CN115631388A - 图像分类方法、装置、电子设备及存储介质 - Google Patents
图像分类方法、装置、电子设备及存储介质 Download PDFInfo
- Publication number
- CN115631388A CN115631388A CN202211644947.7A CN202211644947A CN115631388A CN 115631388 A CN115631388 A CN 115631388A CN 202211644947 A CN202211644947 A CN 202211644947A CN 115631388 A CN115631388 A CN 115631388A
- Authority
- CN
- China
- Prior art keywords
- layer
- module
- candidate
- batch normalization
- last batch
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000010606 normalization Methods 0.000 claims abstract description 137
- 238000013145 classification model Methods 0.000 claims abstract description 54
- 230000009467 reduction Effects 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 67
- 238000004422 calculation algorithm Methods 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 26
- 230000004913 activation Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012886 linear function Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 18
- 238000013528 artificial neural network Methods 0.000 description 17
- 238000012549 training Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 8
- 238000010845 search algorithm Methods 0.000 description 8
- 230000008014 freezing Effects 0.000 description 6
- 238000007710 freezing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000013011 mating Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 101100153586 Caenorhabditis elegans top-1 gene Proteins 0.000 description 1
- 101100370075 Mus musculus Top1 gene Proteins 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Physiology (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Genetics & Genomics (AREA)
- Image Analysis (AREA)
Abstract
Description
浮点运算量 ( Flops ) | 参数量(Parameters) | T op 1 准确率(Top 1 Acc.) | 数据集 (Dataset) | |
MobileNet V2 方法 | 300 M | 3.4 M | 72% | Imagenet |
ShuffleNet V2 方法 | 286 M | 3.7 M | 72.4% | Imagenet |
DARTS 方法 | 595 M | 4.7 M | 73.1% | CIFAR |
PC-DARTS 方法 | 597 M | 5.3 M | 74.9% | CIFAR |
Proxyless 方法 | 465 M | 7.1 M | 75.1% | Imagenet |
SPOS[3] 方法 | 323 M | 3.5 M | 74.4% | Imagenet |
FairNAS[4] 方法 | 388 M | 4.4 M | 74.7% | Imagenet |
BNNAS 方法 | 326 M | 3.7 M | 74.12% | Imagenet |
本实施例方法 | 468 M | 4.9 M | 76.22% | Imagenet |
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211644947.7A CN115631388B (zh) | 2022-12-21 | 2022-12-21 | 图像分类方法、装置、电子设备及存储介质 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211644947.7A CN115631388B (zh) | 2022-12-21 | 2022-12-21 | 图像分类方法、装置、电子设备及存储介质 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115631388A true CN115631388A (zh) | 2023-01-20 |
CN115631388B CN115631388B (zh) | 2023-03-17 |
Family
ID=84910499
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211644947.7A Active CN115631388B (zh) | 2022-12-21 | 2022-12-21 | 图像分类方法、装置、电子设备及存储介质 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115631388B (zh) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140254923A1 (en) * | 2011-10-19 | 2014-09-11 | The University Of Sydney | Image processing and object classification |
