CN114365151A - 神经网络模型转化方法、装置、服务器及存储介质 - Google Patents

神经网络模型转化方法、装置、服务器及存储介质 Download PDF

Info

Publication number
CN114365151A
CN114365151A CN201980100191.XA CN201980100191A CN114365151A CN 114365151 A CN114365151 A CN 114365151A CN 201980100191 A CN201980100191 A CN 201980100191A CN 114365151 A CN114365151 A CN 114365151A
Authority
CN
China
Prior art keywords
model
neural network
model information
target
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201980100191.XA
Other languages
English (en)
Inventor
熊超
蔡权雄
牛昕宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Corerain Technologies Co Ltd
Original Assignee
Shenzhen Corerain Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Corerain Technologies Co Ltd filed Critical Shenzhen Corerain Technologies Co Ltd
Publication of CN114365151A publication Critical patent/CN114365151A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/40—Transformation of program code
    • G06F8/41—Compilation
    • G06F8/42—Syntactic analysis
    • G06F8/427—Parsing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/70—Software maintenance or management
    • G06F8/74—Reverse engineering; Extracting design information from source code
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks

Abstract

本发明实施例公开了一种神经网络模型转化方法、装置、服务器及存储介质，所述方法包括：对神经网络模型进行解析，得到初始模型信息；对所述初始模型信息进行重构，得到数据流模型信息；根据所述数据流模型信息生成目标模型信息文件；在数据流架构下，根据所述目标模型信息文件运行所述神经网络模型。

Description

PCT国内申请，说明书已公开。

Claims (10)

  1. PCT国内申请，权利要求书已公开。
CN201980100191.XA 2019-10-22 2019-10-22 神经网络模型转化方法、装置、服务器及存储介质 Pending CN114365151A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/112464 WO2021077282A1 (zh) 2019-10-22 2019-10-22 神经网络模型转化方法、装置、服务器及存储介质

Publications (1)

Publication Number Publication Date
CN114365151A true CN114365151A (zh) 2022-04-15

Family

ID=75619590

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201980100191.XA Pending CN114365151A (zh) 2019-10-22 2019-10-22 神经网络模型转化方法、装置、服务器及存储介质

Country Status (3)

Country Link
US (1) US11797277B2 (zh)
CN (1) CN114365151A (zh)
WO (1) WO2021077282A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115437642A (zh) * 2022-11-07 2022-12-06 深圳鲲云信息科技有限公司 一种模型编译方法、装置、电子设备和存储介质
CN115437642B (zh) * 2022-11-07 2024-05-14 深圳鲲云信息科技有限公司 一种模型编译方法、装置、电子设备和存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11216718B2 (en) * 2015-10-27 2022-01-04 Yardi Systems, Inc. Energy management system
EP4202782A1 (en) 2015-11-09 2023-06-28 Google LLC Training neural networks represented as computational graphs
US10776714B2 (en) 2016-11-04 2020-09-15 Google Llc Constructing and processing computational graphs for dynamically structured machine learning models
CN108021395B (zh) 2017-12-27 2022-04-29 北京金山安全软件有限公司 一种面向神经网络的数据并行处理方法及系统
EP3762903A4 (en) * 2018-03-09 2021-12-08 TuSimple, Inc. VEHICLE WHEEL DETECTION SYSTEM AND METHOD
US20190286973A1 (en) * 2018-03-14 2019-09-19 Microsoft Technology Licensing, Llc Hardware accelerated neural network subgraphs
US11645358B2 (en) * 2019-01-29 2023-05-09 Hewlett Packard Enterprise Development Lp Generation of executable files corresponding to neural network models
US11694075B2 (en) * 2019-09-05 2023-07-04 Alibaba Group Holding Limited Partitioning control dependency edge in computation graph

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115437642A (zh) * 2022-11-07 2022-12-06 深圳鲲云信息科技有限公司 一种模型编译方法、装置、电子设备和存储介质
CN115437642B (zh) * 2022-11-07 2024-05-14 深圳鲲云信息科技有限公司 一种模型编译方法、装置、电子设备和存储介质

Also Published As

Publication number Publication date
US20220365762A1 (en) 2022-11-17
WO2021077282A1 (zh) 2021-04-29
US11797277B2 (en) 2023-10-24

Similar Documents

Publication Publication Date Title
US11640528B2 (en) Method, electronic device and computer readable medium for information processing for accelerating neural network training
EP4116885A1 (en) Processing method for neural network model, and related device
CN111523640B (zh) 神经网络模型的训练方法和装置
CN112819153A (zh) 一种模型转化方法及装置
CN113434683B (zh) 文本分类方法、装置、介质及电子设备
US20230139106A1 (en) Conversion method and apparatus for deep learning model, server, and storage medium
CN111985831A (zh) 云计算资源的调度方法、装置、计算机设备及存储介质
CN113656590B (zh) 行业图谱的构建方法、装置、电子设备及存储介质
WO2024036662A1 (zh) 一种基于数据采样的并行图规则挖掘方法及装置
JP2021512387A (ja) 量子コンピューティング・デバイス設計
CN110868324A (zh) 一种业务配置方法、装置、设备和存储介质
CN114065915A (zh) 网络模型的构建方法、数据处理方法、装置、介质及设备
CN111813721B (zh) 神经网络数据处理方法、装置、设备及存储介质
CN110555732B (zh) 一种营销策略推送方法、装置及营销策略运营平台
CN115186738B (zh) 模型训练方法、装置和存储介质
CN113569581B (zh) 意图识别方法、装置、设备及存储介质
CN111124409A (zh) 基于Sketch的业务页面生成方法、装置、设备和存储介质
CN114365151A (zh) 神经网络模型转化方法、装置、服务器及存储介质
CN114238128A (zh) 测试用例生成方法、装置、电子设备及计算机可读介质
CN111291186A (zh) 一种基于聚类算法的上下文挖掘方法、装置和电子设备
CN115238805B (zh) 异常数据识别模型的训练方法及相关设备
CN110347506B (zh) 基于lstm的数据处理方法、装置、存储介质与电子设备
US11907693B2 (en) Job decomposition processing method for distributed computing
CN115952830B (zh) 数据处理方法、装置、电子设备及存储介质
US20230267286A1 (en) Translation model training method, translation method, apparatus, device, and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination