NVlabs / STEP

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

a problem when train

pokameng opened this issue · comments

RuntimeError: A tensor was not on the same device as the first tensor

When i run the train.py ,i face up with this problem

Are you using multiple GPUs for training?

Please try it on single GPU for now. Then we can try to train it on multiple GPUs.