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Outdated suggestions cannot be applied.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.
What do these changes do?
This PR removes the handling of cases where
post_activation_bias
can be null from the optimized convolution kernels.In the converter
post_activation_bias
andpost_activation_multiplier
will always be set, so since we don't check for the existence ofpost_activation_multiplier
in the optimized assembly we can also get rid of the check forpost_activation_bias
. This check has been added moved over from TFLite which allows biases to be null. This is not the case here so I think this can be savely removed from the optimized code path.How Has This Been Tested?
This has purely been tested on CI since I originally made these changes when experiment with #263 only now rebased them onto the latest master.
Benchmark Results
I didn't ran any benchmarks for these changes, but I am happy to do so if you think it would be useful
Related issue number
Removing these checks might make implementing AArch64 support for #387 a bit easier.