import torch

import torch.nn as nn

import torch.nn.functional as F

from torch.nn import init

from ._utils import *

from math import sqrt

def init_weights(net, init_type='normal', gain=0.02):

    def init_func(m):

        classname = m.__class__.__name__

        if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):

            if init_type == 'normal':

                init.normal_(m.weight.data, 0.0, gain)

            elif init_type == 'xavier':

                init.xavier_normal_(m.weight.data, gain=gain)

            elif init_type == 'kaiming':

                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')

            elif init_type == 'orthogonal':

                init.orthogonal_(m.weight.data, gain=gain)

            else:

                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)

            if hasattr(m, 'bias') and m.bias is not None:

                init.constant_(m.bias.data, 0.0)

        elif classname.find('BatchNorm2d') != -1:

            init.normal_(m.weight.data, 1.0, gain)

            init.constant_(m.bias.data, 0.0)

    print('initialize network with %s' % init_type)

    net.apply(init_func)

class DoubleConv(nn.Module):

    """

    Double Conv for U-Net

    """

    def __init__(self, in_ch, out_ch, k_1=3, k_2=3):

        super(DoubleConv, self).__init__()

        padding_1 = cal_same_padding(k_1)

        padding_2 = cal_same_padding(k_2)

        self.conv = nn.Sequential(

            nn.Conv2d(in_ch, out_ch, k_1, padding=padding_1),  # in_ch、out_ch是通道数

            nn.BatchNorm2d(out_ch),

            nn.ReLU(inplace=True),

            # Mish(),

            nn.Conv2d(out_ch, out_ch, k_2, padding=padding_2),

            nn.BatchNorm2d(out_ch),

            nn.ReLU(inplace=True)

        )

        for m in self.modules():

            if isinstance(m, nn.Conv2d):

                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels

                m.weight.data.normal_(0, sqrt(2. / n))

                if m.bias is not None:

                    m.bias.data.zero_()

            elif isinstance(m, nn.BatchNorm2d):

                m.weight.data.normal_(1.0, 0.02)

                m.bias.data.fill_(0)

    def forward(self, x):

        return self.conv(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, out_dim=1):

        super(U_Net, self).__init__()

        self.conv1 = DoubleConv(img_ch, 64)

        self.pool1 = nn.MaxPool2d(2)

        self.conv2 = DoubleConv(64, 128)

        self.pool2 = nn.MaxPool2d(2)

        self.conv3 = DoubleConv(128, 256)

        self.pool3 = nn.MaxPool2d(2)

        self.conv4 = DoubleConv(256, 512)

        self.pool4 = nn.MaxPool2d(2)

        self.conv5 = DoubleConv(512, 1024)

        self.up6 = nn.ConvTranspose2d(1024, 512, 2, stride=2)

        self.conv6 = DoubleConv(1024, 512)

        self.up7 = nn.ConvTranspose2d(512, 256, 2, stride=2)

        self.conv7 = DoubleConv(512, 256)

        self.up8 = nn.ConvTranspose2d(256, 128, 2, stride=2)

        self.conv8 = DoubleConv(256, 128)

        self.up9 = nn.ConvTranspose2d(128, 64, 2, stride=2)

        self.conv9 = DoubleConv(128, 64)

        self.conv10 = nn.Conv2d(64, out_dim, 1)

        for m in self.modules():

            if isinstance(m, nn.Conv2d):

                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels

                m.weight.data.normal_(0, sqrt(2. / n))

                if m.bias is not None:

                    m.bias.data.zero_()

            elif isinstance(m, nn.BatchNorm2d):

                m.weight.data.normal_(1.0, 0.02)

                m.bias.data.fill_(0)

    def forward(self, inputs):

        c1 = self.conv1(inputs)

        p1 = self.pool1(c1)

        c2 = self.conv2(p1)

        p2 = self.pool2(c2)

        c3 = self.conv3(p2)

        p3 = self.pool3(c3)

        c4 = self.conv4(p3)

        p4 = self.pool4(c4)

        c5 = self.conv5(p4)

        up_6 = self.up6(c5)

        merge6 = torch.cat([up_6, c4], dim=1)

        c6 = self.conv6(merge6)  

        up_7 = self.up7(c6)

        merge7 = torch.cat([up_7, c3], dim=1)

        c7 = self.conv7(merge7)

        up_8 = self.up8(c7)

        merge8 = torch.cat([up_8, c2], dim=1)  # 256 *48

        c8 = self.conv8(merge8)

        up_9 = self.up9(c8)

        merge9 = torch.cat([up_9, c1], dim=1)

        c9 = self.conv9(merge9)       

        c10 = self.conv10(c9)

        return c10

class R2U_Net(nn.Module):

    def __init__(self,img_ch=3,output_ch=1,t=2):

        super(R2U_Net,self).__init__()

