models.py

import torch
import torch.nn as nn

class ConvBlock(nn.Module):
    def __init__(self, in_channels, out_channels, down=True, use_act=True, use_norm=True, activation="relu", **kwargs):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, padding_mode="reflect", **kwargs)
            if down
            else nn.ConvTranspose2d(in_channels, out_channels, **kwargs),
            nn.InstanceNorm2d(out_channels) if use_norm else nn.Identity(),
            nn.ReLU(inplace=True) if activation == "relu" and use_act else
            nn.LeakyReLU(0.2, inplace=True) if activation == "leaky" and use_act else
            nn.Identity(),
        )

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

class ResidualBlock(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.block = nn.Sequential(
            ConvBlock(channels, channels, kernel_size=3, padding=1),
            ConvBlock(channels, channels, use_act=False, kernel_size=3, padding=1),
        )

    def forward(self, x):
        return x + self.block(x)

class Generator(nn.Module):
    def __init__(self, img_channels, num_features=64, num_residuals=9):
        super().__init__()
        self.initial = nn.Sequential(
            nn.Conv2d(img_channels, num_features, kernel_size=7, stride=1, padding=3, padding_mode="reflect"),
            nn.InstanceNorm2d(num_features),
            nn.ReLU(inplace=True),
        )
        self.down_blocks = nn.ModuleList(
            [
                ConvBlock(num_features, num_features * 2, kernel_size=3, stride=2, padding=1),
                ConvBlock(num_features * 2, num_features * 4, kernel_size=3, stride=2, padding=1),
            ]
        )
        self.res_blocks = nn.Sequential(
            *[ResidualBlock(num_features * 4) for _ in range(num_residuals)]
        )
        self.up_blocks = nn.ModuleList(
            [
                ConvBlock(num_features * 4, num_features * 2, down=False, kernel_size=3, stride=2, padding=1, output_padding=1),
                ConvBlock(num_features * 2, num_features, down=False, kernel_size=3, stride=2, padding=1, output_padding=1),
            ]
        )

        self.last = nn.Conv2d(num_features, img_channels, kernel_size=7, stride=1, padding=3, padding_mode="reflect")

    def forward(self, x):
        x = self.initial(x)
        for layer in self.down_blocks:
            x = layer(x)
        x = self.res_blocks(x)
        for layer in self.up_blocks:
            x = layer(x)
        return torch.tanh(self.last(x))

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

        layers = []
        in_channels = features[0]
        for feature in features[1:]:
            layers.append(
                ConvBlock(
                    in_channels, 
                    feature, 
                    stride=1 if feature == features[-1] else 2, 
                    kernel_size=4, 
                    padding=1,
                    activation="leaky"
                )
            )
            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):
        x = self.initial(x)
        return torch.sigmoid(self.model(x))

def test():
    img_channels = 3
    img_size = 256
    x = torch.randn((2, img_channels, img_size, img_size))
    gen = Generator(img_channels, num_residuals=9)
    print(f"Generator output shape: {gen(x).shape}")
    disc = Discriminator(img_channels)
    print(f"Discriminator output shape: {disc(x).shape}")

if __name__ == "__main__":
    test()