Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn how to implement and train a U-Net model for person segmentation using TensorFlow and Keras in this comprehensive tutorial. Dive into data preprocessing, U-Net architecture design, model training, and evaluation. Begin by loading and preparing the persons dataset, including image resizing and mask conversion. Explore the U-Net model architecture, constructing encoder and decoder components with Keras. Train the model using optimized parameters and callbacks for improved performance. Finally, evaluate the trained model on test data and visualize predicted segmentation masks. Gain hands-on experience in advanced computer vision techniques for human image segmentation.
Syllabus
Intro !!!!!!!
The U-net architecture
Download the dataset and prepare the data
Build The U-net model
Train the model
Test the model with new fresh images
Taught by
Eran Feit