GAN concept (generator and discriminator) in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define the generator model input layer.

TensorFlow

from tensorflow.keras import layers, models

def build_generator():
    model = models.Sequential()
    model.add(layers.Input(shape=([1],)))
    model.add(layers.Dense(128, activation='relu'))
    model.add(layers.Dense(784, activation='sigmoid'))
    return model

Drag options to blanks, or click blank then click option'

A1

B784

C100

D28

Attempts:

3 left

💡 Hint

Common Mistakes

Using the output image size (784) as input shape

Using 1 or 28 which are not typical noise vector sizes

The generator takes a noise vector as input, commonly of size 100.

2fill in blank

medium

Complete the code to define the discriminator model output layer.

TensorFlow

def build_discriminator():
    model = models.Sequential()
    model.add(layers.Input(shape=(784,)))
    model.add(layers.Dense(128, activation='relu'))
    model.add(layers.Dense([1], activation='sigmoid'))
    return model

Drag options to blanks, or click blank then click option'

A1

B784

C128

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using output size equal to input size (784)

Using multiple output neurons instead of one

The discriminator outputs a single probability value (1) indicating real or fake.

3fill in blank

hard

Fix the error in the GAN training step where the generator is updated.

TensorFlow

import tensorflow as tf

@tf.function
def train_step(generator, discriminator, real_images, batch_size, noise_dim, generator_optimizer, discriminator_optimizer, loss_fn):
    noise = tf.random.normal([batch_size, [1]])
    with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
        generated_images = generator(noise, training=True)
        real_output = discriminator(real_images, training=True)
        fake_output = discriminator(generated_images, training=True)
        gen_loss = loss_fn(tf.ones_like(fake_output), fake_output)
        disc_loss = loss_fn(tf.ones_like(real_output), real_output) + loss_fn(tf.zeros_like(fake_output), fake_output)
    gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
    gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)
    generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
    discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))

Drag options to blanks, or click blank then click option'

A100

B1

C784

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Using image size (784) as noise dimension

Using 1 or 128 which are incorrect noise sizes

The noise dimension must match the generator input size, which is 100.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps noise vectors to generated images only if the noise norm is greater than 1.

TensorFlow

noise_vectors = [tf.random.normal([100]) for _ in range(5)]
generated_dict = [1]: generator([2], training=False) for [1] in noise_vectors if tf.norm([2]) > 1}

Drag options to blanks, or click blank then click option'

Anoise

Bnv

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names in the comprehension causing errors

Using 'noise' and 'nv' inconsistently

Use 'nv' as the variable name for noise vectors consistently in the comprehension.

5fill in blank

hard

Fill all three blanks to create a training loop that runs for epochs, generates noise, and trains the GAN.

TensorFlow

epochs = 10
batch_size = 32
noise_dim = [1]
generator_optimizer = tf.keras.optimizers.Adam()
discriminator_optimizer = tf.keras.optimizers.Adam()

for epoch in range([2]):
    noise = tf.random.normal([[3], noise_dim])
    # Assume real_images is loaded batch
    train_step(generator, discriminator, real_images, batch_size, noise_dim, generator_optimizer, discriminator_optimizer, loss_fn)

Drag options to blanks, or click blank then click option'

A100

B10

C32

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Mismatching noise dimension and generator input size

Using wrong batch size in noise generation

Using wrong number of epochs

Noise dimension is 100, epochs is 10, batch size is 32 matching the noise batch size.

Practice

1.

What is the main role of the generator in a GAN?

easy

A. To classify data as real or fake

B. To create fake data that looks real

C. To label data for supervised learning

D. To reduce the size of the dataset

Solution

1. Step 1: Understand the generator's purpose

   The generator's job is to produce new data that mimics real data.

2. Step 2: Differentiate from discriminator

   The discriminator checks data authenticity, but the generator creates fake data.

3. Final Answer:

   To create fake data that looks real -> Option B

4. Quick Check:

   Generator = create fake data [OK]

Hint: Generator makes fake data, discriminator checks it [OK]

Common Mistakes:

• Confusing generator with discriminator
• Thinking generator labels data
• Assuming generator reduces data size

2.

