from torch import nn

from .swin_transformer import SwinTransformer


def to_2tuple(x):
    from itertools import repeat
    import collections.abc
    if isinstance(x, collections.abc.Iterable):
        return x
    return tuple(repeat(x, 2))


class ConvStem(nn.Module):
    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=768, norm_layer=None, flatten=True):
        super().__init__()

        assert patch_size == 4
        assert embed_dim % 8 == 0

        img_size = to_2tuple(img_size)
        patch_size = to_2tuple(patch_size)
        self.img_size = img_size
        self.patch_size = patch_size
        self.grid_size = (img_size[0] // patch_size[0], img_size[1] // patch_size[1])
        self.num_patches = self.grid_size[0] * self.grid_size[1]
        self.flatten = flatten

        stem = []
        input_dim, output_dim = 3, embed_dim // 8
        for l in range(2):
            stem.append(nn.Conv2d(input_dim, output_dim, kernel_size=3, stride=2, padding=1, bias=False))
            stem.append(nn.BatchNorm2d(output_dim))
            stem.append(nn.ReLU(inplace=True))
            input_dim = output_dim
            output_dim *= 2
        stem.append(nn.Conv2d(input_dim, embed_dim, kernel_size=1))
        self.proj = nn.Sequential(*stem)

        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()

    def forward(self, x):
        B, C, H, W = x.shape
        assert H == self.img_size[0] and W == self.img_size[1], \
            f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
        x = self.proj(x)
        if self.flatten:
            x = x.flatten(2).transpose(1, 2)  # BCHW -> BNC
        x = self.norm(x)
        return x


def CTransPath(
    num_classes: int,
    drop_rate: float = 0.,
    drop_path_rate: float = 0.1,
) -> nn.Module:
    model = SwinTransformer(patch_size=4, window_size=7, embed_dim=96, depths=(2, 2, 6, 2), num_heads=(3, 6, 12, 24), embed_layer=ConvStem, drop_rate=drop_rate, drop_path_rate=drop_path_rate)
    if num_classes == 0:
        model.head = nn.Identity()
    else:
        model.head = nn.Linear(768, num_classes)

    return model