Fix NameError in EMAVectorQuantizer.__init__#267
Open
Mr-Neutr0n wants to merge 1 commit intoCompVis:masterfrom
Open
Fix NameError in EMAVectorQuantizer.__init__#267Mr-Neutr0n wants to merge 1 commit intoCompVis:masterfrom
Mr-Neutr0n wants to merge 1 commit intoCompVis:masterfrom
Conversation
EMAVectorQuantizer.__init__ references `codebook_dim` and `num_tokens`, which are not defined in the constructor's scope. The correct parameter names are `embedding_dim` and `n_embed` respectively. This causes an immediate NameError when instantiating EMAVectorQuantizer (and by extension, the EMAVQ model), making EMA-based vector quantization completely unusable.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
EMAVectorQuantizer.__init__references two undefined variables —codebook_dimandnum_tokens— instead of the actual constructor parametersembedding_dimandn_embed. This causes an immediateNameErrorwhen instantiatingEMAVectorQuantizer, making EMA-based vector quantization (and theEMAVQmodel) completely unusable.Change
self.codebook_dim = codebook_dim→self.codebook_dim = embedding_dimself.num_tokens = num_tokens→self.num_tokens = n_embedHow to reproduce
After the fix, the constructor correctly assigns from its own parameters and the class works as intended.