Fix torch regressions in PLNPCA and PLNnetwork#159
Open
EngineerDanny wants to merge 4 commits intoPLN-team:masterfrom
Open
Fix torch regressions in PLNPCA and PLNnetwork#159EngineerDanny wants to merge 4 commits intoPLN-team:masterfrom
EngineerDanny wants to merge 4 commits intoPLN-team:masterfrom
Conversation
EngineerDanny
force-pushed
the
fix/torch-regressions
branch
from
a1337bf to
e804dac
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR fixes torch backend regressions in
PLNPCAandPLNnetwork.Changes
PLNPCAtorchloglik_vecto match the existing rank backend andproject()by adding a torch VE-step for projectionPLNnetworktorch fitting by passing only tensorizable data to the inherited torch optimizerOmegaallocation pass device/dtype wellPLNPCAandPLNnetworktorch pathsValidation
Note
There are other
PLNvariants that dont support torch yet fully (PLNmixture,ZIPLN,ZIPLNnetwork), I just haven't used them in my analysis yet. So if I use them, then I will submit PR for them as well.