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

FullyConnected layer integration changes #2491

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

vnileshdaiict
Copy link

@vnileshdaiict vnileshdaiict commented Mar 5, 2024

Following changes have been made :

  1. Integration of float32, 4-bit & 16-bit fully_connected kernels.
  2. Integration of matmul kernels for float32, 4, 8, 16-bit batched fully_connected cases.
  3. Data-type based registration for fully_connected operator.
  4. Addition of compile flag to include / exclude HiFi floating point optimized fully_connected kernel.

BUG=none

1) Integration of float32, 4-bit & 16-bit fully_connected kernels.
2) Integration of matmul kernels for float32, 4, 8, 16-bit batched fully_connected cases.
3) Data-type based registration for fully_connected operator.
4) Addition of compile flag to include / exclude HiFi floating point optimized fully_connected kernel.
@vnileshdaiict vnileshdaiict requested a review from a team as a code owner March 5, 2024 06:11
Copy link

google-cla bot commented Mar 5, 2024

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

Copy link
Contributor

"This PR is being marked as stale due to inactivity. Remove label or comment to prevent closure in 5 days."

@github-actions github-actions bot added the Stale label Apr 14, 2024
@rascani rascani removed the Stale label Apr 15, 2024
Copy link
Collaborator

@rascani rascani left a comment

Choose a reason for hiding this comment

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

Generally looks good to me, but one minor comment and the code formatting needs to be fixed. I tried to do it, but I don't have permissions to modify the branch.

const TfLiteEvalTensor* input, const TfLiteEvalTensor* filter,
const TfLiteEvalTensor* bias, TfLiteEvalTensor* output) {

#if defined(INCLUDE_FLOAT_OPT) && (defined(HIFI4) || defined(HIFI5))
Copy link
Collaborator

Choose a reason for hiding this comment

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

Should add define for HIFI3.

@rascani
Copy link
Collaborator

rascani commented May 15, 2024

@vp-cad - The formatting errors can be fixed with:

tensorflow/lite/micro/tools/ci_build/test_code_style.sh --fix_formatting

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants