CN107943751A - A kind of autonomous channel convolution method based on depth convolution confrontation network model - Google Patents
A kind of autonomous channel convolution method based on depth convolution confrontation network model Download PDFInfo
- Publication number
- CN107943751A CN107943751A CN201711122542.6A CN201711122542A CN107943751A CN 107943751 A CN107943751 A CN 107943751A CN 201711122542 A CN201711122542 A CN 201711122542A CN 107943751 A CN107943751 A CN 107943751A
- Authority
- CN
- China
- Prior art keywords
- convolution
- mrow
- autonomous channel
- maker
- network model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
- G06F17/153—Multidimensional correlation or convolution
-
- 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
- G06N3/045—Combinations of networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Mathematics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of autonomous channel convolution method based on depth convolution confrontation network model, belong to deep learning field of neural networks, comprise the following steps：S1, construction are originally generated confrontation network model；S2, construction depth convolutional neural networks are as maker and arbiter；S3, initialization random noise, input in maker；S4, carry out convolution operation using autonomous channel convolution in neutral net to image；S5, subsequently trained loss function that autonomous channel convolution operation obtains input maker.The confrontation network model of the depth convolution based on autonomous channel convolution of this method structure, change arbiter, maker receives the convolution mode after picture, by by the different passage independence convolution of image, reducing parameter amount, while improve the training effectiveness of whole network.
Description
Technical field
The present invention relates to deep learning nerual network technique field, and in particular to one kind is based on depth convolution confrontation network mould
The autonomous channel convolution method of type.
Background technology
Production confrontation network (Generative Adversarial Network, abbreviation GAN) is by Goodfellow
In the deep learning frame that 2014 propose, it is based on the thought of " game theory ", construction maker (generator) and arbiter
(discriminator) two kinds of models, the former generates image by the Uniform noise or gaussian random noise for inputting (0,1), after
Person differentiates the image of input, determines the image from data set or the image produced by maker.
In traditional confrontation network model, all passages of same convolution collecting image are used to carry out convolution,
And a kind of method for improving whole network training effectiveness is urgently proposed at present, by the way that each passage is independent, utilize difference
Convolution kernel carry out convolution, finally all characteristic patterns are merged, reduce the parameter amount used.
The content of the invention
The purpose of the present invention is to solve drawbacks described above of the prior art, there is provided one kind is based on depth convolution confrontation net
The autonomous channel convolution method of network model.
The purpose of the present invention can be reached by adopting the following technical scheme that：
A kind of autonomous channel convolution method based on depth convolution confrontation network model, the autonomous channel convolution method
Comprise the following steps：
S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress network instruction
Practice；
S2, construction depth convolutional neural networks are as maker and arbiter；
S3, initialization random noise, input in maker；
S4, carry out convolution operation using autonomous channel convolution in neutral net to image；
S5, subsequently trained loss function that autonomous channel convolution operation obtains input maker.
Further, the step S4 detailed processes are as follows：
S41, by picture breakdown be tri- passages of R, G, B；
S42, the different passages for image, convolution is carried out using different convolution kernels.
Further, the step S5 detailed processes are as follows：
S51, the characteristics of image figure that will be obtained after the convolution of autonomous channel, input in arbiter and are differentiated；
S52, subsequently trained loss function that autonomous channel convolution operation obtains input maker.
Further, the expression formula of the loss function is：
Wherein, D (x) represents differentiation of the arbiter to image, and pr represents the distribution of data images, and pg represents generation image
Distribution, λ is hyper parameter,For gradient, E is the functional symbol for taking average.
The present invention is had the following advantages relative to the prior art and effect：
High efficiency：The present invention changes according to the operating process of autonomous channel convolution and uses same convolution kernel pair in the past
All passages carry out the operating process of convolution, creatively propose and different passages is carried out using multiple and different convolution kernels
Convolution, reduces the usage amount of parameter, improves the training effectiveness of whole network.
Brief description of the drawings
Fig. 1 is the flow chart of the autonomous channel convolution method disclosed by the invention based on depth convolution confrontation network model；
Fig. 2 is the schematic diagram of autonomous channel convolution in the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiments obtained without making creative work, belong to the scope of protection of the invention.
Embodiment
Present embodiment discloses a kind of autonomous channel convolution method based on depth convolution confrontation network model, specifically include
The following steps：
Step S1, construction is originally generated confrontation network model, is inputted by maker generation image to arbiter and carries out net
Network training.
Step S2, construction depth convolutional neural networks are as maker and arbiter.
Different convolution kernels, is embodied in difference, the difference of ranks number of matrix numerical value.
Multiple convolution kernels are constructed, during image is handled, different convolution kernels is meant in network training
Different characteristic of the process learning to generation image.
In traditional confrontation network model, all passages of same convolution collecting image are used to carry out convolution,
And this method is independent by each passage, convolution is carried out using different convolution kernels, finally merges all characteristic patterns, is reduced
Parameter amount, also improves the training effectiveness of whole network.
