paper-with-me

Papers

Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond

2020-08-30 · Dachao Lin, Peiqin Sun, Guangzeng Xie, Shuchang Zhou, Zhihua Zhang

Quantized Neural Networks (QNNs) use low bit-width fixed-point numbers for representing weight parameters and activations, and are often used in real-world applications due to their saving of computation resources and reproducibility of results. Batch Normalization (BN) poses a challenge for QNNs for requiring floating points in reciprocal operations, and previous QNNs either require computing BN at high precision or revise BN to some variants in heuristic ways. In this work, we propose a novel method to quantize BN by converting an affine transformation of two floating points to a fixed-point operation with shared quantized scale, which is friendly for hardware acceleration and model deployment. We confirm that our method maintains same outputs through rigorous theoretical analysis and numerical analysis. Accuracy and efficiency of our quantization method are verified by experiments at layer level on CIFAR and ImageNet datasets. We also believe that our method is potentially useful in other problems involving quantization.

📄 PDF Abstract BibTeX arXiv:2008.13128

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization

2022-04-08 · Yefei He, Luoming Zhang, Weijia Wu, Hong Zhou

Data-free quantization is a task that compresses the neural network to low bit-width without access to original training data. Most existing data-free quantization methods cause severe performance degradation due to inac…

Data Free QuantizationQuantization

PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks

2024-01-01 · CVPR 2024 1 · Marina Neseem, Conor McCullough, Randy Hsin, Chas Leichner 외

Low-precision quantization is recognized for its efficacy in neural network optimization. Our analysis reveals that non-quantized elementwise operations which are prevalent in layers such as parameterized activation …

Quantization

Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization

2021-05-27 · Yukuan Yang, Xiaowei Chi, Lei Deng, Tianyi Yan 외

Huge computational costs brought by convolution and batch normalization (BN) have caused great challenges for the online training and corresponding applications of deep neural networks (DNNs), especially in resource-limi…

Model CompressionQuantization

Scalable Methods for 8-bit Training of Neural Networks

2018-05-25 · NeurIPS 2018 12 · Ron Banner, Itay Hubara, Elad Hoffer, Daniel Soudry

Quantized Neural Networks (QNNs) are often used to improve network efficiency during the inference phase, i.e. after the network has been trained. Extensive research in the field suggests many different quantization sche…

Quantization

Integer-Only Neural Network Quantization Scheme Based on Shift-Batch-Normalization

2021-05-28 · Qingyu Guo, YuAn Wang, Xiaoxin Cui

Neural networks are very popular in many areas, but great computing complexity makes it hard to run neural networks on devices with limited resources. To address this problem, quantization methods are used to reduce mode…

Quantization