Generator and discriminator in PyTorch - Model Pipeline Trace

Model Pipeline - Generator and discriminator

This pipeline shows how a generator and discriminator work together in a GAN (Generative Adversarial Network). The generator creates fake images, and the discriminator learns to tell real images from fake ones. They improve by competing with each other.

Data Flow - 4 Stages

1Input noise vector

64 rows x 100 columns→Random noise sampled from a normal distribution→64 rows x 100 columns

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

↓

2Generator network

64 rows x 100 columns→Transforms noise into fake images using layers of neural network→64 rows x 1 x 28 x 28

Tensor of pixel values between -1 and 1 representing fake images

↓

3Real images input

64 rows x 1 x 28 x 28→Batch of real images from dataset→64 rows x 1 x 28 x 28

Tensor of pixel values between -1 and 1 representing real images

↓

4Discriminator network

64 rows x 1 x 28 x 28→Classifies images as real or fake→64 rows x 1

[0.9, 0.1, 0.8, ..., 0.05] (probabilities of being real)

Training Trace - Epoch by Epoch

Loss
1.2 |****
0.9 |***
0.7 |**
0.5 |*
0.4 |

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.55	Loss is high, accuracy near random guessing
2	0.9	0.65	Loss decreased, discriminator starts to learn
3	0.7	0.75	Generator improves, discriminator accuracy increases
4	0.5	0.82	Loss continues to decrease, model converging
5	0.4	0.88	Good balance between generator and discriminator

Prediction Trace - 3 Layers

Layer 1: Input noise vector

Layer 2: Generator network

Layer 3: Discriminator network

Model Quiz - 3 Questions

What is the role of the generator in this pipeline?

A Classify images as real or fake

B Create fake images from noise

C Provide real images from dataset

D Calculate loss function

Key Insight

The generator and discriminator improve together by competing. The generator learns to create more realistic images, while the discriminator gets better at spotting fakes. This balance helps the GAN produce convincing fake images over time.