Generator and discriminator in PyTorch

Introduction

Generator and discriminator are two parts of a system that learn together. The generator tries to create fake data that looks real, and the discriminator tries to tell real data from fake data.

When you want to create new images that look like real photos.

When you want to improve a model by making it compete against another model.

When you want to generate new music or text that sounds natural.

When you want to learn features from data without labels.

When you want to create art or designs automatically.

Syntax

PyTorch

class Generator(nn.Module):
    def __init__(self):
        super().__init__()
        # define layers
    def forward(self, x):
        # generate fake data
        return generated_data

class Discriminator(nn.Module):
    def __init__(self):
        super().__init__()
        # define layers
    def forward(self, x):
        # predict real or fake
        return prediction

The generator creates fake data from random noise.

The discriminator outputs a score showing if data is real or fake.

Examples

A simple generator that makes 28x28 images from 100 random numbers.

PyTorch

class Generator(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(100, 28*28)
    def forward(self, x):
        x = self.linear(x)
        x = torch.sigmoid(x)
        return x.view(-1, 1, 28, 28)

A simple discriminator that outputs a probability if the image is real.

PyTorch

class Discriminator(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(28*28, 1)
    def forward(self, x):
        x = x.view(-1, 28*28)
        x = self.linear(x)
        return torch.sigmoid(x)

Sample Model

This code shows a simple training step for generator and discriminator. The discriminator learns to tell real from fake data. The generator learns to fool the discriminator.

PyTorch

import torch
import torch.nn as nn
import torch.optim as optim

class Generator(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(100, 28*28)
    def forward(self, x):
        x = self.linear(x)
        x = torch.sigmoid(x)
        return x.view(-1, 1, 28, 28)

class Discriminator(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(28*28, 1)
    def forward(self, x):
        x = x.view(-1, 28*28)
        x = self.linear(x)
        return torch.sigmoid(x)

# Create models
G = Generator()
D = Discriminator()

# Optimizers
opt_G = optim.Adam(G.parameters(), lr=0.001)
opt_D = optim.Adam(D.parameters(), lr=0.001)

# Loss function
criterion = nn.BCELoss()

# Fake noise input
noise = torch.randn(4, 100)

# Real data (random for example)
real_data = torch.rand(4, 1, 28, 28)

# Labels
real_labels = torch.ones(4, 1)
fake_labels = torch.zeros(4, 1)

# Train Discriminator
opt_D.zero_grad()
# Real data loss
output_real = D(real_data)
loss_real = criterion(output_real, real_labels)
# Fake data loss
fake_data = G(noise).detach()  # detach to avoid training G here
output_fake = D(fake_data)
loss_fake = criterion(output_fake, fake_labels)
# Total loss and backward
loss_D = loss_real + loss_fake
loss_D.backward()
opt_D.step()

# Train Generator
opt_G.zero_grad()
fake_data = G(noise)
output = D(fake_data)
loss_G = criterion(output, real_labels)  # want D to think fake is real
loss_G.backward()
opt_G.step()

print(f"Discriminator loss: {loss_D.item():.4f}")
print(f"Generator loss: {loss_G.item():.4f}")
print(f"Discriminator real output: {output_real.detach().cpu().numpy().flatten()}")
print(f"Discriminator fake output: {output_fake.detach().cpu().numpy().flatten()}")

Important Notes

The generator and discriminator train in turns to improve each other.

Use sigmoid activation in the last layer of discriminator for probability output.

Detach fake data when training discriminator to avoid updating generator weights.

Summary

The generator creates fake data from random noise.

The discriminator tries to tell real data from fake data.

They train together to improve the quality of generated data.

Practice

1. What is the main role of the generator in a GAN (Generative Adversarial Network)?

easy

A. To classify data as real or fake

B. To optimize the loss function of the discriminator

C. To create fake data from random noise

D. To preprocess the input data

Solution

1. Step 1: Understand the generator's purpose

   The generator's job is to produce new data that looks like the real data by starting from random noise.

2. Step 2: Differentiate from discriminator's role

   The discriminator's role is to tell real data from fake, not to create data.