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

        self.Upsample = nn.Upsample(scale_factor=2)

        self.RRCNN1 = RRCNN_block(ch_in=img_ch,ch_out=64,t=t)

        self.RRCNN2 = RRCNN_block(ch_in=64,ch_out=128,t=t)

        self.RRCNN3 = RRCNN_block(ch_in=128,ch_out=256,t=t)

        self.RRCNN4 = RRCNN_block(ch_in=256,ch_out=512,t=t)

        self.RRCNN5 = RRCNN_block(ch_in=512,ch_out=1024,t=t)

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

        self.Up_RRCNN5 = RRCNN_block(ch_in=1024, ch_out=512,t=t)

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

        self.Up_RRCNN4 = RRCNN_block(ch_in=512, ch_out=256,t=t)

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

        self.Up_RRCNN3 = RRCNN_block(ch_in=256, ch_out=128,t=t)

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

        self.Up_RRCNN2 = RRCNN_block(ch_in=128, ch_out=64,t=t)

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

    def forward(self,x):

        # encoding path

        x1 = self.RRCNN1(x)

        x2 = self.Maxpool(x1)

        x2 = self.RRCNN2(x2)

        x3 = self.Maxpool(x2)

        x3 = self.RRCNN3(x3)

        x4 = self.Maxpool(x3)

        x4 = self.RRCNN4(x4)

        x5 = self.Maxpool(x4)

        x5 = self.RRCNN5(x5)

        # decoding + concat path

        d5 = self.Up5(x5)

        d5 = torch.cat((x4,d5),dim=1)

        d5 = self.Up_RRCNN5(d5)

        d4 = self.Up4(d5)

        d4 = torch.cat((x3,d4),dim=1)

        d4 = self.Up_RRCNN4(d4)

        d3 = self.Up3(d4)

        d3 = torch.cat((x2,d3),dim=1)

        d3 = self.Up_RRCNN3(d3)

        d2 = self.Up2(d3)

        d2 = torch.cat((x1,d2),dim=1)

        d2 = self.Up_RRCNN2(d2)

        d1 = self.Conv_1x1(d2)

        return d1

class AttU_Net(nn.Module):

    def __init__(self,img_ch=3,output_ch=1):

        super(AttU_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.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)

    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)

        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)

        d1 = self.Conv_1x1(d2)

        return d1

class R2AttU_Net(nn.Module):

    def __init__(self,img_ch=3,output_ch=1,t=2):

        super(R2AttU_Net,self).__init__()

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

        self.Upsample = nn.Upsample(scale_factor=2)

        self.RRCNN1 = RRCNN_block(ch_in=img_ch,ch_out=64,t=t)

        self.RRCNN2 = RRCNN_block(ch_in=64,ch_out=128,t=t)

        self.RRCNN3 = RRCNN_block(ch_in=128,ch_out=256,t=t)

        self.RRCNN4 = RRCNN_block(ch_in=256,ch_out=512,t=t)

        self.RRCNN5 = RRCNN_block(ch_in=512,ch_out=1024,t=t)

        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_RRCNN5 = RRCNN_block(ch_in=1024, ch_out=512,t=t)

        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_RRCNN4 = RRCNN_block(ch_in=512, ch_out=256,t=t)

        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_RRCNN3 = RRCNN_block(ch_in=256, ch_out=128,t=t)

        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_RRCNN2 = RRCNN_block(ch_in=128, ch_out=64,t=t)

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

    def forward(self,x):

        # encoding path

        x1 = self.RRCNN1(x)

        x2 = self.Maxpool(x1)

        x2 = self.RRCNN2(x2)

        x3 = self.Maxpool(x2)

        x3 = self.RRCNN3(x3)

        x4 = self.Maxpool(x3)

        x4 = self.RRCNN4(x4)

        x5 = self.Maxpool(x4)

        x5 = self.RRCNN5(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_RRCNN5(d5)

        d4 = self.Up4(d5)

        x3 = self.Att4(g=d4,x=x3)

        d4 = torch.cat((x3,d4),dim=1)

        d4 = self.Up_RRCNN4(d4)

        d3 = self.Up3(d4)

        x2 = self.Att3(g=d3,x=x2)

        d3 = torch.cat((x2,d3),dim=1)

        d3 = self.Up_RRCNN3(d3)

        d2 = self.Up2(d3)

        x1 = self.Att2(g=d2,x=x1)

        d2 = torch.cat((x1,d2),dim=1)

        d2 = self.Up_RRCNN2(d2)

        d1 = self.Conv_1x1(d2)

        return d1