Regularizers #114
Merged
Regularizers #114
Conversation
This file contains 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
Mostly for validating that a score network has enough capacity to learn the ground truth.
…ber of sampling steps.
sblackburn86
approved these changes
Jan 9, 2025
|
|
||
| if end_index == 0: | ||
| end_time = 0.0 | ||
| end_sigma = 0.0 |
There was a problem hiding this comment.
is this correct? I believe sigma(t=0) is sigma_min, not zero.
There was a problem hiding this comment.
considering this is used to compute an "effective" sigma based on start and end sigma, it should not affect the results much.
There was a problem hiding this comment.
Unfortunately, the last two values of sigma_t are identical in the sigma_array. If I set end_sigma = sigma_min, I'll invoke the conditional score method with sigma = 0, which goes poopoo. To avoid this, I set end_sigma to zero here. As you noted, it shouldn't really change anything.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
I implement a Regularizer class to try to regularize the score. I run and analyze some small experiments in the
experimentsfolder.I try various ideas, which are documented in this note: https://www.notion.so/Regularizing-the-Relative-Coordinates-Score-Network-174690083be48092addad80dda88a58b