Add distillation script for faster inference#54
Merged
Conversation
Flova
changed the title
texhnolyze
reviewed
Feb 6, 2025
texhnolyze
requested changes
Mar 20, 2025
|
|
||
| # Load the learning rate scheduler state if a checkpoint is provided | ||
| if args.checkpoint is not None: | ||
| if args.checkpoint is not None and False: |
Contributor
There was a problem hiding this comment.
This will always result in False.
I assume you meant if args.checkpoint is not None and args.checkpoint is not False in which case I would just do if args.checkpoint:
But I don't really see when it could be False anyway, since it is defined as a str argument.
Member
Author
There was a problem hiding this comment.
It was just a hack to deactivate this code path. I will clean this up with another flag. Because loading the learning rate scheduler state when starting from a pretrained model is not desirable (as the end of the schedule was reached during pretrained). In contrast to that you want to resume the schedule if e.g. the training was interrupted.
texhnolyze
approved these changes
Apr 8, 2025
Flova
added a commit
that referenced
this pull request
Apr 21, 2025
Add distillation script for faster inference
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Proposed changes
This adds an experimental script that is able to distill a diffusion model into one that only does a single step.
Checklist
DDLitLabproject board