Skip to content

Conversation

@nghielme
Copy link

Code to support the ingestion of Resize node from QONNX model and to properly generate hls4ml code

Type of change

For a new feature or function, please create an issue first to discuss it
with us before submitting a pull request.

Note: Please delete options that are not relevant.

  • New feature (non-breaking change which adds functionality)

Tests

No tests added for the moment, they will be added in a second time.

Test Configuration:

Checklist

  • I have read the guidelines for contributing.
  • I have commented my code, particularly in hard-to-understand areas.
  • I have installed and run pre-commit on the files I edited or added.
  • I have added tests that prove my fix is effective or that my feature works.

from hls4ml.model.layers import Resize
from hls4ml.model.optimizer import OptimizerPass

def register_match_quantizer_resize(backend):
Copy link
Owner

Choose a reason for hiding this comment

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

I don't think we need a second optimizer that does the work meant to be done by infer-precision

Copy link
Author

Choose a reason for hiding this comment

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

I'd generally agree but this is for the specific implementation of resize nearest for vivado/vitis. Other type of resize algorithm may require different type of type inference

jmitrevs pushed a commit that referenced this pull request Feb 17, 2025
fix simple-rnn config for Keras; make test names unique
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.

2 participants