Training time
zzw-zwzhang opened this issue · 6 comments
Hi, thanks for your interesting work.
What is your training time on each dataset?
In our paper, we use pre-trained models from other papers.
We also train new models by ourselves and find maybe 24h is enough for cifar10 using 2 RTX3090s and set batch_size 256.
Thank you for your reply.
I use the default DDIM code to train the cifar with 80w steps, but fid is 187. I will try your code again.
Hi, I retrained the CIFAR10 based on your default parameters, but the reproduced result is worse than your provided model. For example,
DDIM 50 steps: 6.1640 vs. 14.3992
Python main.py --runner train --device cuda --config ddim_cifar10.yml --method DDIM --train_path temp/train
Can you provide any suggestions?
All models we provide are from other public repo.
- Maybe you can connect with the author of DDIM for more information?
- Maybe you can change the loss type from linear to square and try again similar to DDIM?
Thanks for your reply. I will try it again.
Before that, I had trained the model based on the DDIM code, but it failed.
ermongroup/ddim#6 (comment)
Perhaps you can refer to my other code DiffOOD, which contains a complete training code. I get FID 3.2 on CIFAR10 by myself.