[WIP] Add mean and median threshold modes to binary quantization #716
+435
−44
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
enp1s0
changed the title
enp1s0
added
breaking
enp1s0
changed the title
|
@enp1s0 this sounds super useful! Thanks for opening the PR. Do you have a sense for how much this improves recall? |
…nto update-binary-quantization
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Outdated suggestions cannot be applied.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.
The current binary quantization function sets a bit when the corresponding input dataset element is positive. This method (zero threshold mode) does not work well for, for example, a dataset where all elements are positive. This PR adds mean and median modes that set bits when the corresponding elements are larger than the dim-wise mean and median, respectively.
The new
transformfunction requires rapidsai/raft#2592 to be merged to support large datasets.TODO: