Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Generate BuiltinData for FullyConnected #2184

Merged
merged 2 commits into from
Aug 24, 2023

Conversation

rascani
Copy link
Contributor

@rascani rascani commented Aug 23, 2023

Each operator has its own set of BuiltinOptions, which will translate into an op-specific TfLite Params structure. This change turns Operator into a base class with common functionality, and adds a FullyConnected subclass that knows how to generate the TfLiteFullyConnectedParams struct.

BUG=b/295175961

Each operator is going to have its own set of BuiltinOptions, which will
translate into an op-specific TfLite Params structure. This change turns
Operator into a base class with common functionality, and adds a
FullyConnected subclass that knows how to generate the
TfLiteFullyConnectedParams struct.

BUG=b/295175961
@rascani rascani requested a review from a team as a code owner August 23, 2023 23:54
@rascani rascani added the ci:run label Aug 23, 2023
@TFLM-bot TFLM-bot removed the ci:run label Aug 23, 2023
Comment on lines +28 to +29
schema_fb.FullyConnectedOptionsWeightsFormat.SHUFFLED4x16INT8:
"kTfLiteFullyConnectedWeightsFormatShuffled4x16Int8",
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

interesting. I didn't even know about this. There might be a lot in the flatbuffer that isn't needed for TFLM at this time.

@mergify mergify bot merged commit f8ab03d into tensorflow:main Aug 24, 2023
28 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants