GAN training loop in PyTorch - Model Pipeline Trace

Model Pipeline - GAN training loop

This pipeline trains a Generative Adversarial Network (GAN) where two models, a Generator and a Discriminator, compete. The Generator tries to create fake data that looks real, while the Discriminator tries to tell real data from fake. Over time, both improve through this competition.

Data Flow - 5 Stages

1Load real data

1000 rows x 28 x 28 pixels→Load and normalize images from dataset→1000 rows x 28 x 28 pixels

Real image of handwritten digit '7' normalized between -1 and 1

↓

2Generate fake data

1000 rows x 100 noise features→Generator transforms noise vector into fake images→1000 rows x 28 x 28 pixels

Fake image generated from random noise resembling digit '3'

↓

3Discriminator input

2000 rows x 28 x 28 pixels→Combine real and fake images for discriminator training→2000 rows x 28 x 28 pixels

Batch of 1000 real and 1000 fake images

↓

4Discriminator output

2000 rows x 28 x 28 pixels→Discriminator predicts real (1) or fake (0)→2000 rows x 1

Array of 1s for real images and 0s for fake images

↓

5Generator update

1000 rows x 100 noise features→Generator updated to fool discriminator→1000 rows x 28 x 28 pixels

Generator produces better fake images after update

Training Trace - Epoch by Epoch

Loss (D/G):
1.2 |*         
1.0 | *        
0.8 |  *       
0.6 |   *      
0.4 |    *     
    +----------
     1 2 3 4 5
     Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	Discriminator: 0.65, Generator: 1.20	Discriminator: 0.60	Discriminator starts learning to distinguish real and fake images
2	Discriminator: 0.55, Generator: 1.10	Discriminator: 0.68	Discriminator accuracy improves, Generator loss decreases slightly
3	Discriminator: 0.48, Generator: 0.95	Discriminator: 0.74	Generator starts producing more realistic images, fooling discriminator more
4	Discriminator: 0.42, Generator: 0.85	Discriminator: 0.78	Both models improve steadily; discriminator accuracy rises
5	Discriminator: 0.38, Generator: 0.75	Discriminator: 0.82	Generator creates convincing images; discriminator accuracy high but challenged

Prediction Trace - 3 Layers

Layer 1: Noise vector input

Layer 2: Generator network

Layer 3: Discriminator network

Model Quiz - 3 Questions

What does the generator try to do during training?

A Classify images as real or fake

B Reduce noise in input data

C Create fake data that looks real

D Increase discriminator accuracy

Key Insight

GAN training is a balance where the generator improves by trying to fool the discriminator, and the discriminator improves by learning to spot fakes. Over time, this competition leads to the generator creating realistic data.

Practice

1. In a GAN training loop, what is the main role of the discriminator?

easy

A. To calculate the learning rate

B. To generate new fake data samples

C. To distinguish between real and fake data

D. To optimize the generator's weights directly

Solution

1. Step 1: Understand the discriminator's purpose

   The discriminator's job is to tell apart real data from fake data created by the generator.

2. Step 2: Differentiate roles in GAN

   The generator creates fake data, while the discriminator judges it. It does not generate data or adjust learning rates.

3. Final Answer:

   To distinguish between real and fake data -> Option C

4. Quick Check:

   Discriminator = spot fake data [OK]

Hint: Discriminator judges data authenticity, generator creates data [OK]

Common Mistakes:

• Confusing discriminator with generator
• Thinking discriminator generates data
• Assuming discriminator sets learning rate

2. Which of the following is the correct way to zero the gradients of both generator and discriminator optimizers in PyTorch during a GAN training loop?

easy

A. optimizer_G.clear(); optimizer_D.clear()

B. optimizer_G.zero_grad(); optimizer_D.zero_grad()

C. optimizer_G.reset_grad(); optimizer_D.reset_grad()

D. optimizer_G.zero(); optimizer_D.zero()

Solution

1. Step 1: Recall PyTorch optimizer method

   In PyTorch, the method to clear gradients before backpropagation is zero_grad().

2. Step 2: Check each option's validity

   Only optimizer_G.zero_grad(); optimizer_D.zero_grad() uses zero_grad(), which is the correct method. Other options use non-existent methods.

