alexgkendall / SegNet-Tutorial

Files for a tutorial to train SegNet for road scenes using the CamVid dataset
http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html
847 stars 517 forks source link

CamVid labels dont seem right #156

Open johnwlambert opened 5 years ago

johnwlambert commented 5 years ago

According to the original paper: "The labeled data has 11 categories: Building, Tree, Sky, Car, Sign-Symbol, Road, Pedestrian, Fence, Column-Pole, Sidewalk, and Bicyclist."

In your tutorial file, you include the Pavement class. Just curious why. Thanks!

980380446 commented 5 years ago

maybe pavement is sidewalk?