unet.py

# ----------------------------
# Step 3.1: Define core building blocks
# ----------------------------

import torch
import torch.nn as nn
import torch.nn.functional as F


# A simple helper: 2×(Conv -> BN -> ReLU)
class DoubleConv(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(DoubleConv, self).__init__()
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1, bias=False),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

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

# ----------------------------
# Step 3.2: Define the full U-Net architecture
# ----------------------------
class UNet(nn.Module):
    def __init__(self, in_channels=3, out_channels=1, features=[64, 128, 256, 512]):
        super(UNet, self).__init__()
        self.downs = nn.ModuleList()
        self.ups   = nn.ModuleList()
        self.pool  = nn.MaxPool2d(kernel_size=2, stride=2)

        # Encoder path
        for feature in features:
            self.downs.append(DoubleConv(in_channels, feature))
            in_channels = feature

        # Bottleneck
        self.bottleneck = DoubleConv(features[-1], features[-1]*2)

        # Decoder path
        for feature in reversed(features):
            self.ups.append(
                nn.ConvTranspose2d(feature*2, feature, kernel_size=2, stride=2)
            )
            self.ups.append(DoubleConv(feature*2, feature))

        # Output layer
        self.final_conv = nn.Conv2d(features[0], out_channels, kernel_size=1)

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

        # Encoder
        for down in self.downs:
            x = down(x)
            skip_connections.append(x)
            x = self.pool(x)

        # Bottleneck
        x = self.bottleneck(x)

        # Decoder
        skip_connections = skip_connections[::-1]
        for idx in range(0, len(self.ups), 2):
            x = self.ups[idx](x)  # upsample
            skip_connection = skip_connections[idx//2]

            # Handle potential size mismatch due to pooling
            if x.shape != skip_connection.shape:
                x = nn.functional.interpolate(x, size=skip_connection.shape[2:])

            concat_skip = torch.cat((skip_connection, x), dim=1)
            x = self.ups[idx+1](concat_skip)

        return self.final_conv(x)