unet_blocks.py

from typing import Optional

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


class DoubleConv(nn.Module):

    def __init__(self,
                 in_channels: int,
                 out_channels: int,
                 mid_channels: Optional[int] = None
                 ) -> None:
        super().__init__()
        if not mid_channels:
            mid_channels = out_channels
        self.double_conv = nn.Sequential(
            nn.Conv2d(in_channels,
                      mid_channels,
                      kernel_size=3,
                      padding=1, bias=False
                      ),
            nn.BatchNorm2d(mid_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(mid_channels,
                      out_channels,
                      kernel_size=3,
                      padding=1,
                      bias=False
                      ),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(inplace=True)
        )

    def forward(self, x: int) -> int:
        return self.double_conv(x)


class DownConv(nn.Module):
    """Downscale with Maxpool and DoubleConv"""

    def __init__(self, in_channels: int, out_channels: int) -> None:
        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 UpConv(nn.Module):
    """Upscale the double conv"""

    def __init__(self,
                 in_channels: int,
                 out_channels: int,
                 bilinear: bool = True
                 ) -> None:
        super().__init__()

        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
            self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
        else:
            self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)
            self.conv = DoubleConv(in_channels, out_channels)

    def forward(self, x1, x2):
        x1 = self.up(x1)

        diffY = x2.size()[2] - x1.size()[2]
        diffX = x2.size()[3] - x1.size()[3]

        x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
                        diffY // 2, diffY - diffY // 2])
        x = torch.cat([x2, x1], dim=1)

        return self.conv(x)


class OutConv(nn.Module):

    def __init__(self, in_channels: int, out_channels: int) -> None:
        super(OutConv, self).__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)

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


class AttentionGate(nn.Module):
    def __init__(self, F_g, F_l, F_int):
        super(AttentionGate, self).__init__()

        # Define the two 1x1 convolutions
        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)
        )

        # Define the final 1x1 convolution that gives the attention coefficients
        self.psi = nn.Sequential(
            nn.Conv2d(F_int, 1, kernel_size=1, stride=1, padding=0, bias=True),
            nn.BatchNorm2d(1),
            nn.Sigmoid()
        )

    def forward(self, g, x):
        # Adjusting spatial dimensions to match
        diffY = x.size()[2] - g.size()[2]
        diffX = x.size()[3] - g.size()[3]
        g = F.pad(g, [diffX // 2, diffX - diffX // 2, diffY // 2, diffY - diffY // 2])

        g1 = self.W_g(g)
        x1 = self.W_x(x)
        psi = self.psi(F.relu(g1 + x1))
        return x * psi