GAN for image generation in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does GAN stand for in machine learning?

GAN stands for Generative Adversarial Network. It is a type of model used to generate new data similar to a given dataset.

beginner

What are the two main parts of a GAN?

A GAN has two parts: the Generator, which creates fake images, and the Discriminator, which tries to tell real images from fake ones.

intermediate

How does the Generator learn to create better images?

The Generator learns by trying to fool the Discriminator. When the Discriminator is tricked, the Generator improves its image creation.

beginner

What is the role of the Discriminator in a GAN?

The Discriminator's role is to classify images as real (from the dataset) or fake (from the Generator). It helps the Generator improve by providing feedback.

intermediate

Why is GAN training considered a game between two networks?

GAN training is like a game because the Generator and Discriminator compete: the Generator tries to create realistic images, and the Discriminator tries to detect fakes. This competition improves both.

What is the main goal of the Generator in a GAN?

A To label images in the dataset

B To classify images as real or fake

C To create images that look real enough to fool the Discriminator

D To reduce the size of the dataset

The Generator tries to create images that look real to trick the Discriminator.

Which part of a GAN decides if an image is real or fake?

A Generator

B Discriminator

C Encoder

D Decoder

The Discriminator's job is to tell if an image is real or generated (fake).

During GAN training, what happens when the Discriminator gets better at spotting fakes?

A The training ends immediately

B The Generator stops learning

C The Discriminator becomes the Generator

D The Generator improves to create more realistic images

As the Discriminator improves, the Generator must create better images to fool it.

What kind of data is typically generated by GANs in image generation tasks?

A New images similar to training images

B Audio signals

C Text descriptions

D Random noise

GANs generate new images that look like the images they were trained on.

Why is GAN training described as adversarial?

A Because the Generator and Discriminator compete against each other

B Because it uses adversarial examples for testing

C Because it trains on adversarial attacks

D Because it uses adversarial loss only for the Discriminator

The Generator and Discriminator compete, which is why the training is called adversarial.

Explain how the Generator and Discriminator work together during GAN training for image generation.

Think of it as a game where one tries to trick the other.

Describe why GANs are useful for generating new images and how their training process helps improve image quality.

Focus on the role of competition and learning from feedback.

Practice

1. What are the two main parts of a GAN used for image generation?

easy

A. Convolution and Pooling

B. Encoder and Decoder

C. Input Layer and Output Layer

D. Generator and Discriminator

Solution

1. Step 1: Understand GAN components

   A GAN consists of two parts: a generator that creates images and a discriminator that evaluates them.

2. Step 2: Match parts to options

   Only Generator and Discriminator correctly names these two parts as Generator and Discriminator.

3. Final Answer:

   Generator and Discriminator -> Option D

4. Quick Check:

   GAN parts = Generator and Discriminator [OK]

Hint: Remember GAN = Generator + Discriminator [OK]

Common Mistakes:

• Confusing GAN parts with autoencoder parts
• Thinking GAN uses Encoder and Decoder
• Mixing up layers with GAN components

2. Which of the following is the correct way to define the generator model in PyTorch for a GAN?

easy

A. generator = nn.Sequential(nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 100), nn.Softmax())

B. generator = nn.Sequential(nn.Conv2d(1, 64, 3), nn.Sigmoid())

C. generator = nn.Sequential(nn.Linear(100, 256), nn.ReLU(), nn.Linear(256, 784), nn.Tanh())

D. generator = nn.Sequential(nn.ConvTranspose2d(100, 1, 3), nn.ReLU())

Solution

1. Step 1: Identify generator input and output sizes

   The generator takes a noise vector (size 100) and outputs an image vector (size 784 for 28x28 images).

2. Step 2: Check model layers and activations

   generator = nn.Sequential(nn.Linear(100, 256), nn.ReLU(), nn.Linear(256, 784), nn.Tanh()) correctly uses Linear layers from 100 to 256 to 784 with ReLU and Tanh activations, common in GAN generators.

3. Final Answer:

   generator = nn.Sequential(nn.Linear(100, 256), nn.ReLU(), nn.Linear(256, 784), nn.Tanh()) -> Option C

4. Quick Check:

   Generator input=100, output=784 with ReLU and Tanh [OK]

Hint: Generator maps noise to image size with Linear + Tanh [OK]

Common Mistakes:

• Using Conv2d instead of Linear for generator input
• Reversing input-output sizes
• Using Softmax instead of Tanh at output

3. Given this PyTorch snippet for a GAN training step, what will be the shape of the generated images tensor?

noise = torch.randn(16, 100)
generated_images = generator(noise)

medium

A. (16, 784)

B. (16, 100)

C. (100, 16)

D. (784, 16)

Solution

1. Step 1: Understand input noise shape

   The noise tensor has shape (16, 100), meaning batch size 16 and noise vector length 100.

2. Step 2: Check generator output shape

   The generator maps each noise vector of size 100 to an image vector of size 784, so output shape is (16, 784).

3. Final Answer:

   (16, 784) -> Option A

4. Quick Check:

   Batch size 16, output image size 784 [OK]

Hint: Output shape matches batch size and image vector size [OK]

Common Mistakes:

• Confusing input noise shape with output shape
• Swapping batch size and feature dimensions
• Assuming output shape is (16, 100)

4. You have this error during GAN training: RuntimeError: size mismatch in Linear layer. What is the most likely cause?

medium

A. The input noise vector size does not match the first Linear layer input size

B. The discriminator output is not a probability

C. The generator uses ReLU instead of Tanh

D. The batch size is too large

Solution

1. Step 1: Understand size mismatch error

   This error usually means the input tensor size does not match the expected input size of a Linear layer.

2. Step 2: Identify likely cause in GAN

   If the noise vector size does not match the first Linear layer's input features in the generator, this error occurs.

3. Final Answer:

   The input noise vector size does not match the first Linear layer input size -> Option A

4. Quick Check:

   Size mismatch = input noise size error [OK]

Hint: Check noise vector size matches Linear layer input [OK]

Common Mistakes:

• Blaming activation functions for size errors
• Thinking batch size causes size mismatch
• Ignoring input dimension mismatch

5. You want to improve the quality of images generated by your GAN. Which of these strategies is most effective?

hard

A. Increase the size of the noise vector and train longer

B. Use a deeper generator and discriminator with batch normalization

C. Remove the discriminator and train only the generator

D. Use random labels instead of real/fake labels for training

Solution

1. Step 1: Consider model architecture improvements

   Deeper networks with batch normalization help stabilize training and improve image quality.

2. Step 2: Evaluate other options

   Increasing noise size alone or removing discriminator harms quality; random labels confuse training.

3. Final Answer:

   Use a deeper generator and discriminator with batch normalization -> Option B

4. Quick Check:

   Better architecture + batch norm = improved GAN images [OK]

Hint: Better models + batch norm improve GAN image quality [OK]

Common Mistakes:

• Thinking bigger noise vector alone improves quality
• Removing discriminator to simplify training
• Using random labels instead of correct ones