):
    def __init__(
        self,
        in_features: int,
        hidden_features: Optional[int] = None,
        out_features: Optional[int] = None,
        act_layer: Callable[..., nn.Module] = nn.GELU,
        drop: float = 0.0,
        bias: bool = True,
        device=None,
    ) -> None:
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features, bias=bias, device=device)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features, bias=bias, device=device)
        self.drop = nn.Dropout(drop)

    def forward(self, x: Tensor) -> Tensor:
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x