In practical applications, it should which according to the complexity of data images feature, the number of convolution kernel is set.
Step S3, random noise is initialized, is inputted in maker.
Step S4, convolution operation is carried out to image using autonomous channel convolution in neutral net.
Specific method is as follows：
S41, by picture breakdown into tri- passages of R, G, B；
S42, for different passages, utilize different convolution kernels to carry out convolution.
Step S5, the loss function input maker that autonomous channel convolution operation obtains subsequently is trained.Specific mistake
Journey is as follows：
S51, by the characteristic pattern after convolution in step S4, input arbiter is differentiated；
S52, subsequently trained loss function that autonomous channel convolution operation obtains input maker.
The effect of loss function is to weigh the ability that arbiter judges generation image.The value of loss function is smaller, explanation
In current iteration, arbiter can have the generation image of preferable performance discrimination maker；Property that is on the contrary then illustrating arbiter
Can be poor.
The expression formula of loss function is：
Wherein, D (x) represents differentiation of the arbiter to image, and pr represents the distribution of data images, and pg represents generation image
Distribution, λ is hyper parameter,For gradient.
In conclusion present embodiment discloses a kind of depth convolution based on autonomous channel convolution to resist network model, pass
The depth convolution confrontation network model of system is to carry out convolution using all passages of same convolution collecting image, and this method will
Each passage is independent, carries out convolution using different convolution kernels, finally merges all characteristic patterns, reduce parameter amount,
Also improve the training effectiveness of whole network.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention and from above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (4)
1. a kind of autonomous channel convolution method based on depth convolution confrontation network model, it is characterised in that described independently leads to
Road convolution method comprises the following steps：
S1, construction are originally generated confrontation network model, and generating image by maker inputs to arbiter progress network training；
S2, construction depth convolutional neural networks are as maker and arbiter；
S3, initialization random noise, input in maker；
S4, carry out convolution operation using autonomous channel convolution in neutral net to image；
S5, subsequently trained loss function that autonomous channel convolution operation obtains input maker.
2. a kind of autonomous channel convolution method based on depth convolution confrontation network model according to claim 1, it is special
Sign is that the step S4 detailed processes are as follows：
S41, by picture breakdown be tri- passages of R, G, B；
S42, the different passages for image, convolution is carried out using different convolution kernels.
3. a kind of autonomous channel convolution method based on depth convolution confrontation network model according to claim 1, it is special
Sign is that the step S5 detailed processes are as follows：
S51, the characteristics of image figure that will be obtained after the convolution of autonomous channel, input in arbiter and are differentiated；
S52, subsequently trained loss function that autonomous channel convolution operation obtains input maker；
S53, input the average of all loss functions and continue to be trained into maker.
4. a kind of autonomous channel convolution method based on depth convolution confrontation network model according to claim 3, it is special
Sign is that the expression formula of the loss function is：
<mrow>
<mi>L</mi>
<mrow>
<mo>(</mo>
<mi>D</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>-</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>x</mi>
<mo>~</mo>
<mi>p</mi>
<mi>r</mi>
</mrow>
</msub>
<mo>&lsqb;</mo>
<mi>D</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>+</mo>
<msub>
<mi>E</mi>
<mrow>
<mi>x</mi>
<mo>~</mo>
<mi>p</mi>
<mi>g</mi>
</mrow>
</msub>
<mo>&lsqb;</mo>
<mi>D</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
<mo>+</mo>
<msub>
<mi>&lambda;E</mi>
<mrow>
<mi>x</mi>
<mo>~</mo>
<mi>X</mi>
</mrow>
</msub>
<msub>
<mo>&dtri;</mo>
<mi>x</mi>
</msub>
</mrow>
Wherein, D (x) represents differentiation of the arbiter to image, and pr represents the distribution of data images, and pg represents point of generation image
Cloth, λ are hyper parameter,For gradient, E is the functional symbol for taking average.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711122542.6A CN107943751A (en) | 2017-11-14 | 2017-11-14 | A kind of autonomous channel convolution method based on depth convolution confrontation network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711122542.6A CN107943751A (en) | 2017-11-14 | 2017-11-14 | A kind of autonomous channel convolution method based on depth convolution confrontation network model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107943751A true CN107943751A (en) | 2018-04-20 |
Family
ID=61934054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711122542.6A Pending CN107943751A (en) | 2017-11-14 | 2017-11-14 | A kind of autonomous channel convolution method based on depth convolution confrontation network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107943751A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345441A (en) * | 2018-10-19 | 2019-02-15 | 上海唯识律简信息科技有限公司 | A kind of de-watermarked method and system of image based on generation confrontation network |
