import torch
import torch.nn as nn
from torchvision import models
import torch.nn.functional as F


class sobel_net(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv_opx = nn.Conv2d(1, 1, 3, bias=False)
        self.conv_opy = nn.Conv2d(1, 1, 3, bias=False)
        sobel_kernelx = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], dtype='float32').reshape((1, 1, 3, 3))
        sobel_kernely = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]], dtype='float32').reshape((1, 1, 3, 3))
        self.conv_opx.weight.data = torch.from_numpy(sobel_kernelx)
        self.conv_opy.weight.data = torch.from_numpy(sobel_kernely)

        for p in self.parameters():
            p.requires_grad = False

    def forward(self, im):  # input rgb
        x = (0.299 * im[:, 0, :, :] + 0.587 * im[:, 1, :, :] + 0.114 * im[:, 2, :, :]).unsqueeze(1)  # rgb2gray
        gradx = self.conv_opx(x)
        grady = self.conv_opy(x)

        x = (gradx ** 2 + grady ** 2) ** 0.5
        x = (x - x.min()) / (x.max() - x.min())
        x = F.pad(x, (1, 1, 1, 1))

        x = torch.cat([im, x], dim=1)
        return x


class conv_block(nn.Module):
    def __init__(self, ch_in, ch_out):
        super(conv_block, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1, bias=True),
            nn.BatchNorm2d(ch_out),
            nn.ReLU(inplace=True),
            nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1, bias=True),
            nn.BatchNorm2d(ch_out),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        x = self.conv(x)
        return x


class up_conv(nn.Module):
    def __init__(self, ch_in, ch_out):
        super(up_conv, self).__init__()
        self.up = nn.Sequential(
            nn.Upsample(scale_factor=2),
            nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1, bias=True),
            nn.BatchNorm2d(ch_out),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        x = self.up(x)
        return x


class Recurrent_block(nn.Module):
    def __init__(self, ch_out, t=2):
        super(Recurrent_block, self).__init__()
        self.t = t
        self.ch_out = ch_out
        self.conv = nn.Sequential(
            nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1, bias=True),
            nn.BatchNorm2d(ch_out),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        for i in range(self.t):

            if i == 0:
                x1 = self.conv(x)

            x1 = self.conv(x + x1)
        return x1


class RRCNN_block(nn.Module):
    def __init__(self, ch_in, ch_out, t=2):
        super(RRCNN_block, self).__init__()
        self.RCNN = nn.Sequential(
            Recurrent_block(ch_out, t=t),
            Recurrent_block(ch_out, t=t)
        )
        self.Conv_1x1 = nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=1, padding=0)

    def forward(self, x):
        x = self.Conv_1x1(x)
        x1 = self.RCNN(x)
        return x + x1


class single_conv(nn.Module):
    def __init__(self, ch_in, ch_out):
        super(single_conv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1, bias=True),
            nn.BatchNorm2d(ch_out),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        x = self.conv(x)
        return x


class Attention_block(nn.Module):
    def __init__(self, F_g, F_l, F_int):
        super(Attention_block, self).__init__()
        self.W_g = nn.Sequential(
            nn.Conv2d(F_g, F_int, kernel_size=1, stride=1, padding=0, bias=True),
            nn.BatchNorm2d(F_int)
        )

        self.W_x = nn.Sequential(
            nn.Conv2d(F_l, F_int, kernel_size=1, stride=1, padding=0, bias=True),
            nn.BatchNorm2d(F_int)
        )

        self.psi = nn.Sequential(
            nn.Conv2d(F_int, 1, kernel_size=1, stride=1, padding=0, bias=True),
            nn.BatchNorm2d(1),
            nn.Sigmoid()
        )

        self.relu = nn.ReLU(inplace=True)

    def forward(self, g, x):
        g1 = self.W_g(g)
        x1 = self.W_x(x)
        psi = self.relu(g1 + x1)
        psi = self.psi(psi)

        return x * psi


class U_Net(nn.Module):
    def __init__(self, img_ch=3, output_ch=1):
        super(U_Net, self).__init__()

        self.Maxpool = nn.MaxPool2d(kernel_size=2, stride=2)

        self.Conv1 = conv_block(ch_in=img_ch, ch_out=64)
        self.Conv2 = conv_block(ch_in=64, ch_out=128)
        self.Conv3 = conv_block(ch_in=128, ch_out=256)
        self.Conv4 = conv_block(ch_in=256, ch_out=512)
        self.Conv5 = conv_block(ch_in=512, ch_out=1024)

        self.Up5 = up_conv(ch_in=1024, ch_out=512)
        self.Up_conv5 = conv_block(ch_in=1024, ch_out=512)

