Image generation basics in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main goal of image generation in machine learning?

The main goal is to create new images that look realistic or meaningful, often by learning patterns from a set of example images.

intermediate

What is a Generative Adversarial Network (GAN)?

A GAN is a type of model with two parts: a generator that creates images and a discriminator that tries to tell real images from fake ones. They learn together to improve image quality.

intermediate

In PyTorch, which function is commonly used to initialize the weights of a neural network for image generation?

The functions torch.nn.init.normal_ or torch.nn.init.xavier_uniform_ are commonly used to initialize weights to help the model learn better.

beginner

What does the 'latent vector' mean in image generation?

A latent vector is a set of numbers that the generator uses as a starting point to create an image. Changing this vector changes the generated image.

beginner

Why do we use a loss function in training image generation models?

A loss function measures how different the generated images are from real images or desired outputs. It guides the model to improve by reducing this difference.

What are the two main parts of a GAN?

A Generator and Discriminator

B Encoder and Decoder

C Input and Output

D Feature Extractor and Classifier

A GAN consists of a Generator that creates images and a Discriminator that evaluates them.

What does a latent vector represent in image generation?

A A starting point of numbers to generate images

B The final output image

C The loss value during training

D The label of an image

The latent vector is the input to the generator that determines the generated image.

Which PyTorch module is typically used to build the generator network?

A torch.optim.Adam

B torch.nn.CrossEntropyLoss

C torch.utils.data.DataLoader

D torch.nn.Sequential

torch.nn.Sequential helps stack layers to build the generator network.

Why do GANs train the generator and discriminator together?

A To speed up data loading

B To reduce the size of the model

C To improve the generator's image quality by competing with the discriminator

D To increase the number of training images

The generator learns to fool the discriminator, improving image realism.

What is the purpose of the loss function in image generation?

A To display images on screen

B To measure how close generated images are to real images

C To initialize model weights

D To load images from disk

The loss function guides the model to generate better images by measuring errors.

Explain how a Generative Adversarial Network (GAN) works for image generation.

Think of a game where one player makes fake images and the other tries to spot fakes.

Describe the role of the latent vector in generating images.

It's like a secret code that decides what the picture looks like.

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