Make plain U-net available on score_sde_pytorch side #35
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
2 tasks
henryaddison
force-pushed
the
u-net-score-module
branch
8 times, most recently
from
cb37f44 to
b23301f
Compare
in theory this should replace the mirroring deterministic package but obviously we should test this once blue pebble is back up properly also include configs for a now more tuned config for plain det unet and one that resembles the old det unet config more closely
henryaddison
force-pushed
the
u-net-score-module
branch
from
b23301f to
3794813
Compare
so can basically disable EMA with a flag. This is another difference between u-net trained on score_sde side deterministically and the separate deterministic training approach."" In theory decay rate of 1 should allow this but it's complicated by a num_updates params too
a rate of 1 means no EMA this is backwards compatible unlike adding a new config attribute
henryaddison
force-pushed
the
u-net-score-module
branch
from
3794813 to
869127c
Compare
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Outdated suggestions cannot be applied.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.
Now that a way to train determinstic models using the same training loop as the score sde models, add a way to use the same u-net implementation as on the deterministic package (so eventually can remove that seperate deterministic package)
Plus add some helper scripts for testing on JASMIN