paper-with-me

Papers

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

2022-10-14 · Cecilia Latotzke, Batuhan Balim, Tobias Gemmeke

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.

📄 PDF Abstract BibTeX arXiv:2210.07906

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning

2022-08-24 · Elias Frantar, Sidak Pal Singh, Dan Alistarh

We consider the problem of model compression for deep neural networks (DNNs) in the challenging one-shot/post-training setting, in which we are given an accurate trained model, and must compress it without any retraining…

Model CompressionQuantization

Post-Training Piecewise Linear Quantization for Deep Neural Networks

2020-01-31 · ECCV 2020 8 · Jun Fang, Ali Shafiee, Hamzah Abdel-Aziz, David Thorsley 외

Quantization plays an important role in the energy-efficient deployment of deep neural networks on resource-limited devices. Post-training quantization is highly desirable since it does not require retraining or access t…

image-classificationImage Classificationobject-detectionObject Detection+2

Resource-Efficient Language Models: Quantization for Fast and Accessible Inference

2025-05-13 · Tollef Emil Jørgensen

Large language models have significantly advanced natural language processing, yet their heavy resource demands pose severe challenges regarding hardware accessibility and energy consumption. This paper presents a focuse…

Quantization

HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays

2024-02-02 · Matteo Risso, Chen Xie, Francesco Daghero, Alessio Burrello 외

Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows while preserving privacy and minimizing energy consumption. Deep Neural Networks …

Neural Architecture SearchPrivacy PreservingQuantization

Gradient $\ell_1$ Regularization for Quantization Robustness

2020-02-18 · ICLR 2020 1 · Milad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos 외

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization…

Quantization