        self.Up4 = up_conv(ch_in=512, ch_out=256)
        self.Up_conv4 = conv_block(ch_in=512, ch_out=256)

        self.Up3 = up_conv(ch_in=256, ch_out=128)
        self.Up_conv3 = conv_block(ch_in=256, ch_out=128)

        self.Up2 = up_conv(ch_in=128, ch_out=64)
        self.Up_conv2 = conv_block(ch_in=128, ch_out=64)

        self.Conv_1x1 = nn.Conv2d(64, output_ch, kernel_size=1, stride=1, padding=0, bias=False)

    def forward(self, x):
        # encoding path
        x1 = self.Conv1(x)

        x2 = self.Maxpool(x1)
        x2 = self.Conv2(x2)

        x3 = self.Maxpool(x2)
        x3 = self.Conv3(x3)

        x4 = self.Maxpool(x3)
        x4 = self.Conv4(x4)

        x5 = self.Maxpool(x4)
        x5 = self.Conv5(x5)

        # decoding + concat path
        d5 = self.Up5(x5)
        d5 = torch.cat((x4, d5), dim=1)

        d5 = self.Up_conv5(d5)

        d4 = self.Up4(d5)
        d4 = torch.cat((x3, d4), dim=1)
        d4 = self.Up_conv4(d4)

        d3 = self.Up3(d4)
        d3 = torch.cat((x2, d3), dim=1)
        d3 = self.Up_conv3(d3)

        d2 = self.Up2(d3)
        d2 = torch.cat((x1, d2), dim=1)
        d2 = self.Up_conv2(d2)

        out = self.Conv_1x1(d2)
        out = torch.sigmoid(out)

        return out


class U_Net_mini(nn.Module):
    def __init__(self, img_ch=3, output_ch=1):
        super(U_Net_mini, self).__init__()

        self.Maxpool = nn.MaxPool2d(kernel_size=2, stride=2)

        self.Conv1 = conv_block(ch_in=img_ch, ch_out=32)
        self.Conv2 = conv_block(ch_in=32, ch_out=64)
        self.Conv3 = conv_block(ch_in=64, ch_out=128)
        self.Conv4 = conv_block(ch_in=128, ch_out=256)
        self.Conv5 = conv_block(ch_in=256, ch_out=512)

        self.Up5 = up_conv(ch_in=512, ch_out=256)
        self.Up_conv5 = conv_block(ch_in=512, ch_out=256)

        self.Up4 = up_conv(ch_in=256, ch_out=128)
        self.Up_conv4 = conv_block(ch_in=256, ch_out=128)

        self.Up3 = up_conv(ch_in=128, ch_out=64)
        self.Up_conv3 = conv_block(ch_in=128, ch_out=64)

        self.Up2 = up_conv(ch_in=64, ch_out=32)
        self.Up_conv2 = conv_block(ch_in=64, ch_out=32)

        self.Conv_1x1 = nn.Conv2d(32, output_ch, kernel_size=1, stride=1, padding=0, bias=False)

    def forward(self, x):
        # encoding path
        x1 = self.Conv1(x)

        x2 = self.Maxpool(x1)
        x2 = self.Conv2(x2)

        x3 = self.Maxpool(x2)
        x3 = self.Conv3(x3)

        x4 = self.Maxpool(x3)
        x4 = self.Conv4(x4)

        x5 = self.Maxpool(x4)
        x5 = self.Conv5(x5)

        # decoding + concat path
        d5 = self.Up5(x5)
        d5 = torch.cat((x4, d5), dim=1)

        d5 = self.Up_conv5(d5)

        d4 = self.Up4(d5)
        d4 = torch.cat((x3, d4), dim=1)
        d4 = self.Up_conv4(d4)

        d3 = self.Up3(d4)
        d3 = torch.cat((x2, d3), dim=1)
        d3 = self.Up_conv3(d3)

        d2 = self.Up2(d3)
        d2 = torch.cat((x1, d2), dim=1)
        d2 = self.Up_conv2(d2)

        out = self.Conv_1x1(d2)
        out = torch.sigmoid(out)

        return d4, out


class AttU_Net(nn.Module):
    def __init__(self, img_ch=3, output_ch=1, need_feature_maps=False):
        super(AttU_Net, self).__init__()

        self.conv1_ = nn.Sequential(nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),
                                    nn.BatchNorm2d(64),
                                    nn.ReLU(inplace=True))

        self.Maxpool = nn.MaxPool2d(kernel_size=2, stride=2)

        self.Conv1 = conv_block(ch_in=64, ch_out=64)
        self.Conv2 = conv_block(ch_in=64, ch_out=128)
        self.Conv3 = conv_block(ch_in=128, ch_out=256)
        self.Conv4 = conv_block(ch_in=256, ch_out=512)
        self.Conv5 = conv_block(ch_in=512, ch_out=1024)

