eembc/energyrunner

The EEMBC EnergyRunner application framework for the MLPerf Tiny benchmark.

/ 100

Emerging

This tool helps embedded systems engineers and hardware developers rigorously benchmark the performance and energy efficiency of tiny machine learning (TinyML) models running on microcontrollers. It takes your compiled TinyML firmware and external hardware (like an Arduino Uno or power measurement equipment) as input, and outputs detailed measurements of inferences per second, accuracy, and energy consumed per inference. This is specifically for engineers developing and optimizing TinyML applications on resource-constrained devices.

No commits in the last 6 months.

Use this if you need to accurately measure the throughput, accuracy, and power consumption of your TinyML models on specific embedded hardware.

Not ideal if you are looking for a high-level tool to train or deploy models without needing to analyze low-level hardware performance metrics.

TinyML benchmarking Embedded systems performance Microcontroller power measurement Hardware validation Edge AI optimization

No License Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 6 / 25

Maturity 8 / 25

Community 16 / 25

How are scores calculated?

Stars

Forks

Language

—

License

—

Higher-rated alternatives

NVIDIA/TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit...

mlcommons/inference

Reference implementations of MLPerf® inference benchmarks

mlcommons/training

Reference implementations of MLPerf® training benchmarks

datamade/usaddress

:us: a python library for parsing unstructured United States address strings into address components

GRAAL-Research/deepparse

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

Explore ML Frameworks

All categories Trending ML Framework directory Insights