My question is if there is an easy way to track gradients similar to

wandb.watch

@<1523705099182936064:profile|GrievingDeer61> not at the moment, but should be fairly easy to add.
Usually torch examples just use TB as a default logging, which would go directly to clearml , but this is a great idea to add
Could probably go straight to the next version 🙂
wdyt?

👍

Thank you @<1523701205467926528:profile|AgitatedDove14> My question is if there is an easy way to track gradients similar to wandb.watch I understand that there is no alternative in clearml

Hi @<1523705099182936064:profile|GrievingDeer61> ,

Everything coming from Pytorch should be automatically captured and detected. If there is something extra you want to log and track you can do it using the Logger module None

Specifically I think what you're looking for is:
None

@<1523705099182936064:profile|GrievingDeer61> if you see them in your Tensorboard they will be captured in ClearML as well.
wdyt?

EDIT
examples (tensorboard or tensorboardX):
None
None

Adding to the next version to do list! 🙂

Thank you @<1523701070390366208:profile|CostlyOstrich36> Are the gradients automatically captured? I run this pytorch example from clearml and I don’t see the gradients in my workspace. Could you please elaborate?

@<1523701205467926528:profile|AgitatedDove14> Thanks Martin. I think it will be a valuable addition to clearml . Thank you for your help.