import math
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
from timm.models.layers import DropPath, to_2tuple, trunc_normal_


class Mlp(nn.Module):
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=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


def window_partition(x, window_size):
    """
    Args:
        x: (B, H, W, C)
        window_size (int): window size

    Returns:
        windows: (num_windows*B, window_size, window_size, C)
    """
    B, H, W, C = x.shape
    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
    return windows


def window_reverse(windows, window_size, H, W):
    """
    Args:
        windows: (num_windows*B, window_size, window_size, C)
        window_size (int): Window size
        H (int): Height of image
        W (int): Width of image

    Returns:
        x: (B, H, W, C)
    """
    B = int(windows.shape[0] / (H * W / window_size / window_size))
    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
    return x


class WindowAttention(nn.Module):

    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):

        super().__init__()
        self.dim = dim
        self.window_size = window_size  # Wh, Ww
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** -0.5

        # define a parameter table of relative position bias
        self.relative_position_bias_table = nn.Parameter(
            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH

        # get pair-wise relative position index for each token inside the window
        coords_h = torch.arange(self.window_size[0])
        coords_w = torch.arange(self.window_size[1])
        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
        relative_coords[:, :, 1] += self.window_size[1] - 1
        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
        self.register_buffer("relative_position_index", relative_position_index)

        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)

        trunc_normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, mask=None):
        """
        Args:
            x: input features with shape of (num_windows*B, N, C)
            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
        """
        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)

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

        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            nW = mask.shape[0]
            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, N, N)
            attn = self.softmax(attn)
        else:
            attn = self.softmax(attn)

        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

    def extra_repr(self) -> str:
        return f'dim={self.dim}, window_size={self.window_size}, num_heads={self.num_heads}'

    def flops(self, N):
        # calculate flops for 1 window with token length of N
        flops = 0
        # qkv = self.qkv(x)
        flops += N * self.dim * 3 * self.dim
        # attn = (q @ k.transpose(-2, -1))
        flops += self.num_heads * N * (self.dim // self.num_heads) * N
        #  x = (attn @ v)
        flops += self.num_heads * N * N * (self.dim // self.num_heads)
        # x = self.proj(x)
        flops += N * self.dim * self.dim
        return flops


class SwinTransformerBlock(nn.Module):

    def __init__(self, dim, img_resolution, num_heads, window_size=7, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.GELU, norm_layer=nn.LayerNorm):
        super().__init__()
        self.dim = dim
        self.img_resolution = img_resolution
        self.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio
        if min(self.img_resolution) <= self.window_size:
            # if window size is larger than input resolution, we don't partition windows
            self.shift_size = 0
            self.window_size = min(self.img_resolution)
        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"

        self.norm1 = norm_layer(dim)
        self.attn = WindowAttention(
            dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)

        self.drop_path = DropPath(drop_path) if drop_path > 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)

        if self.shift_size > 0:
            attn_mask = self.calculate_mask(self.img_resolution)
        else:
            attn_mask = None

        self.register_buffer("attn_mask", attn_mask)

    def calculate_mask(self, x_size):
        # calculate attention mask for SW-MSA
        H, W = x_size
        img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
        h_slices = (slice(0, -self.window_size),
                    slice(-self.window_size, -self.shift_size),
                    slice(-self.shift_size, None))
        w_slices = (slice(0, -self.window_size),
                    slice(-self.window_size, -self.shift_size),
                    slice(-self.shift_size, None))
        cnt = 0
        for h in h_slices:
            for w in w_slices:
                img_mask[:, h, w, :] = cnt
                cnt += 1

        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))

        return attn_mask

    def forward(self, x, x_size):
        H, W = x_size
        B, L, C = x.shape
        # assert L == H * W, "input feature has wrong size"

        shortcut = x
        x = self.norm1(x)
        x = x.view(B, H, W, C)

        # cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
        else:
            shifted_x = x

        # partition windows
        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C

        # W-MSA/SW-MSA (to be compatible for testing on images whose shapes are the multiple of window size
        if self.img_resolution == x_size:
            attn_windows = self.attn(x_windows, mask=self.attn_mask)  # nW*B, window_size*window_size, C
        else:
            attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device))

        # merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
        shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C

        # reverse cyclic shift
        if self.shift_size > 0:
            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
        else:
            x = shifted_x
        x = x.view(B, H * W, C)

        # FFN
        x = shortcut + self.drop_path(x)
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        return x

    def flops(self):
        flops = 0
        H, W = self.img_resolution
        # norm1
        flops += self.dim * H * W
        # W-MSA/SW-MSA
        nW = H * W / self.window_size / self.window_size
        flops += nW * self.attn.flops(self.window_size * self.window_size)
        # mlp
        flops += 2 * H * W * self.dim * self.dim * self.mlp_ratio
        # norm2
        flops += self.dim * H * W
        return flops


class ResBlock(nn.Module):
    def __init__(
        self, n_feats, kernel_size,
        bias=True, bn=False, act=nn.ReLU(True), res_scale=0.1):

        super(ResBlock, self).__init__()
        m = []
        for i in range(2):
            m.append(nn.Conv2d(n_feats, n_feats, kernel_size, padding=1, bias=bias))
            if bn:
                m.append(nn.BatchNorm2d(n_feats))
            if i == 0:
                m.append(act)

        self.body = nn.Sequential(*m)
        self.res_scale = res_scale

    def forward(self, x):
        res = self.body(x).mul(self.res_scale)
        res += x

        return res


class DoubleBranchBlock(nn.Module):

    def __init__(self, dim, img_resolution, depth, num_heads, window_size,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, use_checkpoint=False):

        super().__init__()
        self.dim = dim
        self.input_resolution = img_resolution
        self.depth = depth
        self.use_checkpoint = use_checkpoint

