# Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models

arXiv: https://arxiv.org/abs/2304.00897 · HTML: https://mlsanity.com/paper/2304.00897/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 3 Apr 2023.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [The Efficiency Misnomer](https://mlsanity.com/paper/2110.12894/) (2021)
- [NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks](https://mlsanity.com/paper/1710.05420/) (2017)
- [How to scale distributed deep learning?](https://mlsanity.com/paper/1611.04581/) (2016)
- [Dissecting FLOPs along input dimensions for GreenAI cost estimations](https://mlsanity.com/paper/2107.11949/) (2021)
- [Energy-based Tuning of Convolutional Neural Networks on Multi-GPUs](https://mlsanity.com/paper/1808.00286/) (2018)

## Built on by (most cited first, 9 of 9)

- [Watt For What: Rethinking Deep Learning's Energy-Performance Relationship](https://mlsanity.com/paper/2310.06522/) (2023)
- [Evaluating the Energy Consumption of Machine Learning: Systematic Literature Review and Experiments](https://mlsanity.com/paper/2408.15128/) (2024)
- [On the retraining frequency of global models in retail demand forecasting](https://mlsanity.com/paper/2505.00356/) (2025)
- [Normalizing Energy Consumption for Hardware-Independent Evaluation](https://mlsanity.com/paper/2409.05602/) (2024)
- [The cost of ensembling: is it always worth combining?](https://mlsanity.com/paper/2506.04677/) (2025)
- [An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation](https://mlsanity.com/paper/2508.17007/) (2025)
- [Dissecting Transformers: A CLEAR Perspective towards Green AI](https://mlsanity.com/paper/2510.02810/) (2025)
- [BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services](https://mlsanity.com/paper/2511.08142/) (2025)
- [WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks](https://mlsanity.com/paper/2606.27841/) (2026)

## Abstract (arXiv)

Modern machine learning models have started to consume incredible amounts of energy, thus incurring large carbon footprints (Strubell et al., 2019). To address this issue, we have created an energy estimation pipeline1, which allows practitioners to estimate the energy needs of their models in advance, without actually running or training them. We accomplished this, by collecting high-quality energy data and building a first baseline model, capable of predicting the energy consumption of DL models by accumulating their estimated layer-wise energies.