Neural network quantification method and device, equipment and storage medium

A neural network and quantization method technology, applied in the field of devices, equipment and storage media, and neural network quantification methods, can solve the problems of consuming large storage and computing resources, complex neural network structure, etc., and achieve the effect of occupying less resources

Pending Publication Date: 2022-05-13
SHANGHAI POWERTENSORS INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Due to the complex structure of the neural network, which contains a large number of network parameters, it consumes a large amount of storage and computing resources during the calculation process.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network quantification method and device, equipment and storage medium
  • Neural network quantification method and device, equipment and storage medium
  • Neural network quantification method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0068] The terminology used in the present disclosure is for the purpose of describing particular embodiments only, and is not intended to limit the present disclosure. As used in this disclosure and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention provides a neural network quantification method and device, equipment and a storage medium. For a tensor set formed by tensors in a neural network, when the quantization strategy of the tensor set is determined, a target quantization strategy can be screened out from multiple quantization strategies based on the frequency domain distribution condition of each tensor in the tensor set before and after quantization, so that the tensors in the neural network are quantized by using the target quantization strategy. The quality of the quantization strategy is measured by adopting the frequency domain distribution condition of the tensor before and after quantization, and the quantization strategy can be measured more meticulously from the dimension of the frequency domain, so that the quantized neural network occupies less resources, and the performance is not greatly influenced.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular to a neural network quantization method, device, equipment, and storage medium. Background technique [0002] Due to the complex structure of the neural network, which contains a large number of network parameters, it consumes a large amount of storage and computing resources during the calculation process. In order to allow the neural network to be deployed on ordinary terminal devices and expand its application scenarios, the tensors in the neural network can be quantized, and the original high-precision tensors in the neural network can be converted to low-precision tensors. When quantizing the tensor of the neural network, it is necessary to optimize the quantization strategy, so that the neural network quantized by the optimized quantization strategy consumes as little computing and storage resources as possible, while maintaining its performance wi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06N3/08G06N3/04
CPCG06N3/08G06N3/084G06N3/045
Inventor 史丽坤胡英俊
Owner SHANGHAI POWERTENSORS INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap