search

alterzero / DBPN-Pytorch

The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)
https://alterzero.github.io/projects/DBPN.html
MIT License
565 stars 164 forks source link

gpus should be int #25

Closed drStacky closed 5 years ago

drStacky commented 5 years ago

In the training script main.py, the number of gpus should be in not float:

https://github.com/alterzero/DBPN-Pytorch/blob/9b4b529fc80c7e1732188ce4ef279c4fe294aa86/main.py#L30

The problem is when it's used to make a range:

https://github.com/alterzero/DBPN-Pytorch/blob/9b4b529fc80c7e1732188ce4ef279c4fe294aa86/main.py#L45

drStacky commented 5 years ago

Same problem in eval.py

alterzero commented 5 years ago

Thank you!