Phase 1: Convolutional Neural Networks · ~75 minutes · Python

Semantic Segmentation — U-Net

Segmentation is classification at every pixel. U-Net makes it work by pairing a downsampling encoder with an upsampling decoder and wiring skip connections between them.

What you will learn

Distinguish semantic, instance, and panoptic segmentation and pick the right task for a given problem
Build a U-Net from scratch in PyTorch with encoder blocks, a bottleneck, a decoder with transposed convolutions, and skip connections
Implement pixel-wise cross-entropy, Dice loss, and the combined loss that is the current default for medical and industrial segmentation
Read IoU and Dice metrics per class and diagnose whether a bad score comes from small-object recall, boundary accuracy, or class imbalance

Introduction

Type: Build
Languages: Python
Prerequisites: Image Classification
Time: ~75 minutes

Objective

Learning objectives

Distinguish semantic, instance, and panoptic segmentation and pick the right task for a given problem
Build a U-Net from scratch in PyTorch with encoder blocks, a bottleneck, a decoder with transposed convolutions, and skip connections
Implement pixel-wise cross-entropy, Dice loss, and the combined loss that is the current default for medical and industrial segmentation
Read IoU and Dice metrics per class and diagnose whether a bad score comes from small-object recall, boundary accuracy, or class imbalance

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.