Closed uberMaximus closed 7 years ago
For others, @uberMaximus is referring to this line.
I believe it's because I wanted to train the network on images with a 16:9 aspect ratio (the standard aspect ratio for video these days), and I think the KITTI images are taken at a wider aspect ratio, so I just cropped the middle using some pre-calculated numbers.
Ok, Thanks.
I am trying to work out any image pre-processing that was needed for the KITTI data, and wondered if there was any particular reason for the 20:404 array range?
Did you manually resize the images before ingesting or are you "cropping" the X array?