[FEATURE] Initialization strategies "smallest_and_zeros" and "channel_causal" for channel-slicing slimmable WaveNet#642
Merged
sdatkinson merged 3 commits intomainfrom Mar 11, 2026
Merged
Conversation
- Initialize smallest slice (allowed_channels[0]) with standard Conv1d init - Zero out extra weight/bias for larger channel dimensions - Pass init_strategy from slimmable kwargs through layer factories - Add tests for weight/bias layout, forward, and default-init fallback Made-with: Cursor
…lues - Remove equality check; allow allowed_in != allowed_out when lengths match - Zero w[:c_out, c_in:, :] for each (c_in, c_out) pair - Add test for LayerConv paired case; remove test that expected raise Made-with: Cursor
Iterate (c_in, c_out) pairs by minimum ratio thresholds, alternating increment of c_in or c_out according to which threshold is reached next. Zero w[:c_out, c_in:, :] for each pair. Made-with: Cursor
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add a few different ways to initialize the weights of the slimmable WaveNet