Which of the following is the correct way to define a simple generator model in TensorFlow Keras?

def make_generator_model():
    model = tf.keras.Sequential([
        tf.keras.layers.Dense(7*7*256, use_bias=False, input_shape=(100,)),
        tf.keras.layers.BatchNormalization(),
        tf.keras.layers.LeakyReLU(),
        tf.keras.layers.Reshape((7, 7, 256)),
        tf.keras.layers.Conv2DTranspose(128, 5, strides=1, padding='same', use_bias=False),
        tf.keras.layers.BatchNormalization(),
        tf.keras.layers.LeakyReLU(),
        tf.keras.layers.Conv2DTranspose(1, 5, strides=2, padding='same', activation='tanh')
    ])
    return model

easy

A. The model is missing an input layer

B. The activation function 'tanh' is incorrect for generator output

C. The code correctly defines a generator model

D. The Dense layer should have bias enabled

Solution

1. Step 1: Check model layers and input

   The model starts with a Dense layer with input_shape=(100,), which is correct for noise input.

2. Step 2: Verify output activation and structure

   The last Conv2DTranspose uses 'tanh' activation, common for generator output scaled between -1 and 1.

3. Final Answer:

   The code correctly defines a generator model -> Option C

4. Quick Check:

   Generator model code is correct [OK]

Hint: Generator output often uses tanh activation [OK]

Common Mistakes:

• Forgetting input_shape in first layer
• Using wrong activation for output layer
• Enabling bias unnecessarily in Dense layer

3.

Given the following code snippet for a discriminator model, what will be the output shape after the last Conv2D layer?

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(64, 5, strides=2, padding='same', input_shape=(28, 28, 1)),
    tf.keras.layers.LeakyReLU(),
    tf.keras.layers.Dropout(0.3),
    tf.keras.layers.Conv2D(128, 5, strides=2, padding='same'),
    tf.keras.layers.LeakyReLU(),
    tf.keras.layers.Dropout(0.3),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(1)
])

medium

A. (7, 7, 128)

B. (14, 14, 128)

C. (28, 28, 64)

D. (1, 1, 1)

Solution

1. Step 1: Calculate output after first Conv2D

   Input is (28,28,1), stride=2, padding='same' halves spatial dims: (14,14,64).

2. Step 2: Calculate output after second Conv2D

   Again stride=2, padding='same' halves spatial dims: (7,7,128).

3. Final Answer:

   (7, 7, 128) -> Option A

4. Quick Check:

   Conv2D output shape = (7,7,128) [OK]

Hint: Stride 2 halves spatial dimensions with 'same' padding [OK]

Common Mistakes:

• Forgetting padding='same' keeps output size rounded up
• Misapplying stride effect on dimensions
• Confusing number of filters with spatial size

4.

Identify the error in this GAN training step code snippet:

noise = tf.random.normal([batch_size, noise_dim])
generated_images = generator(noise, training=True)
real_output = discriminator(real_images, training=True)
fake_output = discriminator(generated_images, training=False)

loss = generator_loss(fake_output) + discriminator_loss(real_output, fake_output)

medium

A. Discriminator should be in training mode for fake images

B. Generator should not use training=True during generation

C. Noise shape is incorrect for generator input

D. Loss calculation should not combine generator and discriminator losses

Solution

1. Step 1: Check discriminator training mode

   Discriminator must be in training mode for both real and fake images to update weights properly.

2. Step 2: Identify incorrect training flag

   Here, discriminator(fake images) uses training=False, which disables training behavior like dropout.

3. Final Answer:

   Discriminator should be in training mode for fake images -> Option A

4. Quick Check:

   Discriminator training mode = True for all inputs [OK]

Hint: Discriminator trains on both real and fake data [OK]

Common Mistakes:

• Setting discriminator training=False on fake data
• Confusing generator training flag
• Incorrect noise shape assumptions

5.

You want to improve a GAN to generate clearer images. Which combined approach is best?

1. Increase generator depth and add batch normalization
2. Use a weaker discriminator to avoid overpowering generator
3. Train discriminator more times per generator update
4. Remove dropout layers from discriminator

hard

A. Options 2 and 4 together are best

B. Options 1 and 2 together are best

C. Only option 1 is best

D. Options 1 and 3 together are best

Solution

1. Step 1: Evaluate option 1

   Increasing generator depth and adding batch normalization helps create clearer, stable images.

2. Step 2: Evaluate option 3

   Training discriminator more per generator update helps discriminator learn better, pushing generator to improve.

3. Step 3: Assess options 2 and 4

   Weaker discriminator or removing dropout can reduce training quality and cause poor results.

4. Final Answer:

   Options 1 and 3 together are best -> Option D

5. Quick Check:

   Improve generator + stronger discriminator training = better images [OK]

Hint: Stronger generator + more discriminator training = clearer images [OK]

Common Mistakes:

• Weakening discriminator hurts GAN balance
• Removing dropout may cause overfitting
• Ignoring batch normalization benefits