GAN concept (generator and discriminator) in TensorFlow

Introduction

A GAN helps a computer learn to create new things, like pictures, by playing a game between two parts: one makes fake things, the other checks if they are real or fake.

When you want to create new images that look real, like faces or art.

When you want to improve blurry or low-quality pictures.

When you want to generate new music or sounds that sound like real ones.

When you want to create new text or handwriting styles.

When you want to learn how to make data that looks like your original data for testing.

Syntax

TensorFlow

import tensorflow as tf
from tensorflow.keras import layers

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

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

The generator tries to create fake data from random noise.

The discriminator tries to tell if data is real or fake.

Examples

This creates a fake image from random noise using the generator.

TensorFlow

generator = make_generator_model()
noise = tf.random.normal([1, 100])
fake_image = generator(noise, training=False)

This checks if the discriminator thinks the fake image is real or fake.

TensorFlow

discriminator = make_discriminator_model()
decision = discriminator(fake_image)

Sample Model

This program builds a simple GAN generator and discriminator. It creates one fake image from random noise and then checks what the discriminator thinks about it.

TensorFlow

import tensorflow as tf
from tensorflow.keras import layers
import numpy as np

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

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

# Create models
generator = make_generator_model()
discriminator = make_discriminator_model()

# Create random noise
noise = tf.random.normal([1, 100])

# Generate fake image
fake_image = generator(noise, training=False)

# Discriminator output
decision = discriminator(fake_image)

print(f"Fake image shape: {fake_image.shape}")
print(f"Discriminator output: {decision.numpy()}")

Important Notes

The generator learns to make better fake images by trying to fool the discriminator.

The discriminator learns to get better at spotting fake images.

Training a GAN means both parts improve by playing against each other.

Summary

A GAN has two parts: generator (makes fake data) and discriminator (checks real or fake).

They learn together by competing, helping the generator create realistic data.

This idea is useful for creating new images, sounds, or data that look real.

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