You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, thanks for sharing this great work. I have some questions about the code.
I wonder how many steps the program takes to train a model for a 248×186 image like balloons.png.
In my training environment, I can only pip install certifi==2022.9.24, PyWavelets==1.3.0 and tqdm==4.63.1. However, the requirements in your repo are certifi==2022.12.7, PyWavelets==1.4.1 and tqdm==4.64.1. So I wonder if the downgraded version of the three packages will affect my training results. All the other packages are the same as yours.
Thank you in advance!
The text was updated successfully, but these errors were encountered:
Hi,
Thanks for showing interest in our work!
Regarding (1) we ran all our experiments with the default num_timesteps=120000 value. You can experiment with different LR schedules and optimizers to potentially decrease this value and ultimately decrease training time.
As for (2) these package versions shouldn't cause any problems.
Regards,
Vladimir
Hi, thanks for sharing this great work. I have some questions about the code.
balloons.png
.certifi==2022.9.24
,PyWavelets==1.3.0
andtqdm==4.63.1
. However, the requirements in your repo arecertifi==2022.12.7
,PyWavelets==1.4.1
andtqdm==4.64.1
. So I wonder if the downgraded version of the three packages will affect my training results. All the other packages are the same as yours.Thank you in advance!
The text was updated successfully, but these errors were encountered: