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

Separate input concatenation in segnet #136

Open ShastriRam opened 6 years ago

ShastriRam commented 6 years ago

This isn't so much an issue, but I am seeking some advice and assistance. I am using segnet for outdoor terrain recognition. I have my raw images, as well as my labelled images. I would also like to include as input into the network, the speed at which the robot was driving when the images were taken. To be more specific, for each image, I would have an associated velocity in float format. How would I go about doing this? I am using the attached prototxt. I would really appreciate any help. mySegNetTrain.zip