Distributional Plot Recall vs LID
The following plot shows the Recall vs LID trade-off as distributional plots over all queries. Intensity of the square represents how many of the queries fall into this region of LID/recall valeus. Change the algorithm/dataset/difficult using the buttons below the plots.
Algorithm
Dataset
Difficulty
n_lists 1024204840968192
n_probe 1510100200
n_probe 1510100200
Contact
ANN-Benchmarks has been developed by Martin Aumueller (maau@itu.dk), Erik Bernhardsson (mail@erikbern.com), and Alec Faitfull (alef@itu.dk). Please use Github to submit your implementation or improvements.