GAN for image generation in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the role of the discriminator in a GAN?

In a Generative Adversarial Network (GAN), what is the main job of the discriminator?

A To generate new images from random noise

B To optimize the generator's weights directly

C To classify images as real or fake

D To reduce the size of the input images

💡 Hint

Think about which part of the GAN decides if an image looks real or fake.

The discriminator's job is to tell apart real images from fake ones created by the generator. It acts like a judge.

❓ Predict Output

intermediate

Output shape of generated images in a GAN

Given the following generator model snippet, what is the shape of the output images?

Computer Vision

import tensorflow as tf
from tensorflow.keras import layers

def build_generator():
    model = tf.keras.Sequential([
        layers.Dense(7*7*128, use_bias=False, input_shape=(100,)),
        layers.BatchNormalization(),
        layers.LeakyReLU(),
        layers.Reshape((7, 7, 128)),
        layers.Conv2DTranspose(64, (5,5), strides=(2,2), padding='same', use_bias=False),
        layers.BatchNormalization(),
        layers.LeakyReLU(),
        layers.Conv2DTranspose(1, (5,5), strides=(2,2), padding='same', use_bias=False, activation='tanh')
    ])
    return model

gen = build_generator()
output_shape = gen.output_shape

A (None, 28, 28, 1)

B (None, 14, 14, 64)

C (None, 7, 7, 128)

D (None, 32, 32, 3)

💡 Hint

Check the effect of Conv2DTranspose layers with stride 2 and padding 'same' on spatial dimensions.

The generator starts with a 7x7 feature map, then upsamples twice by factor 2, resulting in 28x28 output with 1 channel.

❓ Hyperparameter

advanced

Choosing the learning rate for GAN training

Which learning rate is most appropriate to start training a GAN to avoid unstable training?

A 1.0

B 0.01

C 0.1

D 0.0002

💡 Hint

GANs are sensitive to learning rates; too high causes instability.

Typical GAN training uses a small learning rate like 0.0002 to keep training stable and avoid mode collapse.

❓ Metrics

advanced

Evaluating GAN image quality with Inception Score

What does a higher Inception Score indicate when evaluating GAN-generated images?

A Generated images have lower resolution

B Generated images are more diverse and realistic

C Generated images are more similar to training images pixel-wise

D Generated images have more noise

💡 Hint

Inception Score measures both quality and variety of generated images.

A higher Inception Score means the images look realistic and cover many different classes or styles, showing diversity and quality.

🔧 Debug

expert

Identifying cause of mode collapse in GAN training

During GAN training, the generator produces very similar images repeatedly, losing diversity. What is the most likely cause?

A Discriminator is too weak and easily fooled

B Generator learning rate is too low

C Batch size is too large

D Noise input dimension is too high

💡 Hint

Mode collapse happens when the generator finds a small set of outputs that fool the discriminator easily.

If the discriminator is weak, the generator can cheat by producing limited outputs that fool it, causing mode collapse.

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