US8965891B1 (en) * | 2009-11-23 | 2015-02-24 | Google Inc. | Training scoring models optimized for highly-ranked results |
CN107316018A (zh) * | 2017-06-23 | 2017-11-03 | 中国人民解放军陆军军官学院 | 一种基于组合部件模型的多类典型目标识别方法 |
CN107609598A (zh) * | 2017-09-27 | 2018-01-19 | 武汉斗鱼网络科技有限公司 | 图像鉴别模型训练方法、装置及可读存储介质 |
CN110956613A (zh) * | 2019-11-07 | 2020-04-03 | 成都傅立叶电子科技有限公司 | 基于图像质量的目标检测算法性能归一化评价方法及系统 |
CN111738355A (zh) * | 2020-07-22 | 2020-10-02 | 中国人民解放军国防科技大学 | 注意力融合互信息的图像分类方法、装置及存储介质 |
CN111814966A (zh) * | 2020-08-24 | 2020-10-23 | 国网浙江省电力有限公司 | 神经网络架构搜索方法、神经网络应用方法、设备及存储介质 |
CN112348188A (zh) * | 2020-11-13 | 2021-02-09 | 北京市商汤科技开发有限公司 | 模型生成方法及装置、电子设备和存储介质 |
US20210158094A1 (en) * | 2019-11-22 | 2021-05-27 | International Business Machines Corporation | Classifying images in overlapping groups of images using convolutional neural networks |
WO2021151318A1 (zh) * | 2020-07-31 | 2021-08-05 | 平安科技(深圳)有限公司 | 基于深度学习的图像分类方法、装置及计算机设备 |
CN113221842A (zh) * | 2021-06-04 | 2021-08-06 | 第六镜科技(北京)有限公司 | 模型训练方法、图像识别方法、装置、设备及介质 |
CN114495243A (zh) * | 2022-04-06 | 2022-05-13 | 第六镜科技(成都)有限公司 | 图像识别模型训练及图像识别方法、装置、电子设备 |
CN115115986A (zh) * | 2022-06-28 | 2022-09-27 | 广州欢聚时代信息科技有限公司 | 视频质量评估模型生产方法及其装置、设备、介质 |
CN115223015A (zh) * | 2022-09-16 | 2022-10-21 | 小米汽车科技有限公司 | 模型训练方法、图像处理方法、装置和车辆 |
-
2022
- 2022-12-21 CN CN202211644947.7A patent/CN115631388B/zh active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8965891B1 (en) * | 2009-11-23 | 2015-02-24 | Google Inc. | Training scoring models optimized for highly-ranked results |
US20140254923A1 (en) * | 2011-10-19 | 2014-09-11 | The University Of Sydney | Image processing and object classification |
CN107316018A (zh) * | 2017-06-23 | 2017-11-03 | 中国人民解放军陆军军官学院 | 一种基于组合部件模型的多类典型目标识别方法 |
CN107609598A (zh) * | 2017-09-27 | 2018-01-19 | 武汉斗鱼网络科技有限公司 | 图像鉴别模型训练方法、装置及可读存储介质 |
CN110956613A (zh) * | 2019-11-07 | 2020-04-03 | 成都傅立叶电子科技有限公司 | 基于图像质量的目标检测算法性能归一化评价方法及系统 |
US20210158094A1 (en) * | 2019-11-22 | 2021-05-27 | International Business Machines Corporation | Classifying images in overlapping groups of images using convolutional neural networks |
CN111738355A (zh) * | 2020-07-22 | 2020-10-02 | 中国人民解放军国防科技大学 | 注意力融合互信息的图像分类方法、装置及存储介质 |
WO2021151318A1 (zh) * | 2020-07-31 | 2021-08-05 | 平安科技(深圳)有限公司 | 基于深度学习的图像分类方法、装置及计算机设备 |
CN111814966A (zh) * | 2020-08-24 | 2020-10-23 | 国网浙江省电力有限公司 | 神经网络架构搜索方法、神经网络应用方法、设备及存储介质 |
CN112348188A (zh) * | 2020-11-13 | 2021-02-09 | 北京市商汤科技开发有限公司 | 模型生成方法及装置、电子设备和存储介质 |
CN113221842A (zh) * | 2021-06-04 | 2021-08-06 | 第六镜科技(北京)有限公司 | 模型训练方法、图像识别方法、装置、设备及介质 |
CN114495243A (zh) * | 2022-04-06 | 2022-05-13 | 第六镜科技(成都)有限公司 | 图像识别模型训练及图像识别方法、装置、电子设备 |
CN115115986A (zh) * | 2022-06-28 | 2022-09-27 | 广州欢聚时代信息科技有限公司 | 视频质量评估模型生产方法及其装置、设备、介质 |
CN115223015A (zh) * | 2022-09-16 | 2022-10-21 | 小米汽车科技有限公司 | 模型训练方法、图像处理方法、装置和车辆 |
Non-Patent Citations (3)
Title |
---|