| CN110598677A (en) * | 2019-10-08 | 2019-12-20 | 电子科技大学 | Space-time multi-channel deep learning system for automatic modulation recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778785A (en) * | 2016-12-23 | 2017-05-31 | 东软集团股份有限公司 | Build the method for image characteristics extraction model and method, the device of image recognition |
| CN106997380A (en) * | 2017-03-21 | 2017-08-01 | 北京工业大学 | Imaging spectrum safe retrieving method based on DCGAN depth networks |
| CN107103590A (en) * | 2017-03-22 | 2017-08-29 | 华南理工大学 | A kind of image for resisting generation network based on depth convolution reflects minimizing technology |
| CN107293289A (en) * | 2017-06-13 | 2017-10-24 | 南京医科大学 | A kind of speech production method that confrontation network is generated based on depth convolution |
| CN107292336A (en) * | 2017-06-12 | 2017-10-24 | 西安电子科技大学 | A kind of Classification of Polarimetric SAR Image method based on DCGAN |
-
2017
- 2017-11-14 CN CN201711122542.6A patent/CN107943751A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778785A (en) * | 2016-12-23 | 2017-05-31 | 东软集团股份有限公司 | Build the method for image characteristics extraction model and method, the device of image recognition |
| CN106997380A (en) * | 2017-03-21 | 2017-08-01 | 北京工业大学 | Imaging spectrum safe retrieving method based on DCGAN depth networks |
| CN107103590A (en) * | 2017-03-22 | 2017-08-29 | 华南理工大学 | A kind of image for resisting generation network based on depth convolution reflects minimizing technology |
| CN107292336A (en) * | 2017-06-12 | 2017-10-24 | 西安电子科技大学 | A kind of Classification of Polarimetric SAR Image method based on DCGAN |
| CN107293289A (en) * | 2017-06-13 | 2017-10-24 | 南京医科大学 | A kind of speech production method that confrontation network is generated based on depth convolution |
Non-Patent Citations (2)
| Title |
|---|
| GULRAJANI ISHAAN等: "Improved Training of Wasserstein GANs", 《MACHINE LEARNING》 * |
| RAYMOND A. YEH等: "Semantic Image Inpainting with Deep Generative Models", 《COMPUTER VISION AND PATTERN RECOGNITION》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345441A (en) * | 2018-10-19 | 2019-02-15 | 上海唯识律简信息科技有限公司 | A kind of de-watermarked method and system of image based on generation confrontation network |
| CN110598677A (en) * | 2019-10-08 | 2019-12-20 | 电子科技大学 | Space-time multi-channel deep learning system for automatic modulation recognition |
| CN110598677B (en) * | 2019-10-08 | 2021-01-26 | 电子科技大学 | Space-time multi-channel deep learning system for automatic modulation recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862377A (en) | A kind of packet convolution method that confrontation network model is generated based on text image | |
| CN107886169A (en) | A kind of multiple dimensioned convolution kernel method that confrontation network model is generated based on text image | |
| CN107590531A (en) | A kind of WGAN methods based on text generation | |
| CN107590518A (en) | A kind of confrontation network training method of multiple features study | |
| CN107871142A (en) | A kind of empty convolution method based on depth convolution confrontation network model | |
| CN107944546A (en) | It is a kind of based on be originally generated confrontation network model residual error network method | |
| Kobler et al. | Variational networks: connecting variational methods and deep learning | |
| CN108009568A (en) | A kind of pedestrian detection method based on WGAN models | |
| CN109145939A (en) | A kind of binary channels convolutional neural networks semantic segmentation method of Small object sensitivity | |
| Zweig et al. | Interponet, a brain inspired neural network for optical flow dense interpolation | |
| CN109191491A (en) | The method for tracking target and system of the twin network of full convolution based on multilayer feature fusion | |
| CN107563509A (en) | A kind of dynamic adjustment algorithm for the condition DCGAN models that feature based returns | |
| CN107767413A (en) | A kind of image depth estimation method based on convolutional neural networks | |
| CN107506722A (en) | One kind is based on depth sparse convolution neutral net face emotion identification method | |
| CN107679491A (en) | A kind of 3D convolutional neural networks sign Language Recognition Methods for merging multi-modal data | |
| CN107992944A (en) | It is a kind of based on be originally generated confrontation network model multiple dimensioned convolution method | |
| CN106447626A (en) | Blurred kernel dimension estimation method and system based on deep learning | |
| CN107273936A (en) | A kind of GAN image processing methods and system | |
| CN107943750A (en) | A kind of decomposition convolution method based on WGAN models | |
| CN107644217A (en) | Method for tracking target based on convolutional neural networks and correlation filter | |
| CN109214337A (en) | A kind of Demographics' method, apparatus, equipment and computer readable storage medium | |
| CN109360159A (en) | A kind of image completion method based on generation confrontation network model | |
| CN109064522A (en) | The Chinese character style generation method of confrontation network is generated based on condition | |
| CN108470196A (en) | A method of handwritten numeral is generated based on depth convolution confrontation network model | |
| CN107943751A (en) | A kind of autonomous channel convolution method based on depth convolution confrontation network model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |