Fix KL error method per-tensor #1041
Merged
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
| error_list.append(_kl_error_function(x[j], range_min[j], range_max[j], n_bins=n_bins, n_bits=n_bits)) | ||
| if per_channel: | ||
| for j in range(x.shape[0]): # iterate all channels of the tensor. | ||
| error_list.append(_kl_error_function(x[j], range_min[j], range_max[j], n_bins=n_bins, n_bits=n_bits)) |
There was a problem hiding this comment.
Maybe this can be done in a vectorial way?
| return lambda x, y, threshold: _kl_error_function_wrapper(x, range_min=0 if not signed else -threshold, | ||
| range_max=threshold, | ||
| n_bits=n_bits, | ||
| per_channel=True) |
There was a problem hiding this comment.
Maybe use variables to pass to _kl_error_function_wrapper to avoid unnecessary duplications?
reuvenperetz
approved these changes
Apr 14, 2024
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Outdated suggestions cannot be applied.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.
Pull Request Description:
KL error method per-tensor didn't work, and we didn't catch it since our selection tests didn't really run per-tensor tests as expected.
Also fixing other configuration tests that didn't check per-channel=False properly.
Checklist before requesting a review: