This is a simple notebook segmenting roads using Unet based model.
Here the present dataset in this repo is the subset(200 images and its masks) of the original dataset (Massachusetts Roads Dataset) consists of 1171 aerial images of the state of Massachusetts. Each image is 1500×1500 pixels in size, covering an area of 2.25 square kilometers
https://www.cs.toronto.edu/~vmnih/data/
This dataset is derived from Volodymyr Mnih's original Massachusetts Roads Dataset. Massachusetts Roads Dataset & Massachusetts Buildings dataset were introduced in Chapter 6 of his PhD thesis. If you use this dataset for research purposes you should use the following citation in any resulting publications:
@phdthesis{MnihThesis,
author = {Volodymyr Mnih},
title = {Machine Learning for Aerial Image Labeling},
school = {University of Toronto},
year = {2013}
}