Module.py

import torch
import torchvision
import torch.nn as nn
import torchvision.transforms as trans
from torch.utils.data import Dataset, DataLoader
import torchvision.models as models
import torch.nn.functional as F
from torchvision.models.vgg import vgg16

import numpy as np

from CommonFunc import *

# we appreciate the pytorch code from the following source as the basic foundation
# UNET: https://github.com/milesial/Pytorch-UNet
# SRGAN: https://github.com/leftthomas/SRGAN

class DoubleConv(nn.Module):
    """(convolution => [BN] => ReLU) * 2"""

    def __init__(self, in_channels, out_channels, mid_channels=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),
            nn.BatchNorm2d(mid_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(mid_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):
    """Downscaling with maxpool then double conv"""

    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):
    """Upscaling then double conv"""

    def __init__(self, in_channels, out_channels, bilinear=False):
        super().__init__()

        # if bilinear, use the normal convolutions to reduce the number of channels
        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)
        # input is CHW
        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])
        # if you have padding issues, see
        # https://github.com/HaiyongJiang/U-Net-Pytorch-Unstructured-Buggy/commit/0e854509c2cea854e247a9c615f175f76fbb2e3a
        # https://github.com/xiaopeng-liao/Pytorch-UNet/commit/8ebac70e633bac59fc22bb5195e513d5832fb3bd
        x = torch.cat([x2, x1], dim=1)
        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)
        self.Sigmoid = nn.Sigmoid()

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


class Segmentor(nn.Module):
    def __init__(self, n_channels, n_outchannels=1, bilinear=False):
        super(Segmentor, self).__init__()
        self.n_channels = n_channels
        self.n_outchannels = n_outchannels
        self.bilinear = bilinear

        # Siamese Network
        self.inc = DoubleConv(n_channels, 64)
        self.down1 = Down(64, 128)
        self.down2 = Down(128, 256)
        self.down3 = Down(256, 512)
        factor = 2 if bilinear else 1
        self.down4 = Down(512, 1024 // factor)
        self.up1 = Up(2048, 1024 // factor, bilinear)
        self.up2 = Up(1024, 512 // factor, bilinear)
        self.up3 = Up(512, 256 // factor, bilinear)
        self.up4 = Up(256, 128, bilinear)
        self.outc = OutConv(128, n_outchannels)

    def forward(self, x1, x2):
        x1_1 = self.inc(x1)
        x2_1 = self.inc(x2)
        x_1 = torch.cat([x1_1, x2_1], dim=1)

        x1_2 = self.down1(x1_1)
        x2_2 = self.down1(x2_1)
        x_2 = torch.cat([x1_2, x2_2], dim=1)

        x1_3 = self.down2(x1_2)
        x2_3 = self.down2(x2_2)
        x_3 = torch.cat([x1_3, x2_3], dim=1)

        x1_4 = self.down3(x1_3)
        x2_4 = self.down3(x2_3)
        x_4 = torch.cat([x1_4, x2_4], dim=1)

        x1_5 = self.down4(x1_4)
        x2_5 = self.down4(x2_4)
        x_5 = torch.cat([x1_5, x2_5], dim=1)

        x = self.up1(x_5, x_4)
        x = self.up2(x, x_3)
        x = self.up3(x, x_2)
        x = self.up4(x, x_1)
        logits = self.outc(x)

        return logits

class Generator(nn.Module):
    def __init__(self, n_channels):
        super(Generator, self).__init__()
        self.block1 = nn.Sequential(
            nn.Conv2d(n_channels, 64, kernel_size=9, padding=4),
            nn.PReLU()
        )
        self.block2 = ResidualBlock(64)
        self.block3 = ResidualBlock(64)
        self.block4 = ResidualBlock(64)
        self.block5 = ResidualBlock(64)
        self.block6 = ResidualBlock(64)
        self.block7 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, padding=1),
            nn.BatchNorm2d(64)
        )
        self.block8 = nn.Conv2d(64, n_channels, kernel_size=9, padding=4)

    def forward(self, x):
        block1 = self.block1(x)
        x = self.block2(block1)
        x = self.block3(x)
        x = self.block4(x)
        x = self.block5(x)
        x = self.block6(x)
        x = self.block7(x)
        x = self.block8(block1 + x)
        # x = self.block8(x)

        # return (torch.tanh(x) + 1) / 2
        return x

class ResidualBlock(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(channels)
        self.prelu = nn.PReLU()
        self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(channels)

    def forward(self, x):
        residual = self.conv1(x)
        residual = self.bn1(residual)
        residual = self.prelu(residual)
        residual = self.conv2(residual)
        residual = self.bn2(residual)

        return x + residual

class Discriminator_SRGAN_simple(nn.Module):
    def __init__(self, n_channels=3):
        super(Discriminator_SRGAN_simple, self).__init__()
        self.net = nn.Sequential(
            nn.Conv2d(n_channels, 64, kernel_size=3, stride=2, padding=1),
            nn.LeakyReLU(0.2, inplace=True),

            nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(128),
            nn.LeakyReLU(0.2, inplace=True),

            nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(256),
            nn.LeakyReLU(0.2, inplace=True),

            nn.Conv2d(256, 512, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(512),
            nn.LeakyReLU(0.2, inplace=True)
        )

        self.classifier = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(512, 1024, kernel_size=1),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(1024, 1, kernel_size=1)
        )

    def forward(self, x, y):
        x = self.net(x)
        y = self.net(y)
        batch_size = x.size(0)
        return torch.sigmoid(self.classifier(x-y).view(batch_size))