GAN for image generation in Computer Vision - Model Pipeline Trace

Model Pipeline - GAN for image generation

This pipeline uses a Generative Adversarial Network (GAN) to create new images that look like real photos. It has two parts: a generator that makes images and a discriminator that checks if images are real or fake. They learn together to improve the image quality.

Data Flow - 5 Stages

1Input Noise Vector

1000 samples x 100 features→Random noise vectors sampled from a normal distribution→1000 samples x 100 features

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

↓

2Generator Network

1000 samples x 100 features→Transforms noise into fake images using layers of neural network→1000 samples x 28 x 28 x 1 (grayscale images)

Generated image pixel values between -1 and 1

↓

3Real Images Input

1000 samples x 28 x 28 x 1→Real images from dataset (e.g., handwritten digits)→1000 samples x 28 x 28 x 1

Image of digit '7' in grayscale

↓

4Discriminator Network

2000 samples x 28 x 28 x 1→Classifies images as real or fake→2000 samples x 1 (probability real)

[0.98, 0.05, 0.87, ..., 0.12]

↓

5Loss Calculation and Backpropagation

Discriminator outputs and labels→Calculate losses for generator and discriminator, update weights→Updated model weights

Discriminator loss: 0.45, Generator loss: 1.2

Training Trace - Epoch by Epoch

Epochs
1  | ***********************
5  | **********************
10 | ********************
20 | ******************
30 | ****************
Loss

Epoch	Loss ↓	Accuracy ↑	Observation
1	Discriminator: 0.69, Generator: 1.38	Discriminator: 50%	Models start learning; discriminator guesses randomly
5	Discriminator: 0.55, Generator: 1.10	Discriminator: 70%	Discriminator improves; generator starts making better images
10	Discriminator: 0.40, Generator: 0.85	Discriminator: 80%	Generator creates more realistic images; discriminator still strong
20	Discriminator: 0.35, Generator: 0.70	Discriminator: 85%	Both models improve steadily; losses decrease
30	Discriminator: 0.30, Generator: 0.60	Discriminator: 88%	Generator produces high-quality images; discriminator confident

Prediction Trace - 4 Layers

Layer 1: Input Noise Vector

Layer 2: Generator Network

Layer 3: Discriminator Network

Layer 4: Output Decision

Model Quiz - 3 Questions

What is the role of the generator in the GAN pipeline?

A Calculate loss values

B Create fake images from noise

C Classify images as real or fake

D Preprocess input images

Key Insight

GANs learn by having two networks compete: the generator tries to fool the discriminator, and the discriminator tries to catch fakes. Over time, this competition improves the generator's ability to create realistic images.

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