Companion Material: Measuring the energy consumption of AI

Overview

This repository contains the material for the course “Measuring the energy consumption of AI” performed at the Second Inria-DFKI European Summer School on AI (IDESSAI 2022) at the Sustainable AI track.

Update: This course was also given at the ERAD|ERAMIA-NO2 2022 (https://www2.sbc.org.br/erad_eramia-no2/programa.html)

Lecturer: Danilo Carastan-Santos

• Twitter: https://twitter.com/DCarastanSantos
• LinkedIn: https://www.linkedin.com/in/danilo-carastan-santos/

Acknowledgements

This work was supported by the research program on Edge Intelligence of the Multi-disciplinary Institute on Artificial Intelligence MIAI at Grenoble Alpes (ANR-19-P3IA-0003) and REGALE (H2020-JTI-EuroHPC-2019-1 agreement n. 956560) projects.

Repository contents

• requirements.org: Pre-installation instructions and requirements for the

hands-on session. READ THIS FILE FIRST!

• course_slides.pdf: Course slides.
• session.py: Main file for the hands-on session.
• models.py: Some models descriptions used in the hands-on session.
• cct.py: Compact Convolutional Transformers model used in the hands-on session.
• requirements.txt: Package requirements used in the installation instructions.