model.py

"""
DCGAN Generator and Discriminator for 64x64 texture image generation.
"""
import torch
import torch.nn as nn


# Latent vector size
LATENT_DIM = 100
# Number of feature maps in generator
NGF = 64
# Number of feature maps in discriminator
NDF = 64
# Number of color channels
NC = 3


class Generator(nn.Module):
    """
    DCGAN Generator: maps a latent vector (100-dim) to a 64x64 RGB image.
    Architecture: Linear -> Reshape -> TransposedConv blocks -> Tanh
    """
    def __init__(self, latent_dim=LATENT_DIM, ngf=NGF, nc=NC):
        super(Generator, self).__init__()
        self.main = nn.Sequential(
            # Input: latent_dim x 1 x 1
            nn.ConvTranspose2d(latent_dim, ngf * 8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 8),
            nn.ReLU(True),
            # State: (ngf*8) x 4 x 4

            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            # State: (ngf*4) x 8 x 8

            nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            # State: (ngf*2) x 16 x 16

            nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            # State: (ngf) x 32 x 32

            nn.ConvTranspose2d(ngf, nc, 4, 2, 1, bias=False),
            nn.Tanh()
            # Output: nc x 64 x 64
        )

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


class Discriminator(nn.Module):
    """
    DCGAN Discriminator: classifies 64x64 RGB images as real or fake.
    Architecture: Conv blocks -> Sigmoid
    """
    def __init__(self, ndf=NDF, nc=NC):
        super(Discriminator, self).__init__()
        self.main = nn.Sequential(
            # Input: nc x 64 x 64
            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            # State: ndf x 32 x 32

            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            # State: (ndf*2) x 16 x 16

            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            # State: (ndf*4) x 8 x 8

            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            # State: (ndf*8) x 4 x 4

            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
            # Output: 1 x 1 x 1
        )

    def forward(self, x):
        return self.main(x).view(-1, 1).squeeze(1)


def weights_init(m):
    """Initialize weights from a normal distribution (DCGAN paper recommendation)."""
    classname = m.__class__.__name__
    if classname.find('Conv') != -1:
        nn.init.normal_(m.weight.data, 0.0, 0.02)
    elif classname.find('BatchNorm') != -1:
        nn.init.normal_(m.weight.data, 1.0, 0.02)
        nn.init.constant_(m.bias.data, 0)