Training details
vidit98 opened this issue · comments
Vidit commented
Hi, great work the results look really good. I had few questions regarding training
- How long did you train the BSRNet?
- Did you apply the proposed data degradation pipeline on the fly as a data-augmentation technique or you applied it on images beforehand and stored them?
Wenning Wei commented
I also want to know.
On the fly is 10 time slow at least when I try the code.
朱文骁 commented
大家在训练的时候有没有出现GPU间断运行的情况?
HodaKhsh commented
I also want to know. On the fly is 10 time slow at least when I try the code.
@iamadai Did you train BSRGAN with your own data?