Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Performance: picked better parameters for Fashion MNIST dataset (239QPS @ 0.96 recall) #727

Merged
merged 4 commits into from
Aug 31, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ann-benchmarks/config.yml
Original file line number Diff line number Diff line change
Expand Up @@ -18,5 +18,5 @@ float:
name: elastiknn-l2lsh
run_groups:
elastiknn-l2lsh:
args: [[100], [4], [1024, 2048]]
query_args: [[500, 1000], [0, 3]]
args: [[175], [7], [3900]]
query_args: [[100,500,1000], [0]]
2 changes: 1 addition & 1 deletion docs/pages/performance/fashion-mnist/plot.b64

Large diffs are not rendered by default.

Binary file modified docs/pages/performance/fashion-mnist/plot.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
11 changes: 3 additions & 8 deletions docs/pages/performance/fashion-mnist/results.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,5 @@
|Model|Parameters|Recall|Queries per Second|
|---|---|---|---|
|eknn-l2lsh|L=100 k=4 w=1024 candidates=500 probes=0|0.378|373.943|
|eknn-l2lsh|L=100 k=4 w=1024 candidates=1000 probes=0|0.447|322.600|
|eknn-l2lsh|L=100 k=4 w=1024 candidates=500 probes=3|0.635|278.750|
|eknn-l2lsh|L=100 k=4 w=1024 candidates=1000 probes=3|0.717|248.708|
|eknn-l2lsh|L=100 k=4 w=2048 candidates=500 probes=0|0.767|328.214|
|eknn-l2lsh|L=100 k=4 w=2048 candidates=1000 probes=0|0.847|291.762|
|eknn-l2lsh|L=100 k=4 w=2048 candidates=500 probes=3|0.922|217.030|
|eknn-l2lsh|L=100 k=4 w=2048 candidates=1000 probes=3|0.960|197.218|
|eknn-l2lsh|L=175 k=7 w=3900 candidates=100 probes=0|0.607|304.462|
|eknn-l2lsh|L=175 k=7 w=3900 candidates=500 probes=0|0.921|269.909|
|eknn-l2lsh|L=175 k=7 w=3900 candidates=1000 probes=0|0.962|239.598|