Concat different types of arrays for training #4389
andreaceruti
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am currently stacking an RGB image that is of uint8 type with another channel that represents the depth that is an uint16 image. Feeding this concatenatiom to the network gives no error and I am wondering if this is conceptually wrong or I should rescale the depth channel to be an uint8 too.
Beta Was this translation helpful? Give feedback.
All reactions