3. Final Answer:

   optimizer_G.zero_grad(); optimizer_D.zero_grad() -> Option B

4. Quick Check:

   Clear gradients = zero_grad() [OK]

Hint: Use zero_grad() to clear gradients before backward pass [OK]

Common Mistakes:

• Using non-existent optimizer methods
• Forgetting to zero gradients before backward
• Confusing zero_grad() with optimizer step()

3. Given the following PyTorch GAN training snippet, what will be the printed output for print(loss_D.item(), loss_G.item()) after one iteration?

real_data = torch.ones(4)
fake_data = torch.zeros(4)
criterion = torch.nn.BCELoss()

# Discriminator output
output_real = torch.tensor([0.9, 0.8, 0.95, 0.85])
output_fake = torch.tensor([0.1, 0.2, 0.05, 0.15])

loss_real = criterion(output_real, real_data)
loss_fake = criterion(output_fake, fake_data)
loss_D = (loss_real + loss_fake) / 2

# Generator tries to fool discriminator
output_fake_for_G = torch.tensor([0.4, 0.3, 0.5, 0.6])
loss_G = criterion(output_fake_for_G, real_data)

print(loss_D.item(), loss_G.item())

medium

A. Approximately 0.693 and 0.105

B. Approximately 0.0 and 1.0

C. Approximately 0.5 and 0.5

D. Approximately 0.136 and 0.831

Solution

1. Step 1: Calculate discriminator loss

   Loss_real = BCELoss([0.9,0.8,0.95,0.85], [1,1,1,1]) ≈ 0.136; Loss_fake = BCELoss([0.1,0.2,0.05,0.15], [0,0,0,0]) ≈ 0.136; Average loss_D ≈ 0.136.

2. Step 2: Calculate generator loss

   Generator tries to fool discriminator, so loss_G = BCELoss([0.4,0.3,0.5,0.6], [1,1,1,1]) ≈ 0.831.

3. Final Answer:

   Approximately 0.136 and 0.831 -> Option D

4. Quick Check:

   Discriminator loss < Generator loss [OK]

Hint: Discriminator loss low near 0, generator loss higher when fooled less [OK]

Common Mistakes:

• Mixing up real and fake labels in loss
• Confusing which loss belongs to generator
• Ignoring averaging of discriminator losses

4. Identify the error in this GAN training loop snippet and select the fix:

for real_data in dataloader:
    optimizer_D.zero_grad()
    output_real = discriminator(real_data)
    loss_real = criterion(output_real, torch.ones_like(output_real))

    fake_data = generator(torch.randn(batch_size, noise_dim))
    output_fake = discriminator(fake_data.detach())
    loss_fake = criterion(output_fake, torch.zeros_like(output_fake))

    loss_D = loss_real + loss_fake
    loss_D.backward()
    optimizer_D.step()

    optimizer_G.zero_grad()
    output_fake_for_G = discriminator(fake_data)
    loss_G = criterion(output_fake_for_G, torch.ones_like(output_fake_for_G))
    loss_G.backward()
    optimizer_D.step()

medium

A. Replace last optimizer_D.step() with optimizer_G.step()

B. Add optimizer_G.zero_grad() before loss_G.backward()

C. Detach fake_data before passing to generator

D. Use torch.zeros_like for output_fake_for_G labels

Solution

1. Step 1: Analyze optimizer steps

   After computing generator loss and backward, the generator's optimizer should update weights, not discriminator's.

2. Step 2: Identify incorrect optimizer call

   The code calls optimizer_D.step() twice; the second should be optimizer_G.step() to update generator.

3. Final Answer:

   Replace last optimizer_D.step() with optimizer_G.step() -> Option A

4. Quick Check:

   Generator update uses optimizer_G.step() [OK]

Hint: Generator updates need optimizer_G.step(), not optimizer_D.step() [OK]

Common Mistakes:

• Calling discriminator optimizer twice
• Forgetting to update generator weights
• Misplacing zero_grad calls

5. You want to improve GAN training stability by modifying the training loop. Which change below best helps prevent the discriminator from overpowering the generator?

hard

A. Train the discriminator less frequently than the generator

B. Increase the learning rate of the discriminator only

C. Remove the generator's loss calculation

D. Use the same optimizer instance for both models

Solution

1. Step 1: Understand discriminator overpowering

   If the discriminator learns too fast, the generator receives poor feedback and training stalls.

2. Step 2: Evaluate options to balance training

   Training discriminator less often than generator slows its learning, giving generator a chance to improve.

3. Final Answer:

   Train the discriminator less frequently than the generator -> Option A

4. Quick Check:

   Balance training frequency to stabilize GAN [OK]

Hint: Train discriminator less often to balance GAN training [OK]

Common Mistakes:

• Increasing discriminator learning rate worsens imbalance
• Removing generator loss stops generator learning
• Sharing optimizer causes parameter update conflicts