from functools import partial
from itertools import repeat
from typing import Iterable
import math
import torch.nn as nn
import torch.nn.functional as F


__all__ = [
    "get_abs_pos",
    "PatchEmbed",
    "Mlp",
    "DropPath",
]


def to_2tuple(x):
    if isinstance(x, Iterable) and not isinstance(x, str):
        return tuple(x)
    return tuple(repeat(x, 2))


def get_abs_pos(abs_pos, has_cls_token, hw):
    """
    Calculate absolute positional embeddings. If needed, resize embeddings and remove cls_token
        dimension for the original embeddings.
    Args:
        abs_pos (Tensor): absolute positional embeddings with (1, num_position, C).
        has_cls_token (bool): If true, has 1 embedding in abs_pos for cls token.
        hw (Tuple): size of input image tokens.

    Returns:
        Absolute positional embeddings after processing with shape (1, H, W, C)
    """
    h, w = hw
    if has_cls_token:
        abs_pos = abs_pos[:, 1:]
    xy_num = abs_pos.shape[1]
    size = int(math.sqrt(xy_num))
    assert size * size == xy_num

    if size != h or size != w:
        new_abs_pos = F.interpolate(
            abs_pos.reshape(1, size, size, -1).permute(0, 3, 1, 2),
            size=(h, w),
            mode="bicubic",
            align_corners=False,
        )

        return new_abs_pos.permute(0, 2, 3, 1)
    else:
        return abs_pos.reshape(1, h, w, -1)


def drop_path(
    x, drop_prob: float = 0.0, training: bool = False, scale_by_keep: bool = True
):
    if drop_prob == 0.0 or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (
        x.ndim - 1
    )  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
    if keep_prob > 0.0 and scale_by_keep:
        random_tensor.div_(keep_prob)
    return x * random_tensor


class PatchEmbed(nn.Module):
    """
    Image to Patch Embedding.
    """

    def __init__(
        self,
        kernel_size=(16, 16),
        stride=(16, 16),
        padding=(0, 0),
        in_chans=3,
        embed_dim=768,
    ):
        """
        Args:
            kernel_size (Tuple): kernel size of the projection layer.
            stride (Tuple): stride of the projection layer.
            padding (Tuple): padding size of the projection layer.
            in_chans (int): Number of input image channels.
            embed_dim (int):  embed_dim (int): Patch embedding dimension.
        """
        super().__init__()

        self.proj = nn.Conv2d(
            in_chans, embed_dim, kernel_size=kernel_size, stride=stride, padding=padding
        )

    def forward(self, x):
        x = self.proj(x)
        # B C H W -> B H W C
        x = x.permute(0, 2, 3, 1)
        return x


class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks)."""

    def __init__(self, drop_prob: float = 0.0, scale_by_keep: bool = True):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob
        self.scale_by_keep = scale_by_keep

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training, self.scale_by_keep)

    def extra_repr(self):
        return f"drop_prob={round(self.drop_prob,3):0.3f}"


class Mlp(nn.Module):
    def __init__(
        self,
        in_features,
        hidden_features=None,
        out_features=None,
        act_layer=nn.GELU,
        norm_layer=None,
        bias=True,
        drop=0.0,
        use_conv=False,
    ):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        bias = to_2tuple(bias)
        drop_probs = to_2tuple(drop)
        linear_layer = partial(nn.Conv2d, kernel_size=1) if use_conv else nn.Linear

        self.fc1 = linear_layer(in_features, hidden_features, bias=bias[0])
        self.act = act_layer()
        self.drop1 = nn.Dropout(drop_probs[0])
        self.norm = (
            norm_layer(hidden_features) if norm_layer is not None else nn.Identity()
        )
        self.fc2 = linear_layer(hidden_features, out_features, bias=bias[1])
        self.drop2 = nn.Dropout(drop_probs[1])

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop1(x)
        x = self.norm(x)
        x = self.fc2(x)
        x = self.drop2(x)
        return x