Skip to content

Register `ApplyAlpha` layer templates

Javier Duarte requested to merge register_applyalpha into master

Created by: thesps

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.

Merge request reports