        self.Up5 = up_conv(ch_in=1024, ch_out=512)
        self.Att5 = Attention_block(F_g=512, F_l=512, F_int=256)
        self.Up_conv5 = conv_block(ch_in=1024, ch_out=512)

        self.Up4 = up_conv(ch_in=512, ch_out=256)
        self.Att4 = Attention_block(F_g=256, F_l=256, F_int=128)
        self.Up_conv4 = conv_block(ch_in=512, ch_out=256)

        self.Up3 = up_conv(ch_in=256, ch_out=128)
        self.Att3 = Attention_block(F_g=128, F_l=128, F_int=64)
        self.Up_conv3 = conv_block(ch_in=256, ch_out=128)

        self.Up2 = up_conv(ch_in=128, ch_out=64)
        self.Att2 = Attention_block(F_g=64, F_l=64, F_int=32)
        self.Up_conv2 = conv_block(ch_in=128, ch_out=64)

        self.Conv_1x1 = nn.Conv2d(64, output_ch, kernel_size=1, stride=1, padding=0)

        self.need_feature_maps = need_feature_maps

        # self.loc_xy = (torch.stack(torch.meshgrid([torch.arange(0, 256), torch.arange(0, 256)])).permute(0, 2, 1).unsqueeze(0).float() - 127.5) / 127.5  # 1*2*256*256

    def forward(self, x):
        # encoding path
        # batch = x.size(0)
        # if self.need_feature_maps:
        #     x = torch.cat((x, self.loc_xy.repeat(batch, 1, 1, 1).cuda()), dim=1)
        x1 = self.conv1_(x)
        x1 = self.Conv1(x1)

        x2 = self.Maxpool(x1)
        x2 = self.Conv2(x2)

        x3 = self.Maxpool(x2)
        x3 = self.Conv3(x3)

        x4 = self.Maxpool(x3)
        x4 = self.Conv4(x4)

        x5 = self.Maxpool(x4)
        x5 = self.Conv5(x5)

        # decoding + concat path
        d5 = self.Up5(x5)
        x4 = self.Att5(g=d5, x=x4)
        d5 = torch.cat((x4, d5), dim=1)
        d5 = self.Up_conv5(d5)

        d4 = self.Up4(d5)
        x3 = self.Att4(g=d4, x=x3)
        d4 = torch.cat((x3, d4), dim=1)
        d4 = self.Up_conv4(d4)

        d3 = self.Up3(d4)
        x2 = self.Att3(g=d3, x=x2)
        d3 = torch.cat((x2, d3), dim=1)
        d3 = self.Up_conv3(d3)

        d2 = self.Up2(d3)
        x1 = self.Att2(g=d2, x=x1)
        d2 = torch.cat((x1, d2), dim=1)
        d2 = self.Up_conv2(d2)

        wc = self.Conv_1x1(d2)

        if self.need_feature_maps:
            return d2, wc
        else:
            return bm


class Doc_UNet(nn.Module):
    def __init__(self):
        super(Doc_UNet, self).__init__()
        self.U_net1 = AttU_Net(3, 3, need_feature_maps=True)
        self.U_net2 = U_Net(64 + 3 + 2, 2, need_feature_maps=False)
        self.htan = nn.Hardtanh(0, 1.0)
        self.f_activation = nn.Hardtanh()

        self.loc_xy = (torch.stack(torch.meshgrid([torch.arange(0, 128), torch.arange(0, 128)])).permute(0, 2,
                                                                                                         1).unsqueeze(
            0).float() - 63.5) / 63.5  # 1*2*256*256

    def forward(self, x):
        batch = x.size(0)

        feature_maps, wc = self.U_net1(x)
        wc = self.htan(wc)

        x = torch.cat((self.loc_xy.repeat(batch, 1, 1, 1).cuda(), wc, feature_maps), dim=1)
        bm = self.U_net2(x)
        bm = self.f_activation(bm)

        return wc, bm


def get_parameter_number(net):
    total_num = sum(p.numel() for p in net.parameters())
    trainable_num = sum(p.numel() for p in net.parameters() if p.requires_grad)
    return {'Total': total_num, 'Trainable': trainable_num}


if __name__ == '__main__':
    net = U2NET(3, 1).cuda()
    print(get_parameter_number(net))  # 69090500 加attention后69442032
    with torch.no_grad():
        inputs = torch.zeros(1, 3, 256, 256).cuda()
        outs = net(inputs)
        print(outs[0].shape)  # torch.Size([2, 3, 256, 256]) torch.Size([2, 2, 256, 256])