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.