GAN training loop in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to generate random noise input for the generator.

PyTorch

noise = torch.randn(batch_size, [1], device=device)

Drag options to blanks, or click blank then click option'

Abatch_size

Blatent_dim

Cimage_size

Dnum_classes

Attempts:

3 left

💡 Hint

Common Mistakes

Using batch_size instead of latent_dim for noise vector size.

Using image_size which is for output images, not input noise.

The generator takes random noise vectors of size latent_dim as input to create fake images.

2fill in blank

medium

Complete the code to calculate the discriminator loss on real images.

PyTorch

output_real = discriminator(real_images)
loss_real = criterion(output_real, [1])

Drag options to blanks, or click blank then click option'

Atorch.ones_like(output_real)

Bnoise

Creal_images

Dtorch.zeros_like(output_real)

Attempts:

3 left

💡 Hint

Common Mistakes

Using zeros for real images labels.

Passing images instead of labels to the loss function.

Real images are labeled as 1 (true) when training the discriminator.

3fill in blank

hard

Fix the error in updating the generator by completing the missing code.

PyTorch

optimizer_G.zero_grad()
fake_images = generator(noise)
output_fake = discriminator(fake_images)
loss_G = criterion(output_fake, [1])
loss_G.backward()
optimizer_G.step()

Drag options to blanks, or click blank then click option'

Atorch.zeros_like(output_fake)

Breal_images

Cfake_images

Dtorch.ones_like(output_fake)

Attempts:

3 left

💡 Hint

Common Mistakes

Using zeros for fake images labels in generator loss.

Passing images instead of labels to the loss function.

The generator tries to fool the discriminator, so fake images are labeled as real (ones) when computing generator loss.

4fill in blank

hard

Fill both blanks to compute discriminator loss on fake images and combine total discriminator loss.

PyTorch

output_fake = discriminator(fake_images.detach())
loss_fake = criterion(output_fake, [1])
loss_D = loss_real + [2]

Drag options to blanks, or click blank then click option'

Atorch.zeros_like(output_fake)

Bloss_fake

Ctorch.ones_like(output_fake)

Dloss_G

Attempts:

3 left

💡 Hint

Common Mistakes

Using ones for fake images labels in discriminator loss.

Adding generator loss instead of fake loss to loss_real.

Fake images are labeled as zeros for discriminator loss. Total discriminator loss is sum of real and fake losses.

5fill in blank

hard

Fill all three blanks to complete the GAN training step: zero gradients, backward pass, and optimizer step for discriminator.

PyTorch

optimizer_D.[1]()
loss_D.[2]()
optimizer_D.[3]()

Drag options to blanks, or click blank then click option'

Azero_grad

Bbackward

Cstep

Ddetach

Attempts:

3 left

💡 Hint

Common Mistakes

Calling step before backward.

Forgetting to zero gradients before backward.

Training step requires clearing gradients, computing gradients with backward, and updating weights with step.

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