Generator and discriminator in PyTorch - Model Pipeline Trace

Model Pipeline - Generator and discriminator

This pipeline shows how a generator and discriminator work together in a GAN (Generative Adversarial Network). The generator creates fake images, and the discriminator learns to tell real images from fake ones. They improve by competing with each other.

Data Flow - 4 Stages

1Input noise vector

64 rows x 100 columns→Random noise sampled from a normal distribution→64 rows x 100 columns

[0.12, -0.45, 0.33, ..., 0.05]

↓

2Generator network

64 rows x 100 columns→Transforms noise into fake images using layers of neural network→64 rows x 1 x 28 x 28

Tensor of pixel values between -1 and 1 representing fake images

↓

3Real images input

64 rows x 1 x 28 x 28→Batch of real images from dataset→64 rows x 1 x 28 x 28

Tensor of pixel values between -1 and 1 representing real images

↓

4Discriminator network

64 rows x 1 x 28 x 28→Classifies images as real or fake→64 rows x 1

[0.9, 0.1, 0.8, ..., 0.05] (probabilities of being real)

Training Trace - Epoch by Epoch

Loss
1.2 |****
0.9 |***
0.7 |**
0.5 |*
0.4 |

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.55	Loss is high, accuracy near random guessing
2	0.9	0.65	Loss decreased, discriminator starts to learn
3	0.7	0.75	Generator improves, discriminator accuracy increases
4	0.5	0.82	Loss continues to decrease, model converging
5	0.4	0.88	Good balance between generator and discriminator

Prediction Trace - 3 Layers

Layer 1: Input noise vector

Layer 2: Generator network

Layer 3: Discriminator network

Model Quiz - 3 Questions

What is the role of the generator in this pipeline?

A Classify images as real or fake

B Create fake images from noise

C Provide real images from dataset

D Calculate loss function

Key Insight

The generator and discriminator improve together by competing. The generator learns to create more realistic images, while the discriminator gets better at spotting fakes. This balance helps the GAN produce convincing fake images over time.

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