import torch
import torch.nn as nn


class GELU(nn.Module):

    def __init__(self, inplace=True):
        super(GELU, self).__init__()
        self.inplace = inplace

    def forward(self, x):
        return torch.nn.functional.gelu(x)


class Swish(nn.Module):

    def __init__(self, inplace=True):
        super(Swish, self).__init__()
        self.inplace = inplace

    def forward(self, x):
        if self.inplace:
            x.mul_(torch.sigmoid(x))
            return x
        else:
            return x * torch.sigmoid(x)


class Activation(nn.Module):

    def __init__(self, act_type, inplace=True):
        super(Activation, self).__init__()
        act_type = act_type.lower()
        if act_type == 'relu':
            self.act = nn.ReLU(inplace=inplace)
        elif act_type == 'relu6':
            self.act = nn.ReLU6(inplace=inplace)
        elif act_type == 'sigmoid':
            self.act = nn.Sigmoid()
        elif act_type == 'hard_sigmoid':
            self.act = nn.Hardsigmoid(inplace)
        elif act_type == 'hard_swish':
            self.act = nn.Hardswish(inplace=inplace)
        elif act_type == 'leakyrelu':
            self.act = nn.LeakyReLU(inplace=inplace)
        elif act_type == 'gelu':
            self.act = GELU(inplace=inplace)
        elif act_type == 'swish':
            self.act = Swish(inplace=inplace)
        else:
            raise NotImplementedError

    def forward(self, inputs):
        return self.act(inputs)


def drop_path(x,
              drop_prob: float = 0.0,
              training: bool = False,
              scale_by_keep: bool = True):
    """Drop paths (Stochastic Depth) per sample (when applied in main path of
    residual blocks).

    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
    'survival rate' as the argument.
    """
    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 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 Identity(nn.Module):

    def __init__(self):
        super(Identity, self).__init__()

    def forward(self, input):
        return input


class Mlp(nn.Module):

    def __init__(
        self,
        in_features,
        hidden_features=None,
        out_features=None,
        act_layer=nn.GELU,
        drop=0.0,
    ):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

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


class Attention(nn.Module):

    def __init__(self,
                 dim,
                 num_heads=8,
                 qkv_bias=False,
                 qk_scale=None,
                 attn_drop=0.0,
                 proj_drop=0.0):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
        self.scale = qk_scale or head_dim**-0.5

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

    def forward(self, x):
        B, N, C = x.shape
        qkv = (self.qkv(x).reshape(B, N, 3, self.num_heads,
                                   C // self.num_heads).permute(2, 0, 3, 1, 4))
        q, k, v = qkv[0], qkv[1], qkv[
            2]  # make torchscript happy (cannot use tensor as tuple)

        attn = (q @ k.transpose(-2, -1)) * self.scale
        attn = attn.softmax(dim=-1)
        attn = self.attn_drop(attn)

        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


class Block(nn.Module):

    def __init__(
        self,
        dim,
        num_heads,
        mlp_ratio=4.0,
        qkv_bias=False,
        qk_scale=None,
        drop=0.0,
        attn_drop=0.0,
        drop_path=0.0,
        act_layer=nn.GELU,
        norm_layer=nn.LayerNorm,
    ):
        super().__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention(
            dim,
            num_heads=num_heads,
            qkv_bias=qkv_bias,
            qk_scale=qk_scale,
            attn_drop=attn_drop,
            proj_drop=drop,
        )
        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
        self.drop_path = 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 = Mlp(in_features=dim,
                       hidden_features=mlp_hidden_dim,
                       act_layer=act_layer,
                       drop=drop)

    def forward(self, x):
        x = x + self.drop_path(self.attn(self.norm1(x)))
        x = x + self.drop_path(self.mlp(self.norm2(x)))
        return x


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

    def __init__(self,
                 img_size=[32, 128],
                 patch_size=[4, 4],
                 in_chans=3,
                 embed_dim=768):
        super().__init__()
        num_patches = (img_size[1] // patch_size[1]) * (img_size[0] //
                                                        patch_size[0])
        self.img_size = img_size
        self.patch_size = patch_size
        self.num_patches = num_patches

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

    def forward(self, x):
        B, C, H, W = x.shape
        # FIXME look at relaxing size constraints
        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).flatten(2).transpose(1, 2)
        return x