3. Final Answer:

   To create fake data from random noise -> Option C

4. Quick Check:

   Generator creates fake data = B [OK]

Hint: Generator makes fake data; discriminator checks it [OK]

Common Mistakes:

• Confusing generator with discriminator
• Thinking generator classifies data
• Assuming generator preprocesses data

2. Which of the following is the correct way to define a simple discriminator model in PyTorch?

easy

A. class Discriminator(nn.Module):
def __init__(self):
self.fc = nn.Linear(784, 1)
def forward(self, x):
return torch.sigmoid(self.fc(x))

B. def Discriminator():
return nn.Linear(784, 1)

C. class Discriminator:
def __init__(self):
self.fc = nn.Linear(784, 1)
def forward(self, x):
return torch.sigmoid(self.fc(x))

D. class Discriminator(nn.Module):
def __init__(self):
super().__init__()
self.fc = nn.Linear(784, 1)
def forward(self, x):
return torch.sigmoid(self.fc(x))

Solution

1. Step 1: Check PyTorch model class structure

   A PyTorch model must inherit from nn.Module and call super().__init__() in __init__.

2. Step 2: Verify forward method and layers

   class Discriminator(nn.Module): def __init__(self): super().__init__() self.fc = nn.Linear(784, 1) def forward(self, x): return torch.sigmoid(self.fc(x)) correctly defines the class with inheritance, super call, layer, and forward method.

3. Final Answer:

   Correct PyTorch discriminator class with inheritance and super call -> Option D

4. Quick Check:

   Proper nn.Module subclass = A [OK]

Hint: PyTorch models inherit nn.Module and call super().__init__() [OK]

Common Mistakes:

• Forgetting to inherit nn.Module
• Missing super().__init__() call
• Defining forward outside class

3. Given this PyTorch code snippet for a generator and discriminator, what will be the output shape of fake_output?

noise = torch.randn(16, 100)
generator = Generator()
fake_data = generator(noise)
discriminator = Discriminator()
fake_output = discriminator(fake_data)

Assume generator outputs shape (16, 784) and discriminator outputs shape (batch_size, 1).

medium

A. torch.Size([16, 1])

B. torch.Size([16, 784])

C. torch.Size([100, 16])

D. torch.Size([1, 16])

Solution

1. Step 1: Understand generator output shape

   The generator outputs fake data with shape (16, 784), meaning batch size 16 and 784 features.

2. Step 2: Understand discriminator input and output shape

   The discriminator takes input of shape (16, 784) and outputs shape (16, 1), one score per sample.

3. Final Answer:

   torch.Size([16, 1]) -> Option A

4. Quick Check:

   Discriminator output shape = (batch_size, 1) = A [OK]

Hint: Discriminator outputs one score per input sample [OK]

Common Mistakes:

• Confusing input and output shapes
• Mixing batch size and feature dimensions
• Assuming output shape matches noise size

4. Identify the error in this discriminator training step code snippet:

optimizer.zero_grad()
output = discriminator(fake_data)
loss = criterion(output, real_labels)
loss.backward()
optimizer.step()

Assuming fake_data is generated by the generator and real_labels are labels for real data.

medium

A. Using real_labels for fake_data loss calculation

B. Not calling optimizer.zero_grad() before backward

C. Using fake_data instead of real_data for discriminator input

D. Missing loss.backward() call

Solution

1. Step 1: Check input and labels for discriminator

   The discriminator should compare fake_data with fake labels, not real_labels.

2. Step 2: Identify label mismatch in loss calculation

   Using real_labels with fake_data causes wrong loss and training signals.

3. Final Answer:

   Using real_labels for fake_data loss calculation -> Option A

4. Quick Check:

   Fake data needs fake labels = C [OK]

Hint: Match fake data with fake labels during discriminator training [OK]

Common Mistakes:

• Mixing real and fake labels
• Skipping zero_grad() call
• Forgetting loss.backward()

5. You want to improve your GAN training stability. Which technique involving the discriminator can help reduce mode collapse and improve generator quality?

hard

A. Use dropout only in the generator

B. Use label smoothing on discriminator targets

C. Remove the discriminator and train generator alone

D. Increase generator learning rate only

Solution

1. Step 1: Understand mode collapse and training stability

   Mode collapse happens when generator produces limited outputs; discriminator tricks help prevent it.

2. Step 2: Identify label smoothing effect

   Label smoothing softens discriminator targets, preventing it from becoming too confident and stabilizing training.

3. Final Answer:

   Use label smoothing on discriminator targets -> Option B

4. Quick Check:

   Label smoothing stabilizes discriminator = D [OK]

Hint: Smooth discriminator labels to stabilize GAN training [OK]

Common Mistakes:

• Ignoring discriminator role in stability
• Changing only generator learning rate
• Removing discriminator breaks GAN