Green Ai Bench

Benchmarking of frameworks for tracking of energy consumption of running inference.

Developer:

  • Freja Thoresen (freja.thoresen@alexandra.dk)

Overview

Green AI Bench is a benchmarking tool designed to measure and compare the energy consumption of various Python libraries, hardware platforms, and power measurement tools. It provides insights into the environmental impact of running inference of machine learning models.

Additional documentation is here: https://alexandrainst.github.io/green_ai_bench

Features

  • Library Comparisons: Measure energy consumption using the Python libraries CodeCarbon, PyJoules, and Zeus.
  • Hardware Benchmarks: Compare energy usage on different platforms, such as laptop CPUs & GPUs, Raspberry Pi CPUs and Hailo devices.
  • Power Supply Integration: Measure actual energy consumption using a Siglent Power Supply.

Project Setup

The following steps will set up the project repository. Furthermore, to set up the Raspberry Pi and Siglent Power Supply, please follow these guides:

Installation

  1. Run make install, which sets up a virtual environment and all Python dependencies therein.
  2. Run source .venv/bin/activate to activate the virtual environment.
  3. (Optional) Run make install-pre-commit, which installs pre-commit hooks for linting, formatting and type checking.

Adding and Removing Packages

To install new PyPI packages, run: 

uv add <package-name>

To remove them again, run: 

uv remove <package-name>

To show all installed packages, run: 

uv pip show

All Built-in Commands

The project includes the following convenience commands:

  • make install: Install the project and its dependencies in a virtual environment.
  • make install-pre-commit: Install pre-commit hooks for linting, formatting and type checking.
  • make lint: Lint the code using ruff.
  • make format: Format the code using ruff.
  • make type-check: Type check the code using mypy.
  • make test: Run tests using pytest and update the coverage badge in the readme.
  • make docker: Build a Docker image and run the Docker container.
  • make docs: View documentation locally in a browser.
  • make publish-docs: Publish documentation to GitHub Pages.
  • make tree: Show the project structure as a tree.

Energy Consumption Experiments

These pages will help you get started on running experiments and benchmarking the energy consumption of machine learning models: