Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

How to Actually Remove Any Background with U²-Net

Eran Feit via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This hands-on tutorial walks you through a complete U²-Net pipeline for background removal, demonstrating how to achieve professional results without blurry edges or green screens. Learn to build a U²-Net model in TensorFlow, preprocess datasets into an efficient pipeline, train the model on person segmentation data, and run inference on your own images. The 31-minute video covers everything from installation to implementation, with chapters including an introduction and demo, U²-Net architecture explanation, installation process, model building, custom mode creation, and running inference on single images. Access the complete code through the provided link and explore additional computer vision tutorials on the creator's blog and YouTube playlists focused on Visual Language models and image segmentation techniques.

Syllabus

00:00 Introduction and Demo
02:57 U2-net
04:26 Installation
09:31 Build the U2-net model
13:40 Build a custom mode
26:08 Run inference on a single image

Taught by

Eran Feit

Reviews

Start your review of How to Actually Remove Any Background with U²-Net

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.