Simple GAN implementation in TensorFlow - Model Pipeline Trace

Model Pipeline - Simple GAN implementation

This pipeline shows how a simple Generative Adversarial Network (GAN) learns to create fake images that look like real ones. It has two parts: a generator that makes images and a discriminator that checks if images are real or fake. They train together to improve.

Data Flow - 4 Stages

1Input Noise Vector

1000 rows x 100 columns→Random noise vectors sampled from a normal distribution→1000 rows x 100 columns

[0.12, -0.45, 0.33, ..., 0.05]

↓

2Generator Network

1000 rows x 100 columns→Transforms noise into fake images using dense and reshape layers→1000 rows x 28 x 28 x 1

Generated image pixel values between -1 and 1

↓

3Real Images Input

1000 rows x 28 x 28 x 1→Real images from dataset normalized between -1 and 1→1000 rows x 28 x 28 x 1

Handwritten digit image pixels

↓

4Discriminator Network

1000 rows x 28 x 28 x 1→Classifies images as real or fake using convolutional layers→1000 rows x 1

Probability scores between 0 (fake) and 1 (real)

Training Trace - Epoch by Epoch

Loss
1.2 |****
1.0 |***
0.8 |**
0.6 |**
0.4 |*
0.2 |
    +----------------
     1 5 10 15 20 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.20	0.50	Discriminator starts guessing randomly; generator produces poor images
5	0.85	0.65	Discriminator improves; generator starts making better images
10	0.60	0.75	Generator creates more realistic images; discriminator accuracy rises
15	0.45	0.82	Both networks improve steadily; loss decreases and accuracy increases
20	0.35	0.88	Generator produces convincing images; discriminator accuracy high

Prediction Trace - 4 Layers

Layer 1: Input Noise Vector

Layer 2: Generator Dense Layers

Layer 3: Generator Conv2DTranspose Layers

Layer 4: Discriminator Prediction

Model Quiz - 3 Questions

What is the role of the generator in this GAN?

A Create fake images from noise

B Classify images as real or fake

C Normalize input images

D Calculate loss values

Key Insight

This visualization shows how a GAN trains two networks together: the generator learns to make images that fool the discriminator, while the discriminator learns to better spot fakes. Over time, both improve, leading to realistic generated images.

Practice

1. In a simple GAN, what is the main role of the generator?

easy

A. To classify data as real or fake

B. To create fake data that looks real

C. To optimize the loss function of the discriminator

D. To preprocess the input data

Solution

1. Step 1: Understand the generator's purpose

   The generator's job is to produce fake data samples that resemble real data.

2. Step 2: Differentiate from discriminator's role

   The discriminator's role is to distinguish real from fake data, not the generator's.

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 to fool discriminator [OK]

Common Mistakes:

• Confusing generator with discriminator
• Thinking generator classifies data
• Assuming generator preprocesses data

2. Which of the following is the correct way to define the input noise vector for the generator in TensorFlow?

easy

A. noise = tf.random.normal([batch_size, noise_dim])

B. noise = tf.zeros([batch_size, noise_dim])

C. noise = tf.ones([batch_size, noise_dim])

D. noise = tf.random.uniform([noise_dim])

Solution

1. Step 1: Identify typical noise input shape

   The noise vector usually has shape [batch_size, noise_dim] to generate a batch of samples.

2. Step 2: Check correct TensorFlow function

   tf.random.normal generates random normal noise, commonly used for GAN input.

3. Final Answer:

   noise = tf.random.normal([batch_size, noise_dim]) -> Option A

4. Quick Check:

   Use tf.random.normal with batch size and noise dim [OK]

Hint: Use tf.random.normal with batch and noise dims [OK]

Common Mistakes:

• Using tf.zeros or tf.ones which produce constant noise
• Missing batch dimension in noise shape
• Using tf.random.uniform without batch dimension

3. Given this TensorFlow code snippet for a GAN training step, what will be the shape of fake_output?

noise = tf.random.normal([32, 100])
fake_images = generator(noise)
fake_output = discriminator(fake_images)

medium

A. [32, 1]

B. [100, 32]

C. [32, 100]

D. [1, 32]

Solution

1. Step 1: Analyze input batch size

   The noise input has batch size 32, so generator outputs 32 fake images.

2. Step 2: Understand discriminator output shape

   The discriminator outputs a prediction per image, usually shape [batch_size, 1].

3. Final Answer:

   [32, 1] -> Option A

4. Quick Check:

   Discriminator output shape = [batch_size, 1] [OK]

Hint: Discriminator outputs one score per input image [OK]

Common Mistakes:

• Confusing noise dimension with output shape
• Swapping batch size and feature dimensions
• Assuming discriminator outputs full image shape

4. You have this error during GAN training: ValueError: Shapes (32, 1) and (64, 1) are incompatible. What is the most likely cause?

medium

A. Discriminator model is missing an output layer

B. Generator output shape is incorrect

C. Mismatch between batch sizes of real and fake data during training

D. Noise vector dimension is too large

Solution

1. Step 1: Understand the error message

   The error shows two tensors with batch sizes 32 and 64 being compared or combined.

2. Step 2: Identify cause in GAN training

   Real and fake batches must have the same batch size when computing loss or concatenating.

3. Final Answer:

   Mismatch between batch sizes of real and fake data during training -> Option C

4. Quick Check:

   Batch size mismatch causes shape errors [OK]

Hint: Ensure real and fake batches have same size [OK]

Common Mistakes:

• Ignoring batch size mismatch
• Blaming generator output shape without checking batch
• Assuming model layers missing cause shape error

5. You want to improve your simple GAN's training stability. Which change is best to try first?

hard

A. Train discriminator twice as often as generator

B. Increase noise vector dimension to 1000

C. Remove batch normalization layers from generator

D. Use label smoothing on discriminator labels

Solution

1. Step 1: Understand training stability issues

   GANs often suffer from unstable training causing oscillations or mode collapse.

2. Step 2: Evaluate common techniques

   Label smoothing (e.g., using 0.9 instead of 1 for real labels) helps discriminator not be too confident, improving stability.

3. Final Answer:

   Use label smoothing on discriminator labels -> Option D

4. Quick Check:

   Label smoothing improves GAN training stability [OK]

Hint: Try label smoothing first to stabilize GAN training [OK]

Common Mistakes:

• Increasing noise dimension too much adds complexity
• Removing batch norm can hurt generator learning
• Training discriminator more often can cause imbalance