GAN training loop in PyTorch - Model Pipeline Trace

Model Pipeline - GAN training loop

This pipeline trains a Generative Adversarial Network (GAN) where two models, a Generator and a Discriminator, compete. The Generator tries to create fake data that looks real, while the Discriminator tries to tell real data from fake. Over time, both improve through this competition.

Data Flow - 5 Stages

1Load real data

1000 rows x 28 x 28 pixels→Load and normalize images from dataset→1000 rows x 28 x 28 pixels

Real image of handwritten digit '7' normalized between -1 and 1

↓

2Generate fake data

1000 rows x 100 noise features→Generator transforms noise vector into fake images→1000 rows x 28 x 28 pixels

Fake image generated from random noise resembling digit '3'

↓

3Discriminator input

2000 rows x 28 x 28 pixels→Combine real and fake images for discriminator training→2000 rows x 28 x 28 pixels

Batch of 1000 real and 1000 fake images

↓

4Discriminator output

2000 rows x 28 x 28 pixels→Discriminator predicts real (1) or fake (0)→2000 rows x 1

Array of 1s for real images and 0s for fake images

↓

5Generator update

1000 rows x 100 noise features→Generator updated to fool discriminator→1000 rows x 28 x 28 pixels

Generator produces better fake images after update

Training Trace - Epoch by Epoch

Loss (D/G):
1.2 |*         
1.0 | *        
0.8 |  *       
0.6 |   *      
0.4 |    *     
    +----------
     1 2 3 4 5
     Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	Discriminator: 0.65, Generator: 1.20	Discriminator: 0.60	Discriminator starts learning to distinguish real and fake images
2	Discriminator: 0.55, Generator: 1.10	Discriminator: 0.68	Discriminator accuracy improves, Generator loss decreases slightly
3	Discriminator: 0.48, Generator: 0.95	Discriminator: 0.74	Generator starts producing more realistic images, fooling discriminator more
4	Discriminator: 0.42, Generator: 0.85	Discriminator: 0.78	Both models improve steadily; discriminator accuracy rises
5	Discriminator: 0.38, Generator: 0.75	Discriminator: 0.82	Generator creates convincing images; discriminator accuracy high but challenged

Prediction Trace - 3 Layers

Layer 1: Noise vector input

Layer 2: Generator network

Layer 3: Discriminator network

Model Quiz - 3 Questions

What does the generator try to do during training?

A Classify images as real or fake

B Reduce noise in input data

C Create fake data that looks real

D Increase discriminator accuracy

Key Insight

GAN training is a balance where the generator improves by trying to fool the discriminator, and the discriminator improves by learning to spot fakes. Over time, this competition leads to the generator creating realistic data.