CN114902240A - 神经网络通道数搜索方法和装置 - Google Patents
神经网络通道数搜索方法和装置 Download PDFInfo
- Publication number
- CN114902240A CN114902240A CN202080091992.7A CN202080091992A CN114902240A CN 114902240 A CN114902240 A CN 114902240A CN 202080091992 A CN202080091992 A CN 202080091992A CN 114902240 A CN114902240 A CN 114902240A
- Authority
- CN
- China
- Prior art keywords
- sub
- weighting coefficients
- feature
- tensors
- feature tensors
- 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
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 84
- 230000015654 memory Effects 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 27
- 238000003672 processing method Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 abstract description 18
- 238000005516 engineering process Methods 0.000 abstract description 16
- 238000011176 pooling Methods 0.000 description 33
- 238000004891 communication Methods 0.000 description 21
- 238000013527 convolutional neural network Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 17
- 239000011159 matrix material Substances 0.000 description 14
- 238000012549 training Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 12
- 238000013473 artificial intelligence Methods 0.000 description 5
- 230000006835 compression Effects 0.000 description 5
- 238000007906 compression Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000037361 pathway Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 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
Images
Classifications
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
一种神经网络通道数搜索方法和装置，能够实现可微分搜索技术能够进行网络通道数搜索问题，在保证网络性能的同时，减少网络的计算复杂度。该方法包括：确定卷积层的输出通道数N，N为正整数(S301)；将卷积层输出的特征张量分割为n个子特征张量，每个子特征张量的通道数为N/n，n为可以被N整除的整数，且n≥2(S302)；确定n组加权系数，每组加权系数包括多个加权系数，多个加权系数与n个子特征张量中的多个子特征张量一一对应(S303)；确定n组加权系数中每组加权系数中的最大值所对应的子特征张量(S304)，以得到n个所述最大值所对应的子特征张量；根据n个最大值所对应的子特征张量重新确定卷积层的输出通道数(S305)。
Description
PCT国内申请，说明书已公开。
Claims (16)
- PCT国内申请，权利要求书已公开。
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/078413 WO2021179117A1 (zh) | 2020-03-09 | 2020-03-09 | 神经网络通道数搜索方法和装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114902240A true CN114902240A (zh) | 2022-08-12 |
Family
ID=77671220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080091992.7A Pending CN114902240A (zh) | 2020-03-09 | 2020-03-09 | 神经网络通道数搜索方法和装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114902240A (zh) |
| WO (1) | WO2021179117A1 (zh) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117634711B (zh) * | 2024-01-25 | 2024-05-14 | 北京壁仞科技开发有限公司 | 张量维度切分方法、系统、设备和介质 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631466B (zh) * | 2015-12-21 | 2019-05-07 | 中国科学院深圳先进技术研究院 | 图像分类的方法及装置 |
| US10691975B2 (en) * | 2017-07-19 | 2020-06-23 | XNOR.ai, Inc. | Lookup-based convolutional neural network |
| CN108596274A (zh) * | 2018-05-09 | 2018-09-28 | 国网浙江省电力有限公司 | 基于卷积神经网络的图像分类方法 |
| CN109635842A (zh) * | 2018-11-14 | 2019-04-16 | 平安科技（深圳）有限公司 | 一种图像分类方法、装置及计算机可读存储介质 |
| CN110197258B (zh) * | 2019-05-29 | 2021-10-29 | 北京市商汤科技开发有限公司 | 神经网络搜索方法、图像处理方法及装置、设备和介质 |
| CN110533068B (zh) * | 2019-07-22 | 2020-07-17 | 杭州电子科技大学 | 一种基于分类卷积神经网络的图像对象识别方法 |
-
2020
- 2020-03-09 CN CN202080091992.7A patent/CN114902240A/zh active Pending
- 2020-03-09 WO PCT/CN2020/078413 patent/WO2021179117A1/zh active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021179117A1 (zh) | 2021-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mahmoud et al. | Diffy: A Déjà vu-free differential deep neural network accelerator | |
| US10891537B2 (en) | Convolutional neural network-based image processing method and image processing apparatus | |
| US20210398252A1 (en) | Image denoising method and apparatus | |
| WO2021018163A1 (zh) | 神经网络的搜索方法及装置 | |
| CN108765425B (zh) | 图像分割方法、装置、计算机设备和存储介质 | |
| CN111914997B (zh) | 训练神经网络的方法、图像处理方法及装置 | |
| CN112561027A (zh) | 神经网络架构搜索方法、图像处理方法、装置和存储介质 | |
| CN111445418A (zh) | 图像去雾处理方法、装置及计算机设备 | |
| CN110020639B (zh) | 视频特征提取方法及相关设备 | |
| US11836971B2 (en) | Method and device with convolution neural network processing | |
| CN112215332A (zh) | 神经网络结构的搜索方法、图像处理方法和装置 | |
| EP4379607A1 (en) | Neural network accelerator, and data processing method for neural network accelerator | |
| CN112862023B (zh) | 对象密度确定方法、装置、计算机设备和存储介质 | |
| CN111260020A (zh) | 卷积神经网络计算的方法和装置 | |
| CN111695673A (zh) | 训练神经网络预测器的方法、图像处理方法及装置 | |
| CN111709415B (zh) | 目标检测方法、装置、计算机设备和存储介质 | |
| CN114067007A (zh) | 图像处理方法与装置、神经网络训练的方法与装置 | |
| CN116547694A (zh) | 用于对模糊图像去模糊的方法和系统 | |
| CN114902240A (zh) | 神经网络通道数搜索方法和装置 | |
| CN112016522A (zh) | 一种视频数据处理方法、系统及相关组件 | |
| WO2023122896A1 (zh) | 一种数据处理方法和装置 | |
| Zhao et al. | A high-performance accelerator for super-resolution processing on embedded GPU | |
| Khan et al. | Binarized convolutional neural networks for efficient inference on GPUs | |
| WO2022141094A1 (zh) | 模型生成方法、图像处理方法、装置及可读存储介质 | |
| CN114049491A (zh) | 指纹分割模型训练、指纹分割方法、装置、设备及介质 |
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 |