Image generation basics in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main role of the generator in a GAN?

In a Generative Adversarial Network (GAN), what is the primary function of the generator model?

A To optimize the loss function of the discriminator

B To classify images as real or fake

C To create fake images that try to fool the discriminator

D To preprocess the input images before training

💡 Hint

Think about which part of the GAN creates new images.

The generator's job is to produce new images that look like real data to fool the discriminator into thinking they are real.

❓ Predict Output

intermediate

Output shape of generated images in a simple GAN

Consider the following PyTorch code snippet for a generator outputting images. What is the shape of the generated images tensor?

PyTorch

import torch
import torch.nn as nn

class SimpleGenerator(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(100, 256*8*8)
        self.conv = nn.Sequential(
            nn.ConvTranspose2d(256, 128, 4, 2, 1),
            nn.ReLU(),
            nn.ConvTranspose2d(128, 3, 4, 2, 1),
            nn.Tanh()
        )
    def forward(self, z):
        x = self.fc(z)
        x = x.view(-1, 256, 8, 8)
        x = self.conv(x)
        return x

g = SimpleGenerator()
z = torch.randn(16, 100)
output = g(z)
output.shape

A torch.Size([16, 3, 32, 32])

B torch.Size([16, 100])

C torch.Size([16, 3, 16, 16])

D torch.Size([16, 256, 8, 8])

💡 Hint

Check how the ConvTranspose2d layers change the spatial dimensions.

The first ConvTranspose2d doubles 8x8 to 16x16, the second doubles 16x16 to 32x32, outputting 3 channels.

❓ Hyperparameter

advanced

Choosing the latent vector size in image generation

Which statement best describes the effect of increasing the size of the latent vector (noise input) in a GAN generator?

A Latent vector size does not affect the generator's output

B Larger latent vectors always improve image quality without drawbacks

C Smaller latent vectors produce more diverse images

D Larger latent vectors can increase diversity but may make training harder

💡 Hint

Think about the trade-off between diversity and training complexity.

A larger latent space allows more variety in generated images but can make the model harder to train well.

❓ Metrics

advanced

Evaluating image quality with Inception Score

What does a higher Inception Score (IS) indicate when evaluating generated images?

A Inception Score measures only the speed of generation

B Generated images are more diverse and look more like real images

C Generated images have lower diversity but higher resolution

D Generated images are less realistic but more varied

💡 Hint

IS combines image quality and variety in its score.

A higher IS means the images are both diverse and recognizable as real by a pretrained classifier.

🔧 Debug

expert

Identifying the cause of mode collapse in GAN training

During GAN training, the generator produces very similar images repeatedly, showing mode collapse. Which change is most likely to help reduce this problem?

A Add noise to the discriminator inputs and use label smoothing

B Increase the learning rate of the discriminator significantly

C Use a smaller batch size to reduce noise in gradients

D Remove dropout layers from the generator

💡 Hint

Think about techniques that stabilize GAN training and encourage diversity.

Adding noise and label smoothing helps the discriminator not become too confident, encouraging the generator to explore more diverse outputs.