alexgkendall / caffe-segnet

Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling
http://mi.eng.cam.ac.uk/projects/segnet/
Other
1.08k stars 452 forks source link

Add LaneMarkings and Traffic Light classes to the dataset #106

Open titoghose opened 7 years ago

titoghose commented 7 years ago

The current dataset does not have the lane markings or traffic lights labeled as any class. I need to segment lane markings and traffic lights and hence need to be able to train on the lights and markings present in the original CamVid dataset. How do I calculate the class weights for lane markings and traffic lights.