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.

Practice

1. What is the main role of a generator in image generation using PyTorch?

easy

A. To create new images from random noise

B. To classify images into categories

C. To reduce the size of images

D. To label images with tags

Solution

1. Step 1: Understand the generator's purpose

   A generator is a neural network designed to produce new data, often images, from random noise inputs.

2. Step 2: Differentiate from other network roles

   Unlike classifiers or reducers, generators focus on creating new images, not labeling or compressing them.

3. Final Answer:

   To create new images from random noise -> Option A

4. Quick Check:

   Generator = create images from noise [OK]

Hint: Generators make images from noise, not classify or compress [OK]

Common Mistakes:

• Confusing generator with classifier
• Thinking generator reduces image size
• Assuming generator labels images

2. Which PyTorch code snippet correctly initializes a noise tensor for image generation?

easy

A. noise = torch.randn(16, 100)

B. noise = torch.zeros(16, 100)

C. noise = torch.ones(16, 100)

D. noise = torch.randint(0, 1, (16, 100))

Solution

1. Step 1: Identify noise initialization for generators

   Generators typically use random noise from a normal distribution, which torch.randn provides.

2. Step 2: Check other options

   Zeros or ones do not provide randomness; randint with 0 to 1 range is invalid as upper bound is exclusive.

3. Final Answer:

   noise = torch.randn(16, 100) -> Option A

4. Quick Check:

   Random normal noise = torch.randn [OK]

Hint: Use torch.randn for random normal noise input [OK]

Common Mistakes:

• Using zeros or ones instead of random noise
• Incorrect use of torch.randint with invalid range
• Confusing noise shape dimensions

3. Given this PyTorch generator output code, what is the shape of the generated images?

import torch
noise = torch.randn(8, 100)
generator = torch.nn.Sequential(
    torch.nn.Linear(100, 256),
    torch.nn.ReLU(),
    torch.nn.Linear(256, 784),
    torch.nn.Tanh()
)
fake_images = generator(noise)

medium

A. (8, 28, 28)

B. (100, 256)

C. (8, 784)

D. (256, 784)

Solution

1. Step 1: Trace the generator output shape

   The last Linear layer outputs 784 features per input, so for batch size 8, output shape is (8, 784).

2. Step 2: Understand image reshaping

   784 corresponds to 28x28 pixels flattened; reshaping to (8, 28, 28) is done later, not shown here.

3. Final Answer:

   (8, 784) -> Option C

4. Quick Check:

   Output shape = (batch_size, 784) [OK]

Hint: Output shape matches last Linear layer output size [OK]

Common Mistakes:

• Assuming output is already 2D image shape
• Confusing input noise shape with output
• Mixing intermediate layer shapes

4. Identify the error in this PyTorch generator code snippet:

import torch
class Generator(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = torch.nn.Linear(100, 784)
    def forward(self, x):
        x = self.fc(x)
        x = torch.sigmoid(x)
        return x
noise = torch.randn(16, 100)
gen = Generator()
output = gen(noise).reshape(16, 28, 28)

medium

A. Missing batch normalization layers

B. Not calling super().__init__() in constructor

C. Incorrect reshape dimensions for output

D. Using sigmoid activation instead of tanh

Solution

1. Step 1: Check activation function for image generation

   Image generation often uses tanh to scale outputs between -1 and 1, matching normalized image data.

2. Step 2: Analyze impact of sigmoid

   Sigmoid outputs between 0 and 1, which may mismatch expected scaling and reduce image quality.

3. Final Answer:

   Using sigmoid activation instead of tanh -> Option D

4. Quick Check:

   Activation should be tanh, not sigmoid [OK]

Hint: Use tanh for output scaling in image generation [OK]

Common Mistakes:

• Thinking reshape dimensions are wrong
• Believing batch norm is mandatory here
• Forgetting to call super().__init__()

5. You want to generate 64 images of size 32x32 with pixel values scaled between -1 and 1 using a PyTorch generator. Which output layer and activation setup is best?

hard

A. Linear layer with 1024 outputs followed by sigmoid activation

B. Linear layer with 1024 outputs followed by tanh activation

C. Linear layer with 1024 outputs followed by ReLU activation

D. Linear layer with 1024 outputs followed by softmax activation

Solution

1. Step 1: Calculate output size for 32x32 images

   32x32 = 1024 pixels, so output layer must have 1024 units to represent each pixel.

2. Step 2: Choose activation for scaling pixel values

   Tanh activation scales outputs between -1 and 1, matching the desired pixel value range.

3. Step 3: Evaluate other activations

   Sigmoid outputs 0 to 1, ReLU outputs 0 to infinity, softmax is for classification, so they are unsuitable here.

4. Final Answer:

   Linear layer with 1024 outputs followed by tanh activation -> Option B

5. Quick Check:

   Output size 1024 + tanh for [-1,1] scaling [OK]

Hint: Use tanh activation for output scaled between -1 and 1 [OK]

Common Mistakes:

• Using sigmoid instead of tanh for output scaling
• Choosing softmax for image pixel output
• Ignoring correct output size for image dimensions