Added NearPy multi-hash configuration and optimized parameters a bit #3
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
erikbern
added a commit
that referenced
this pull request
Jun 4, 2015
Added NearPy multi-hash configuration and optimized parameters a bit
|
Thanks! Will rerun NearPy! |
|
Awesome! Thanks! Looking forward to the results. I think NearPy will never be close to the really good libraries, because it is more of a framework for evaluating and comparing ANN methods, than a optimized solution. Still I would like to get it up in the graph a bit, of course. |
|
I think Nearpy might do well on huge data sets (say 1B) though, would be interesting to see |
erikbern
pushed a commit
that referenced
this pull request
Apr 25, 2016
Updating the number of queries and the seed (also README)
erikbern
pushed a commit
that referenced
this pull request
May 3, 2018
Correctly set number of probes in FAISS.
tinkerlin
pushed a commit
to tinkerlin/ann-benchmarks
that referenced
this pull request
Jul 1, 2020
Closed
erikbern
pushed a commit
that referenced
this pull request
Apr 14, 2023
Correctly set number of probes in FAISS.
erikbern
pushed a commit
that referenced
this pull request
Jun 9, 2023
enable benchmark to be triggered manually
jgpruitt
added a commit
to timescale/ann-benchmarks
that referenced
this pull request
Jun 10, 2024
Allow tracking shared_buffers and iterating query params
BenjaminXiang
added a commit
to BenjaminXiang/ann-benchmarks
that referenced
this pull request
Jul 4, 2024
From Jiexu merge nsg to longxiang branch
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Outdated suggestions cannot be applied.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.
I fixed a bug in NearPy cosine similarity, updated it on pypi to 0.2.1.
I also added multi-hash configuration to the NearPy benchmark, because this is the only way I ever use it, hope that is valid with respect to the benchmark.