HU ZG,ET AL: "Image-based neural architecture automatic search method for hyperspectral image classification" * |
曹家乐等: "基于深度学习的视觉目标检测技术综述" * |
蒲生亮等: "采用神经架构搜索的高光谱图像深度学习分类方法" * |
Also Published As
Publication number | Publication date |
---|---|
CN115631388B (zh) | 2023-03-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109584337B (zh) | 一种基于条件胶囊生成对抗网络的图像生成方法 | |
Lei Ba et al. | Predicting deep zero-shot convolutional neural networks using textual descriptions | |
CN109754078A (zh) | 用于优化神经网络的方法 | |
US20150006444A1 (en) | Method and system for obtaining improved structure of a target neural network | |
CA3066029A1 (en) | Image feature acquisition | |
US20210215818A1 (en) | Generative adversarial network-based target identification | |
JP7111671B2 (ja) | 学習装置、学習システム、および学習方法 | |
CN113780292B (zh) | 一种基于证据推理的语义分割网络模型不确定性量化方法 | |
Chen et al. | Remote sensing image quality evaluation based on deep support value learning networks | |
CN108804617B (zh) | 领域术语抽取方法、装置、终端设备及存储介质 | |
CN110826379A (zh) | 一种基于特征复用与YOLOv3的目标检测方法 | |
CN114330670A (zh) | 图神经网络训练方法、装置、设备及存储介质 | |
CN116385773A (zh) | 小目标的检测方法、存储介质及电子设备 | |
CN112749737A (zh) | 图像分类方法及装置、电子设备、存储介质 | |
CN114492540B (zh) | 目标检测模型的训练方法、装置、计算机设备及存储介质 | |
CN112364747A (zh) | 一种有限样本下的目标检测方法 | |
Cui et al. | Informative Bayesian neural network priors for weak signals | |
EP4191480A1 (en) | Neural network model training method and apparatus for complex characteristic classification and common localization | |
Salem et al. | Sequential dimension reduction for learning features of expensive black-box functions | |
CN113516019A (zh) | 高光谱图像解混方法、装置及电子设备 | |
Shono | Application of support vector regression to CPUE analysis for southern bluefin tuna Thunnus maccoyii, and its comparison with conventional methods | |
CN115631388B (zh) | 图像分类方法、装置、电子设备及存储介质 | |
CN117291250A (zh) | 一种用于图像分割的神经网络剪枝方法 | |
CN109886299B (zh) | 一种用户画像方法、装置、可读存储介质及终端设备 | |
KR102110316B1 (ko) | 뉴럴 네트워크를 이용한 변분 추론 방법 및 장치 |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CB03 | Change of inventor or designer information |
Inventor after: Luo Jianxiang Inventor after: Liu Chuang Inventor after: Hu Junyi Inventor after: Liu Qianqiao Inventor after: Zhang Yifu Inventor before: Luo Jianxiang Inventor before: Liu Chuang Inventor before: Hu Junyi Inventor before: Liu Qianqiao Inventor before: Zhang Yifu |
|
CB03 | Change of inventor or designer information | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240506 Address after: 710000, 1st to 5th floors, Building 15, Qianhai Garden, Silk Road (Xi'an), No. 900 Xitai Road, High tech Zone, Xi'an City, Shaanxi Province Patentee after: XI'AN GLASSSIX NETWORK TECHNOLOGY CO.,LTD. Country or region after: China Address before: No.3, 26 / F, building 3, No.88, Jitai fifth road, hi tech Zone, Chengdu, Sichuan 610000 Patentee before: GLASSSIC TECHNOLOGY (CHENGDU) Co.,Ltd. Country or region before: China |
|
TR01 | Transfer of patent right |