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.