Image generation basics in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a random noise tensor for image generation.

PyTorch

noise = torch.randn([1], 100, 1, 1)

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

A128

B32

C64

D16

Attempts:

3 left

💡 Hint

Common Mistakes

Using a batch size too large for memory causing out-of-memory errors.

Confusing the noise vector size with batch size.

The batch size for generating images is commonly set to 32 for training stability and speed.

2fill in blank

medium

Complete the code to define the output shape of the generated image tensor.

PyTorch

output = generator(noise)
print(output.shape)  # Should be ([1], 3, 64, 64)

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

A32

B16

C64

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing image channels or spatial dimensions with batch size.

Using a batch size different from the noise input.

The output batch size matches the input noise batch size, which is 32 here.

3fill in blank

hard

Fix the error in the generator model's forward pass to correctly reshape the noise input.

PyTorch

def forward(self, input):
    x = input.view([1], 100, 1, 1)
    output = self.main(x)
    return output

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

Ainput.shape[0]

Binput.shape[1]

Cinput.size(1)

Dinput.size(0)

Attempts:

3 left

💡 Hint

Common Mistakes

Using input.size(1) which is the noise vector size, not batch size.

Using input.shape which is valid but inconsistent with PyTorch style.

input.size(0) correctly gets the batch size dimension to reshape the noise tensor.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps image labels to their counts.

PyTorch

label_counts = {label: labels.count([1]) for label in set([2])}

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

Alabel

Blabels

Clabel_

Dlabel_counts

Attempts:

3 left

💡 Hint

Common Mistakes

Using a variable not defined in the comprehension.

Confusing the key and value variables.

We count how many times each label appears in the labels list by iterating over unique labels.

5fill in blank

hard

Fill all three blanks to complete the training loop snippet for the generator model.

PyTorch

for epoch in range(num_epochs):
    for i, data in enumerate(dataloader):
        noise = torch.randn([1], 100, 1, 1)
        fake_images = generator([2])
        loss = criterion(fake_images, data[[3]])
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

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

Abatch_size

Bnoise

C0

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong index for images in data tuple.

Passing wrong variable to generator.

The noise tensor uses the batch size, the generator input is noise, and real images are at index 0 in data.

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