Solve the failure of using the train.py file during the yolov3spp code running process

 

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu

reported this issue

In the util.py script add

at = at.to(j.device)

Make these two variables run on the same device to directly train.py file

Guess you like

Origin blog.csdn.net/sinat_34626178/article/details/130532435