Simplify inference optimizations by
(1) using eval() to disable dropout instead of explicitly setting dropout modules to None;
(2) always using default value inplace=False for activation modules.
Pull Request Checklist
[x] Changes are complete (if posting work-in-progress code, prefix your pull request title with '[WIP]'
until you can check this box.
[x] Unit tests pass (pytest)
[ ] Were system tests modified? If so did you run these at least 5 times to account for the variation across runs?
[x] System tests pass (pytest test/system)
[x] Passed code style checking (./style-check.sh)
[ ] You have considered writing a test
[x] Updated major/minor version in sockeye/__init__.py. Major version bump if this is a backwards incompatible change.
[x] Updated CHANGELOG.md
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
This PR refactors inference optimizations:
inference_onlymode switchable.eval()to disable dropout instead of explicitly setting dropout modules to None; (2) always using default valueinplace=Falsefor activation modules.Pull Request Checklist
pytest)Were system tests modified? If so did you run these at least 5 times to account for the variation across runs?pytest test/system)./style-check.sh)You have considered writing a testsockeye/__init__.py. Major version bump if this is a backwards incompatible change.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.