Script to combine generator and detector checkpoints into a single one for training #41
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
facebook-github-bot
added
the
CLA Signed
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Outdated suggestions cannot be applied.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.
Why ?
The preprocessed generator and detector checkpoints (e.g. those provided with the ICML24 paper) cannot be used directly as starting point to train the model as the training expects a single cohesive checkpoint for the whole model.
How ?
The script
scripts/combine_checkpoints.pysimply reverses the detector/generator separation done inscripts/checkpoints.py.I am mostly unsure about the handling of 'xp.cfg' when recombining the checkpoint.
Test plan
The changes can be tested with
pytest tests/test_combine_checkpoints.py.