import torch
import torch.nn as nn

class AttentionBlock(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=3, padding=1):
        super(AttentionBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels,
                               kernel_size=kernel_size, padding=padding)
        self.conv2 = nn.Conv2d(out_channels, out_channels,
                               kernel_size=kernel_size, padding=padding)
        self.attn = nn.MultiheadAttention(
            out_channels, num_heads=8, batch_first=True)
        self.norm = nn.LayerNorm(out_channels)
        self.activation = nn.ReLU()

    def forward(self, x):
        x = self.conv1(x)
        x = self.activation(x)
        x = self.conv2(x)
        b, c, h, w = x.size()
        x = x.view(b, c, h * w).permute(2, 0, 1)  # Reshape and permute
        attn_output, _ = self.attn(x, x, x)
        x = attn_output.permute(1, 2, 0).view(
            b, c, h, w)  # Revert the permute and reshape
        x = x.view(b, c, -1)  # Flatten the last two dimensions
        # Reshape for LayerNorm and apply normalization
        x = self.norm(x.reshape(b, -1, c))
        x = x.view(b, c, h, w)  # Reshape back to original
        return x



class UNet(nn.Module):
    def __init__(self):
        super(UNet, self).__init__()

        self.encoder = nn.Sequential(
            nn.Conv2d(3, 32, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(64, 128, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(128, 256, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(256, 512, kernel_size=3, padding=1),
            nn.ReLU(),
        )

        self.lstm = nn.LSTM(512, 512, batch_first=True)
        self.attn_block = AttentionBlock(512, 512)

        self.decoder = nn.Sequential(
            nn.ConvTranspose2d(1024, 256, kernel_size=2, stride=2),
            nn.ReLU(),
            nn.ConvTranspose2d(512, 128, kernel_size=2, stride=2),
            nn.ReLU(),
            nn.ConvTranspose2d(256, 64, kernel_size=2, stride=2),
            nn.ReLU(),
            nn.ConvTranspose2d(128, 32, kernel_size=2, stride=2),
            nn.ReLU(),
            nn.ConvTranspose2d(64, 3, kernel_size=1),
            nn.Sigmoid(),
        )

    def forward(self, x):
        skip_connections = []

        for layer in self.encoder:
            x = layer(x)
            skip_connections.append(x)
            if isinstance(layer, nn.MaxPool2d):
                skip_connections.pop()

        batch_size, channels, height, width = x.size()
        x = x.view(batch_size, -1, channels)
        x, _ = self.lstm(x)
        x = x.unsqueeze(1)
        x = x.permute(0, 2, 3, 1)
        x = x.reshape(batch_size, channels, height, width)

        x = self.attn_block(x)

        skip_connections = skip_connections[::-1]

        for i, layer in enumerate(self.decoder):
            if isinstance(layer, nn.ConvTranspose2d):
                x = layer(torch.cat((x, skip_connections[i]), dim=1))
            else:
                x = layer(x)

        return x