Fix scale calculation in attention mechanism #314
Merged
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
Modified the scale calculation in the attention mechanism to use the instance's scale value instead of a local variable. This change ensures that the scaling factor is consistent with the object's state.
Changed from:
if exists(self.scale):
default_scale = q.shape[-1]
q = q * (scale / default_scale)
To:
if exists(self.scale):
default_scale = q.shape[-1]
q = q * (self.scale / default_scale)
|
@dev-jinwoohong oops, thanks! |
WillyChap
pushed a commit
to WillyChap/denoising-diffusion-pytorch
that referenced
this pull request
Sep 27, 2024
Fix scale calculation in attention mechanism
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Outdated suggestions cannot be applied.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.
Modified the scale calculation in the attention mechanism to use the instance's scale value instead of a local variable. This change ensures that the scaling factor is consistent with the object's state.
Changed from:
if exists(self.scale):
default_scale = q.shape[-1]
q = q * (scale / default_scale)
To:
if exists(self.scale):
default_scale = q.shape[-1]
q = q * (self.scale / default_scale)