hummingbird/benchmarks/operators
..
README.md
__init__.py
run.py
score.py
train.py

README.md

Operators Experiments

This directory contains the script to reproduce the experiments of Section 6.1.2 of the paper A Tensor Compiler for Unified Machine Learning Prediction Serving. This script is configured to run sklearn and compare it against onnx-ml, torchscript and onnx (the last 2 using Hummingbird), for the iris dataset over 1 core, and with batch of 1M.

  • python run.py will run the benchmarks for CPU
  • python run.py -gpu will run the benchmarks for GPU