pytorch-retinanet icon indicating copy to clipboard operation
pytorch-retinanet copied to clipboard

Published 20 hours ago • verified publisher icon yhenon

using retinanet implementation for localization only, i.e num_classes = 0

Open rajaswa opened this issue 6 years ago • 3 comments

How can we proceed further with the current implementation to use it for a localization task only. I have a custom dataset with no classification requirements as such. I just need to detect the objects position and get the bounding boxes, object class label is not required

rajaswa avatar Jan 31 '19 16:01 rajaswa

hi. Im facing same issue. Need to get the object position . Did you solve it?

BojanAndonovski71 avatar Mar 23 '20 09:03 BojanAndonovski71

Hi, I'm working on a similar issue. Did you get this working?

nathasha-naranpanawa avatar Apr 07 '20 08:04 nathasha-naranpanawa

no. Is it possible to get the orientation of the detected objects with this?

BojanAndonovski71 avatar Apr 09 '20 08:04 BojanAndonovski71