        # build blocks
        self.FIEB = nn.ModuleList([
            SwinTransformerBlock(dim=dim, img_resolution=img_resolution,
                                 num_heads=num_heads, window_size=window_size,
                                 shift_size=0 if (i % 2 == 0) else window_size // 2,
                                 mlp_ratio=mlp_ratio,
                                 qkv_bias=qkv_bias, qk_scale=qk_scale,
                                 drop=drop, attn_drop=attn_drop,
                                 drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
                                 norm_layer=norm_layer)
            for i in range(depth)])

        SIEB = []
        SIEB.append(ResBlock(dim, 3))

        self.SIEB = nn.Sequential(*SIEB)


    def forward(self, x, x_size):
        H, W = x_size
        B, _, C = x.shape
        x_ = self.SIEB(x.transpose(1, 2).reshape(B, C, H, W))
        for fbranch in self.FIEB:
            x = fbranch(x, x_size)
        return torch.cat((x, x_.flatten(2).transpose(1, 2)), dim=2)

    # def extra_repr(self) -> str:
    #     return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}"

    def flops(self):
        flops = 0
        for blk in self.blocks:
            flops += blk.flops()
        # if self.downsample is not None:
        #     flops += self.downsample.flops()
        return flops


class DoublebranchFeatureExtractionBlock(nn.Module):

    def __init__(self, dim, img_resolution, depth, num_heads, window_size,
                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False,
                 img_size=224, patch_size=4, resi_connection='1conv'):
        super(DoublebranchFeatureExtractionBlock, self).__init__()

        self.dim = dim
        self.input_resolution = img_resolution

        self.DFEB = DoubleBranchBlock(dim=dim,
                                         img_resolution=img_resolution,
                                         depth=depth,
                                         num_heads=num_heads,
                                         window_size=window_size,
                                         mlp_ratio=mlp_ratio,
                                         qkv_bias=qkv_bias, qk_scale=qk_scale,
                                         drop=drop, attn_drop=attn_drop,
                                         drop_path=drop_path,
                                         norm_layer=norm_layer,
                                         # downsample=downsample,
                                         use_checkpoint=use_checkpoint)

        if resi_connection == '1conv':
            self.conv = nn.Conv2d(dim*2, dim, 3, 1, 1)
            # self.conv = nn.Sequential(nn.Conv2d(dim*2, dim, 3, 1, 1),
            #                           nn.ReLU(True),
            #                           nn.Conv2d(dim, dim, 3, 1, 1))

        self.token_embed = PatchEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=0, embed_dim=dim,
            norm_layer=None)

        self.token_unembed = PatchUnEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=0, embed_dim=dim,
            norm_layer=None)

    def forward(self, x, x_size):
        x_token = self.DFEB(x, x_size)
        x = self.token_unembed(x_token, x_size)
        x = self.conv(x)
        x_token = self.token_embed(x)

        return x_token

    def flops(self):
        flops = 0
        flops += self.residual_group.flops()
        H, W = self.input_resolution
        flops += 2 * H * W * (self.dim * 9 + 1) * self.dim * 2
        flops += 2 * H * W * (self.dim * 2 * 9 + 1) * self.dim
        flops += self.patch_embed.flops()
        flops += self.patch_unembed.flops()

        return flops


class PatchEmbed(nn.Module):

    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
        super().__init__()
        img_size = to_2tuple(img_size)
        self.img_size = img_size

        self.in_chans = in_chans
        self.embed_dim = embed_dim

        if norm_layer is not None:
            self.norm = norm_layer(embed_dim)
        else:
            self.norm = None

    def forward(self, x):
        x = x.flatten(2).transpose(1, 2)  # B Ph*Pw C
        if self.norm is not None:
            x = self.norm(x)
        return x

    def flops(self):
        flops = 0
        H, W = self.img_size
        if self.norm is not None:
            flops += H * W * self.embed_dim
        return flops


class PatchUnEmbed(nn.Module):

    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
        super().__init__()
        img_size = to_2tuple(img_size)
        self.img_size = img_size

        self.in_chans = in_chans
        self.embed_dim = embed_dim

    def forward(self, x, x_size):
        B, HW, C = x.shape
        x = x.transpose(1, 2).view(B, -1, x_size[0], x_size[1])  # B Ph*Pw C
        return x

    def flops(self):
        flops = 0
        return flops


class MFAM(nn.Module):

    def __init__(self, img_size=64, patch_size=1, in_chans=1,
                 embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
                 window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
                 norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
                 use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv',
                 **kwargs):
        super(MFAM, self).__init__()
        # print("MFAM-dongba")
        num_in_ch = in_chans
        num_out_ch = in_chans
        self.img_range = img_range

