AI · Deep Learning · Computer Vision · Generative AI

From GANs to Pix2Pix

2026-08-01 · updated 2026-08-01 · Hyeongrok Ryu

Notes connecting alternating generator and discriminator updates with Pix2Pix conditioning and L1 loss.

Series
2025 Generative Models Intensive · 4
Type / level
study-note · intermediate
Tools
Python, PyTorch
01Two-model game

A checkpoint in the study sequence for this note.

02Gradient path

A checkpoint in the study sequence for this note.

03Reading losses

A checkpoint in the study sequence for this note.

04Pix2Pix

A checkpoint in the study sequence for this note.

A compact concept path generated from this post's table of contents.

Two-model game

The generator produces samples while the discriminator distinguishes real from fake. Their different objectives require separate optimizer steps.

Generator, output, discriminator, and Pix2Pix loss flow
Conditioning and L1 extend the adversarial game to paired image translation.

Gradient path

I detached generated samples during the discriminator update. The generator update preserved the path through D without changing D’s parameters.

Reading losses

A small discriminator loss alone can be misleading. Generated samples, diversity, and both curves are needed to identify imbalance or mode collapse.

Pix2Pix

Pix2Pix conditions both networks on the input. Adversarial loss rewards realistic structure, L1 preserves the paired target, and U-Net skips carry spatial detail.

Planned comparison

The course output image was not saved. I will compare L1-only with adversarial-plus-L1 on the same paired dataset in a new run.

Sources used

Publication first-page preview