import torch
import torch.nn as nn
import torch.nn.functional as F
import pytorch_lightning as L

class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
        )

    def forward(self, x):
        return self.double_conv(x)


class Down(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.maxpool_conv = nn.Sequential(
            nn.MaxPool2d(2),
            DoubleConv(in_channels, out_channels)
        ) 

    def forward(self, x):
        return self.maxpool_conv(x)


class Up(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.up = nn.Upsample(
            scale_factor = 2,
            mode = 'bilinear',
            align_corners = True
        )

        self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        # x1, x2 -> upsampled tensor, skip-connection tensor
        x1 = self.up(x1)

        # Input -> CHW
        diffY = x2.size()[2] - x1.size()[2]  # Height difference
        diffX = x2.size()[3] - x1.size()[3]  # Width difference
        # [left, right, top , bottom]
        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2, diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1) # channel-wise dim increase

        return self.conv(x)

class OutConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(OutConv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

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

class mIoULoss(nn.Module):
    def __init__(self, weight=None, size_average=True, n_classes=2):
        super().__init__()
        self.classes = n_classes

    def to_one_hot(self, tensor):
        tensor = tensor.long()  # Ensure tensor is a LongTensor
        n,c,h,w = tensor.size()
        one_hot = torch.zeros(n,self.classes,h,w).to(tensor.device).scatter_(1,tensor.view(n,1,h,w),1)
        return one_hot

    def forward(self, inputs, target):
        # inputs => N x Classes x H x W
        # target_oneHot => N x Classes x H x W

        N = inputs.size()[0]

        # predicted probabilities for each pixel along channel
        inputs = F.softmax(inputs,dim=1)
        
        # Numerator Product
        target_oneHot = self.to_one_hot(target)
        inter = inputs * target_oneHot
        ## Sum over all pixels N x C x H x W => N x C
        inter = inter.view(N,self.classes,-1).sum(2)

        #Denominator 
        union= inputs + target_oneHot - (inputs*target_oneHot)
        ## Sum over all pixels N x C x H x W => N x C
        union = union.view(N,self.classes,-1).sum(2)

        loss = inter/union

        ## Return average loss over classes and batch
        return 1-loss.mean()


class UNet(L.LightningModule):
    def __init__(self, n_channels=3, n_classes=6):
        super().__init__()
        self.n_channels = n_channels
        self.n_classes = n_classes

        self.inc = DoubleConv(n_channels, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        self.down4 = Down(512, 512)
        self.up1 = Up(1024, 256)
        self.up2 = Up(512, 128)
        self.up3 = Up(256, 64)
        self.up4 = Up(128, 64)
        self.outc = OutConv(64, n_classes)

        self.criterion = mIoULoss(n_classes=n_classes)

    def forward(self, x):
        x1 = self.inc(x)
        x2 = self.down1(x1)
        x3 = self.down2(x2)
        x4 = self.down3(x3)
        x5 = self.down4(x4)
        x = self.up1(x5, x4)
        x = self.up2(x, x3)
        x = self.up3(x, x2)
        x = self.up4(x, x1)
        logits = self.outc(x)
        return logits

    def training_step(self, batch, batch_idx):
        images, masks = batch
        logits = self(images)
        loss = self.criterion(logits, masks)
        self.log('train_loss', loss)
        print('train_loss', loss)
        return loss

    def validation_step(self, batch, batch_idx):
        images, masks = batch
        logits = self(images)
        loss = self.criterion(logits, masks)
        self.log('val_loss', loss)
        print('val_loss', loss)
        return loss

    def configure_optimizers(self):
        optimizer =  torch.optim.Adam(self.parameters(), lr=1e-3)
        return optimizer