unet.py

import torch
import torch.nn as nn

class EncodingBlock(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(EncodingBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.activation = nn.ReLU(inplace=True)

    def forward(self, x):
        x = self.conv1(x)
        x = self.activation(x)
        x = self.conv2(x)
        x = self.activation(x)
        skip_connection = x
        x = self.pool(x)
        return x, skip_connection

class DecodingBlock(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(DecodingBlock, self).__init__()
        self.conv_transpose = nn.ConvTranspose2d(in_channels, out_channels, kernel_size=5, stride=2, padding=2)
        self.conv1 = nn.Conv2d(out_channels * 2, out_channels, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1)
        self.activation = nn.ReLU(inplace=True)

    def forward(self, x, skip_connection):
        x = self.conv_transpose(x)
        pd = (0, skip_connection.size(-1) - x.size(-1), 0, skip_connection.size(-2) - x.size(-2))
        x = nn.functional.pad(x, pd, mode='constant', value=0)
        x = torch.cat((x, skip_connection), dim=1)
        x = self.conv1(x)
        x = self.activation(x)
        x = self.conv2(x)
        x = self.activation(x)
        return x

class UNet(nn.Module):
    def __init__(self, init_features=32, bottleneck_size=512):
        super(UNet, self).__init__()
        self.encoding_block1 = EncodingBlock(1, init_features)
        self.encoding_block2 = EncodingBlock(init_features, init_features*2)
        self.encoding_block3 = EncodingBlock(init_features*2, init_features*4)
        self.encoding_block4 = EncodingBlock(init_features*4, init_features*8)

        self.bottleneck_conv1 = nn.Conv2d(init_features*8, bottleneck_size, kernel_size=3, padding=1)
        self.bottleneck_conv2 = nn.Conv2d(bottleneck_size, bottleneck_size, kernel_size=3, padding=1)

        self.decoding_block4 = DecodingBlock(bottleneck_size, init_features*8)
        self.decoding_block3 = DecodingBlock(init_features*8, init_features*4)
        self.decoding_block2 = DecodingBlock(init_features*4, init_features*2)
        self.decoding_block1 = DecodingBlock(init_features*2, init_features)

        self.final_conv = nn.Conv2d(init_features, 1, kernel_size=1)
        
    def forward(self, x):
        x, skip1 = self.encoding_block1(x)
        x, skip2 = self.encoding_block2(x)
        x, skip3 = self.encoding_block3(x)
        x, skip4 = self.encoding_block4(x)

        x = self.bottleneck_conv1(x)
        x = nn.ReLU(inplace=True)(x)
        x = self.bottleneck_conv2(x)
        x = nn.ReLU(inplace=True)(x)

        x = self.decoding_block4(x, skip4)
        x = self.decoding_block3(x, skip3)
        x = self.decoding_block2(x, skip2)
        x = self.decoding_block1(x, skip1)

        x = self.final_conv(x)
        return x