1 dépôt
Generates interactive scatter plots from benchmark data to visualize recall versus queries per second.
Distinct from Scatter Plot Rendering: Distinct from Scatter Plot Rendering: focuses on interactive benchmark-specific visualizations, not general scatter plot creation.
Explore 1 awesome GitHub repository matching graphics & multimedia · Interactive Benchmark Plots. Refine with filters or upvote what's useful.
ann-benchmarks is a standardized benchmarking suite for evaluating approximate nearest neighbor (ANN) search algorithms. It provides a reproducible framework for comparing how different ANN implementations perform across multiple datasets and distance measures, using precomputed ground truth results stored in HDF5 files to ensure consistent accuracy measurements. The project wraps each ANN library behind a common Python interface, allowing algorithms to be swapped without modifying the benchmarking harness. It orchestrates parameter sweeps over algorithm-specific hyperparameters to generate f
Generates interactive scatter plots visualizing recall versus queries per second across algorithms and datasets.