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.