        # if in_chans == 3:
        #     rgb_mean = (0.4488, 0.4371, 0.4040)
        #     self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)
        # else:
        #     self.mean = torch.zeros(1, 1, 1, 1)

        self.upscale = upscale
        self.upsampler = upsampler
        self.window_size = window_size

        self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1)

        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.patch_norm = patch_norm
        self.num_features = embed_dim
        self.mlp_ratio = mlp_ratio

        # split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None)
        # num_patches = self.patch_embed.num_patches
        self.img_resolution = self.patch_embed.img_size
        img_resolution = self.patch_embed.img_size

        # merge non-overlapping patches into image
        self.patch_unembed = PatchUnEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
            norm_layer=norm_layer if self.patch_norm else None)

        self.pos_drop = nn.Dropout(p=drop_rate)

        # stochastic depth
        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule

        # build Residual Swin Transformer blocks (RSTB)
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            layer = DoublebranchFeatureExtractionBlock(dim=embed_dim,
                         img_resolution=(img_resolution[0],
                                           img_resolution[1]),
                         depth=depths[i_layer],
                         num_heads=num_heads[i_layer],
                         window_size=window_size,
                         mlp_ratio=self.mlp_ratio,
                         qkv_bias=qkv_bias, qk_scale=qk_scale,
                         drop=drop_rate, attn_drop=attn_drop_rate,
                         drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],  # no impact on SR results
                         norm_layer=norm_layer,
                         downsample=None,
                         use_checkpoint=use_checkpoint,
                         img_size=img_size,
                         patch_size=patch_size,
                         resi_connection=resi_connection

                         )
            self.layers.append(layer)
        self.norm = norm_layer(self.num_features)

        # build the last conv layer in deep feature extraction
        if resi_connection == '1conv':
            self.conv_after_body = ResBlock(embed_dim, 3)

        self.conv_last = nn.Conv2d(embed_dim, num_out_ch//2, 3, 1, 1)

        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    @torch.jit.ignore
    def no_weight_decay(self):
        return {'absolute_pos_embed'}

    @torch.jit.ignore
    def no_weight_decay_keywords(self):
        return {'relative_position_bias_table'}

    def check_image_size(self, x):
        _, _, h, w = x.size()
        mod_pad_h = (self.window_size - h % self.window_size) % self.window_size
        mod_pad_w = (self.window_size - w % self.window_size) % self.window_size
        x = F.pad(x, (0, mod_pad_w, 0, mod_pad_h), 'reflect')
        return x

    def forward_features(self, x):
        x_size = (x.shape[2], x.shape[3])
        x = self.patch_embed(x)
        # if self.ape:
        #     x = x + self.absolute_pos_embed
        x = self.pos_drop(x)
        res = 0.
        for layer in self.layers:
            x = layer(x, x_size)
            res += x
        x = self.norm(x+res)  # B L C
        x = self.patch_unembed(x, x_size)

        return x

    def forward(self, x):
        H, W = x.shape[2:]
        x = self.check_image_size(x)

        x_first = self.conv_first(x)
        res = self.conv_after_body(self.forward_features(x_first)) + x_first
        # x = x + self.conv_last(res)
        x = self.conv_last(res)

        return x[:, :, :H * self.upscale, :W * self.upscale]

    def flops(self):
        flops = 0
        H, W = self.img_resolution
        flops += 2 * H * W * (12 * 9 + 1) * self.embed_dim * 2
        flops += self.patch_embed.flops()
        for i, layer in enumerate(self.layers):
            flops += layer.flops()
        flops += 2 * H * W * (self.embed_dim * 9 + 1) * self.embed_dim * 2
        flops += 2 * H * W * (self.embed_dim * 9 + 1) * 12
        return flops


# if __name__ == '__main__':
#     upscale = 4
#     window_size = 8
#     height = (1024 // upscale // window_size + 1) * window_size
#     width = (720 // upscale // window_size + 1) * window_size
#     model = SwinIR(upscale=1, img_size=(height, width),
#                    window_size=window_size, img_range=1., depths=[6, 6, 6, 6, 6, 6],
#                    embed_dim=180, num_heads=[6, 6, 6, 6, 6, 6], mlp_ratio=2, upsampler='')
#
    # def get_parameter_number(model):
    #     total_num = sum(p.numel() for p in model.parameters())
    #     trainable_num = sum(p.numel() for p in model.parameters() if p.requires_grad)
    #     return {'Total': total_num, 'Trainable': trainable_num}
    #
    # print(get_parameter_number(model))

    # print(model)
    # print(height, width, model.flops() / 1e9)

    # x = torch.randn((1, 3, height, width))
    # x = torch.FloatTensor(x).cuda(1)
    # x = model(x)
    # print(x.shape)