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

[PTQ][Experimental stats] MAD and Percentile aggregators accept dynamic tensors #2221

Conversation

daniil-lyakhov
Copy link
Collaborator

On top of #2213

Changes

MAD and Percentile aggregators accepts tensors that have different axes along aggregation axes

Reason for changes

To align behaviour of the experimental tensor collectors with common tensor collectors

Related tickets

123519

Tests

  • test_mad_percentile_aggregators_different_sizes

@github-actions github-actions bot added NNCF TF Pull requests that updates NNCF TensorFlow NNCF PT Pull requests that updates NNCF PyTorch NNCF Common Pull request that updates NNCF Common experimental NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF ONNX Pull requests that updates NNCF ONNX labels Oct 25, 2023
return retval


def _moveaxes_flatten_cat(
Copy link
Collaborator Author

Choose a reason for hiding this comment

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

This function is working correctly only for cases when 0 is present in original aggregation axes. I didn't implement additional logic for other cases because it will be impossible after the #2213 anyway

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
experimental NNCF Common Pull request that updates NNCF Common NNCF ONNX Pull requests that updates NNCF ONNX NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF PT Pull requests that updates NNCF PyTorch NNCF TF Pull requests that updates NNCF TensorFlow
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant