Option to continue training from the official checkpoint #99
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
srstevenson
reviewed
Aug 13, 2019
Thanks @srstevenson Co-Authored-By: Scott Stevenson <[email protected]>
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Outdated suggestions cannot be applied.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.
It seems like many people are interested in continuing training from the official checkpoint (e.g. to adapt the model for their own data). As discussed in #35, this pull request adds this possibility by:
forwardmethod inglow_old.py, andInvertible1x1Convwith log absolute determinantDuring training,
glow_oldcan be used by setting theOLD_GLOWenvironment variable to 1 (see the updatedREADME.md).