search

lingtengqiu / Yolo_Nano

Pytorch implementation of yolo_Nano for pedestrian detection
140 stars 15 forks source link

RuntimeError: The size of tensor a (80) must match the size of tensor b (87) at non-singleton dimension 1 #17

Open kulkarnikeerti opened 2 years ago

kulkarnikeerti commented 2 years ago

Hi, I am trying to train the model with all 80 classes instead of just a single person class.

I have modified the default_path.py as per the requirement, also I am using yolo-nono.cfgand also config/coco.data. But unfortunately I still end up with this error.

Can someone tell me where I am going wrong? or What all needs to be changes if I want to train with 80 classes? @lingtengqiu

thanks