diffusers
diffusers copied to clipboard
Textual inv make save log both steps
Based on this issue. Still a WIP. I'm trying to keep the logging functionality to be the same as the same functionality where every x amounts of steps, we log.
I was thinking of moving the logic of the logging to a function. But then I need a way to get wandb there. I was thinking of passing it in as a default parameter or if available, automatically import. Let me know if anyone has some ideas for this.
The documentation is not available anymore as the PR was closed or merged.
will try fixing the checks. Bit confused why it failed though.
@isamu-isozaki I'm not sure I see what logic would have to be moved to a function? Regardless, I do think importing wandb on the top level of the module is better as I don't think there's intention to scope the import to the function.
@williamberman Thanks for the review! Ah if we just going with steps then no worries! I was mainly talking about if we want to support logging either for steps or epochs
Will fix merge conflict
Hey @isamu-isozaki we just updated some style dependencies cf #2279 , so you'll need to update the diffusers with
pip install --upgrade -e .["quality"]
Rebase the branch and then run make style
.
Let me know if you need any help with this.
Sounds good! Fixing merge conflict and style now
@patil-suraj @williamberman Should be fixed! One small note. When testing I noticed that the default train_batch_size is 16 which might be a bit tough for non-high-end gpus.
Interesting. I'll try fixing my version of black and fix the styles
I do have black version 23.1.0 which should be exactly the same. I'll see if I can figure out the issue.
Looks basically there :)
@patrickvonplaten @williamberman Thanks a bunch for the reviews! Will fix now
@patrickvonplaten @williamberman Should be fixed! For the deprecation warning, I did it after the dataset creation because that's when we know the size of each epoch. For everything else should be fixed!
Testing now
Ok, I don't know if this is a bug with the code but for the first image, it doesn't log. But after the second one, it starts logging. Will double-check.
By not logging, I mean the pipeline gets run but it doesn't go to wandb.
Actually, I noticed this in general with wandb. Sorry, prob not relevant.
Anyways should be done!
@williamberman could you check here?
Thanks a lot @isamu-isozaki
@patrickvonplaten np! Always happy to contribute