Common Training Loss Curve of DCGAN and WGAN

class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()

        self.init_size = opt.img_size // 4
        self.l1 = nn.Sequential(nn.Linear(opt.latent_dim, 128 * self.init_size ** 2))

        self.conv_blocks = nn.Sequential(
            nn.BatchNorm2d(128),
            nn.Upsample(scale_factor=2),
            nn.Conv2d(128, 128, 3, stride=1, padding=1),
            nn.BatchNorm2d(128, 0.8),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Upsample(scale_factor=2),
            nn.Conv2d(128, 64, 3, stride=1, padding=1),
            nn.BatchNorm2d(64, 0.8),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(64, opt.channels, 3, stride=1, padding=1),
            nn.Tanh(),
        )

    def forward(self, z):
        out = self.l1(z)
        out = out.view(out.shape[0], 128, self.init_size, self.init_size)
        img = self.conv_blocks(out)
        return img

class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()

        def discriminator_block(in_filters, out_filters, bn=True):
            block = [nn.Conv2d(in_filters, out_filters, 3, 2, 1), nn.LeakyReLU(0.2, inplace=True), nn.Dropout2d(0.25)]
            if bn:
                block.append(nn.BatchNorm2d(out_filters, 0.8))
            return block

        self.model = nn.Sequential(
            *discriminator_block(opt.channels, 16, bn=False),
            *discriminator_block(16, 32),
            *discriminator_block(32, 64),
            *discriminator_block(64, 128),
        )

        # The height and width of downsampled image
        ds_size = opt.img_size // 2 ** 4
        self.adv_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, 1), nn.Sigmoid())

    def forward(self, img):
        out = self.model(img)
        out = out.view(out.shape[0], -1)
        validity = self.adv_layer(out)

        return validity

adversarial_loss = torch.nn.BCELoss()

# -----------------
#  Train Generator
# -----------------

optimizer_G.zero_grad()

# Sample noise as generator input
z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))

# Generate a batch of images
gen_imgs = generator(z)

# Loss measures generator's ability to fool the discriminator
g_loss = adversarial_loss(discriminator(gen_imgs), valid)

g_loss.backward()
optimizer_G.step()

# ---------------------
#  Train Discriminator
# ---------------------

optimizer_D.zero_grad()

# Measure discriminator's ability to classify real from generated samples
real_loss = adversarial_loss(discriminator(real_imgs), valid)
fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
d_loss = (real_loss + fake_loss) / 2

d_loss.backward()
optimizer_D.step()

# Sample noise as generator input
z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))

# Generate a batch of images
fake_imgs = generator(z)

# Real images
real_validity = discriminator(real_imgs)
# Fake images
fake_validity = discriminator(fake_imgs)
# Gradient penalty
gradient_penalty = compute_gradient_penalty(discriminator, real_imgs.data, fake_imgs.data)
# Adversarial loss
d_loss = -torch.mean(real_validity) + torch.mean(fake_validity) + lambda_gp * gradient_penalty

d_loss.backward()
optimizer_D.step()

optimizer_G.zero_grad()

# Train the generator every n_critic steps
if i % opt.n_critic == 0:
    # Generate a batch of images
    fake_imgs = generator(z)
    
    # Loss measures generator's ability to fool the discriminator
    # Train on fake images
    fake_validity = discriminator(fake_imgs)
    g_loss = -torch.mean(fake_validity)
    g_loss.backward()
    optimizer_G.step()

def compute_gradient_penalty(D, real_samples, fake_samples):
    """Calculates the gradient penalty loss for WGAN GP"""
    # Random weight term for interpolation between real and fake samples
    alpha = Tensor(np.random.random((real_samples.size(0), 1, 1, 1)))
    # Get random interpolation between real and fake samples
    interpolates = (alpha * real_samples + ((1 - alpha) * fake_samples)).requires_grad_(True)
    d_interpolates = D(interpolates)
    fake = Variable(Tensor(real_samples.shape[0], 1).fill_(1.0), requires_grad=False)
    # Get gradient w.r.t. interpolates
    gradients = autograd.grad(
        outputs=d_interpolates,
        inputs=interpolates,
        grad_outputs=fake,
        create_graph=True,
        retain_graph=True,
        only_inputs=True,
    )[0]
    gradients = gradients.view(gradients.size(0), -1)
    gradient_penalty = ((gradients.norm(2, dim=1) - 1) ** 2).mean()
    return gradient_penalty