Register ApplyAlpha
layer templates
#499
Merged
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Outdated suggestions cannot be applied.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.
As first noticed by @jmitrevs in #490, since the merge of #395 the
ApplyAlpha
layer is no longer written out. The issue was that the templates weren't registered, so I've added that here. I cherry picked the commit adding the test that @jmitrevs added to expose the problem. It fails on current master, passes on the PR.I started a
quantized_templates.py
module anticipating that we may add more specialized functions / layers for handling scale factors etc for the QONNX work later, so their template registration might go there.