DifFace icon indicating copy to clipboard operation
DifFace copied to clipboard

Published 20 hours ago • verified publisher icon zsyOAOA

adjust_lr() missing 1 required argument

Open mshaheryar91 opened this issue 2 years ago • 6 comments

adjust_lr() missing 1 required positional argument: 'ii'adjust_lr() missing 1 required positional argument: 'ii'.

In trainer_py trainer.py", line 255, in train self.adjust_lr()self.adjust_lr()

Please correct me if I am wrong? What to put there? I am trying to train model with batch size [8, 2]

mshaheryar91 avatar Jan 18 '23 11:01 mshaheryar91

I have corrected this problem. Please have a look again. Thanks.

zsyOAOA avatar Jan 19 '23 03:01 zsyOAOA

Can you specify which line have you changed? I will download that file only

mshaheryar91 avatar Jan 19 '23 04:01 mshaheryar91

Ok Dear i got the file, its train.py and i update the code and it's running well. Thanks. Can you please specify on 4, 12GB GPU's roughly how much time it will take to train?

mshaheryar91 avatar Jan 19 '23 06:01 mshaheryar91

I can only run 1k iterations per 12min on the 3090, so I need at least 160h to train the full 800k iterations and 23.9G of GPU memory. Can you please publish your training time?

HWalkingMan avatar Jan 30 '23 10:01 HWalkingMan

I can only run 1k iterations per 12min on the 3090, so I need at least 160h to train the full 800k iterations and 23.9G of GPU memory. Can you please publish your training time?

hi, bro, how many gpus do you use to train? (1 or 8?)

chensming avatar May 18 '23 13:05 chensming

I train the diffusion model with 8 V100 GPUs, about taking one week. Note that you can only implement 500k iteration, having similar performance. @chensming @HWalkingMan

zsyOAOA avatar May 19 '23 01:05 zsyOAOA