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

Author: alexklibisz

ann-benchmarks/config.yml

@@ -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]]

docs/pages/performance/fashion-mnist/plot.b64

@@ -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|