Skip to content

Tune ScaNN for other angular datasets#172

Merged
erikbern merged 1 commit intoerikbern:masterfrom
sammymax:scann-tuning
Jul 16, 2020
Merged

Tune ScaNN for other angular datasets#172
erikbern merged 1 commit intoerikbern:masterfrom
sammymax:scann-tuning

Conversation

@sammymax
Copy link
Copy Markdown
Contributor

The originally submitted configuration was only tuned for Glove-100. Here are some better configurations for the other angular datasets. Still investigating NYTimes...

Glove-25:
glove-25
LastFM:
lastfm

@erikbern
Copy link
Copy Markdown
Owner

Nice!

FYI nytimes-256 has a few "missing" vectors (all elements set to zero) which I guess is a bug or a feature depending on how you look at it (I've been arguing that's a common case that libraries should ideally be able to handle). So that might cause issues for ScANN

@erikbern
Copy link
Copy Markdown
Owner

Let me know if you want me to merge this. Otherwise will keep it open so you can optimize more :)

@sammymax
Copy link
Copy Markdown
Contributor Author

sammymax commented Jul 16, 2020 via email

@erikbern erikbern merged commit 55b9950 into erikbern:master Jul 16, 2020
@sammymax sammymax mentioned this pull request Jul 23, 2020
erikbern added a commit that referenced this pull request Apr 14, 2023
Tune ScaNN for other angular datasets
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

2 participants