discriminator.py

import torch
import torch.nn as nn


class CNNBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride):
        super(CNNBlock, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(
                in_channels, out_channels, 4, stride, 1, bias=False, padding_mode="reflect"
            ),
            nn.BatchNorm2d(out_channels),
            nn.LeakyReLU(0.2),
        )

        self.initialize_weights()

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

    def initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.normal_(m.weight, mean=0, std=0.02)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)


class Discriminator(nn.Module):
    def __init__(self, in_channels=3, features=[64, 128, 256, 512]):
        super().__init__()
        self.initial = nn.Sequential(
            nn.Conv2d(
                in_channels * 2,
                features[0],
                kernel_size=4,
                stride=2,
                padding=1,
                padding_mode="reflect",
            ),
            nn.LeakyReLU(0.2),
        )

        layers = []
        in_channels = features[0]
        for feature in features[1:]:
            layers.append(
                CNNBlock(in_channels, feature, stride=1 if feature == features[-1] else 2),
            )
            in_channels = feature

        layers.append(
            nn.Conv2d(
                in_channels, 1, kernel_size=4, stride=1, padding=1, padding_mode="reflect"
            ),
        )

        self.model = nn.Sequential(*layers)

    def forward(self, x, y):
        y = torch.cat([y, y, y], dim=1) # for 3 channel only
        x = torch.cat([x, y], dim=1)
        x = self.initial(x)
        x = self.model(x)
        return x


def test():
    x = torch.randn((1, 3, 256, 256))
    y = torch.randn((1, 1, 256, 256))
    model = Discriminator(in_channels=3)
    preds = model(x, y)
    
    print(preds.shape)

if __name__== "__main__":
    test()