Update aggregator.py #2995
Merged
Update aggregator.py #2995
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
l-bat
reviewed
Sep 30, 2024
l-bat
reviewed
Oct 4, 2024
Co-authored-by: Liubov Talamanova <[email protected]>
Co-authored-by: Liubov Talamanova <[email protected]>
l-bat
reviewed
Oct 4, 2024
|
Great, any other changes required to close this issue? |
No, once the PR passes all checks, we’ll merge it |
|
Is a set value to be used for subset_size, or do I import it from somewhere? |
l-bat
reviewed
Oct 7, 2024
Co-authored-by: Liubov Talamanova <[email protected]>
Co-authored-by: Liubov Talamanova <[email protected]>
|
Please fix linter |
l-bat
reviewed
Oct 8, 2024
|
Thank you for your assistance!! |
alexsu52
reviewed
Oct 11, 2024
| raise nncf.ValidationError(EMPTY_DATASET_ERROR) | ||
| if self.stat_subset_size is not None and self.stat_subset_size > processed_samples: | ||
| nncf_logger.warning( | ||
| f"Dataset contains only {processed_samples} samples, " |
There was a problem hiding this comment.
@l-bat, @eaidova, @nikita-savelyevv please check that this is not impact NNCF examples, OpenVINO notebooks and optimum-intel.
There was a problem hiding this comment.
@zina-cs Could you please provide subset_size to the nncf.quantize in the following examples?
- https://github.com/openvinotoolkit/nncf/tree/develop/examples/post_training_quantization/openvino:
- anomaly_stfpm_quantize_with_accuracy_control -
subset_size=109 - yolov8 -
subset_size=128 - yolov8_quantize_with_accuracy_control -
subset_size=128
- anomaly_stfpm_quantize_with_accuracy_control -
- https://github.com/openvinotoolkit/nncf/tree/develop/examples/post_training_quantization/onnx/yolov8_quantize_with_accuracy_control -
subset_size=128 - https://github.com/openvinotoolkit/nncf/tree/develop/examples/post_training_quantization/torch/ssd300_vgg16 -
subset_size=128
Closed
alexsu52
pushed a commit
that referenced
this pull request
Oct 21, 2024
### Changes Add `subset_size` to PTQ samples after merging #2995 to remove the warning message CI: https://github.com/openvinotoolkit/nncf/actions/runs/11436915496
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Changes
Added an error message
Reason for changes
send warning message to avoid Inconsistencies arise when the dataset size is less than the provided or default 'subset_size'.
Related tickets
Closes: #2562
I had an inquiry:
I noticed that subset_size is sometimes put as 100, or 300, or specified in the advanced parameters. Should a default be used here, or could you point me to where I can find the correct subset_size to be imported?