search

YapengTian / TDAN-VSR-CVPR-2020

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution, CVPR 2020
MIT License
400 stars 62 forks source link

number of batch and loss scale #19

Closed YoungJoongUNC closed 4 years ago

YoungJoongUNC commented 4 years ago

Hello!

If I use 1 gpu with batch size 1, then I get the average loss of 0.06945 after 1 epoch. If I use 4 gpu with batch size 4, then I get the average loss of 2.56850 after 1 epoch.

May I ask why is the loss scale different?

YoungJoongUNC commented 4 years ago

Sorry, the loss scale became same after more epochs.