# Post-Training Quantization for Energy Efficient Realization of Deep Neural Networks

Source: [Post-Training Quantization for Energy Efficient Realization of Deep Neural Networks](<https://www.sota2.com/research/paper/68fa6daa1e209131cea3b51d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:40:22.216Z

Authors: Cecilia Latotzke, Batuhan Balim, Tobias Gemmeke

Published: 2022-10-14T15:43:57.000Z

## Abstract

The biggest challenge for the deployment of Deep Neural Networks (DNNs) close to the generated data on edge devices is their size, i.e., memory footprint and computational complexity. Both are significantly reduced with quantization. With the resulting lower word-length, the energy efficiency of DNNs increases proportionally. However, lower word-length typically causes accuracy degradation. To counteract this effect, the quantized DNN is retrained. Unfortunately, training costs up to 5000x more energy than the inference of the quantized DNN. To address this issue, we propose a post-training quantization flow without the need for retraining. For this, we investigated different quantization options. Furthermore, our analysis systematically assesses the impact of reduced word-lengths of weights and activations revealing a clear trend for the choice of word-length. Both aspects have not been systematically investigated so far. Our results are independent of the depth of the DNNs and apply to uniform quantization, allowing fast quantization of a given pre-trained DNN. We excel state-of-the-art for 6 bit by 2.2% Top-1 accuracy for ImageNet. Without retraining, our quantization to 8 bit surpasses floating-point accuracy.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.07906>)

[PDF](<https://arxiv.org/pdf/2210.07906.pdf>)
