Head 1x1 convolution#189
Merged
Merged
Conversation
added 6 commits
January 16, 2026 12:29
…x1_params when instantiating Wavenet and LayerArray
…nels is different from number of bottleneck channels
Contributor
Author
|
Tests passing, @sdatkinson this is ready for review! |
sdatkinson
requested changes
Jan 19, 2026
sdatkinson
left a comment
sdatkinson
left a comment
Owner
There was a problem hiding this comment.
Pretty good. One crit on a += that I think snuck in.
| endif() | ||
|
|
||
| set(NAM_DEPS_PATH "${CMAKE_CURRENT_SOURCE_DIR}/Dependencies") | ||
| include_directories(SYSTEM "${NAM_DEPS_PATH}/eigen") |
Owner
There was a problem hiding this comment.
Interesting that this wasn't(?) a (big?) problem previously. But I'm not great at CMake :)
| const int bottleneck = layer_config.value("bottleneck", channels); // defaults to channels if not present | ||
|
|
||
| // Parse head1x1 parameters | ||
| bool head1x1_active = layer_config.value("head1x1_active", false); |
Owner
There was a problem hiding this comment.
Nit: if head1x1_active==true, then we shouldn't allow for defaults (we'll make sure they're provided nicely in the trainer).
Nit because it'll still work for now; I just like loud failures :)
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Added a head1x1 convolution layer which processes the output of each layer contributions to the final model output. This updates Wavenet and LayerArray to take a Head1x1Params struct that is used to configure head1x1.
Developed with support and sponsorship from TONE3000