paper-with-me

홈 › Papers

Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search

2018-11-30 · ICLR 2019 5 · Bichen Wu, Yanghan Wang, Peizhao Zhang, Yuandong Tian, Peter Vajda, Kurt Keutzer

Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices with limited computational and memory resources. However, existing quantization methods often represent all weights and activations with the same precision (bit-width). In this paper, we explore a new dimension of the design space: quantizing different layers with different bit-widths. We formulate this problem as a neural architecture search problem and propose a novel differentiable neural architecture search (DNAS) framework to efficiently explore its exponential search space with gradient-based optimization. Experiments show we surpass the state-of-the-art compression of ResNet on CIFAR-10 and ImageNet. Our quantized models with 21.1x smaller model size or 103.9x lower computational cost can still outperform baseline quantized or even full precision models.

📄 PDF Abstract BibTeX arXiv:1812.00090

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture SearchQuantization

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization

2021-02-20 · ICLR 2021 1 · Huanrui Yang, Lin Duan, Yiran Chen, Hai Li

Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method t…

Neural Architecture SearchQuantization

SDQ: Stochastic Differentiable Quantization with Mixed Precision

2022-06-09 · Xijie Huang, Zhiqiang Shen, Shichao Li, Zechun Liu 외

In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent resea…

Knowledge DistillationNeural Architecture SearchQuantization

FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search

2023-08-07 · Jordan Dotzel, Gang Wu, Andrew Li, Muhammad Umar 외

Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent har…

Quantization

Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution

2021-06-04 · Zhang Zhaoyang, Shao Wenqi, Gu Jinwei, Wang Xiaogang 외

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts …

Quantization

Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization

2021-03-04 · Qigong Sun, Licheng Jiao, Yan Ren, Xiufang Li 외

Since model quantization helps to reduce the model size and computation latency, it has been successfully applied in many applications of mobile phones, embedded devices and smart chips. The mixed-precision quantization …

Quantization