CN110443286A - Training method, image-recognizing method and the device of neural network model - Google Patents
Training method, image-recognizing method and the device of neural network model Download PDFInfo
- Publication number
- CN110443286A CN110443286A CN201910651552.1A CN201910651552A CN110443286A CN 110443286 A CN110443286 A CN 110443286A CN 201910651552 A CN201910651552 A CN 201910651552A CN 110443286 A CN110443286 A CN 110443286A
- Authority
- CN
- China
- Prior art keywords
- branching networks
- neural network
- network model
- layer
- training
- 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
- 238000003062 neural network model Methods 0.000 title claims abstract description 82
- 238000012549 training Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000002708 enhancing effect Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 230000000977 initiatory effect Effects 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 8
- 238000013528 artificial neural network Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 12
- 238000013527 convolutional neural network Methods 0.000 description 11
- 238000013135 deep learning Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 208000001491 myopia Diseases 0.000 description 3
- 210000004218 nerve net Anatomy 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007306 functionalization reaction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
This application discloses a kind of training method of neural network model, image-recognizing method and device, the training method of the neural network model includes: acquisition neural network model；Wherein, neural network model is the neural network model being trained, and neural network model includes at least the first branching networks；The second branching networks are added in neural network model；The second branching networks will be input to, to training dataset individually to be trained to the second branching networks；First branching networks and the second branching networks are merged, to complete the training of neural network model.By the above-mentioned means, can be improved the efficiency of neural network model training, and the recognition effect of original neural network model is not influenced.
Description
Technical field
This application involves technical field of image processing, training method, image more particularly to a kind of neural network model
Recognition methods and device.
Background technique
With the rise of deep learning, more and more technologies realize the image of picture or video flowing using deep learning
Identification.Compared to conventional method, deep learning avoids manual parameters and adjusts the complexity selected with manual features, by building
Deep-neural-network model, to data carry out multi-layer analysis and abstract feature extraction, with high accuracy, high reliability,
The characteristics of high-adaptability.Common image recognition application covers action recognition, recognition of face, target identification, scene Recognition etc..
Wherein, target identification and scene Recognition are known as image retrieval, the basis of image classification, scene understanding, environment sensing in mode
Not, the fields such as machine learning play an important role.
When carrying out image recognition using the neural network model trained, if being badly in need of adding new feature, have at present
Two methods: 1, a neural network model is individually created；2, the image with new feature is input to original nerve net
Network model carries out continuing to train.The former will consume double computing resource, and the latter's time consumption for training will be longer, can not react rapidly,
And after being unable to control addition new samples, to the recognition effect of original classification, it is more likely that will affect original recognition effect.
Summary of the invention
To solve the above problems, this application provides a kind of training method of neural network model, image-recognizing method with
And device, it can be improved the efficiency of neural network model training, and do not influence the recognition effect of original neural network model.
The technical solution that the application uses is: a kind of training method of neural network model is provided, this method comprises:
Obtain neural network model；Wherein, neural network model is the neural network model being trained, and neural network mould
Type includes at least the first branching networks；The second branching networks are added in neural network model；It will be input to training dataset
Second branching networks, individually to be trained to the second branching networks；First branching networks and the second branching networks are melted
It closes, to complete the training of neural network model.
Wherein, the second branching networks are added in neural network model, comprising: determine multiple convolution of the first branching networks
The output scale of module；The second branching networks are added to the certain volume product module in the first branching networks based on output scale demand
Block.
Wherein, the first branching networks include: input layer；First convolution module；First pond layer；Second convolution module；The
Two pond layers；Third convolution module；Volume Four volume module；5th convolution module；First global average pond layer；First full connection
Layer；First sorter network layer；First branching networks output layer.
Wherein, the second branching networks include: feature selecting layer, connect Volume Four volume module；6th convolution module；Second is complete
The average pond layer of office；Second full articulamentum；Second sorter network layer；Second branching networks output layer.
Wherein, network mode further include: fused layer connects the first branching networks output layer and the output of the second branching networks
Layer；Merge output layer.
Wherein, the second branching networks will be input to training dataset, individually to be trained to the second branching networks, packet
It includes: obtaining to training dataset；It treats training dataset and carries out data enhancing processing；By data enhancing treated number to be trained
The second branching networks are input to according to collection, the second branching networks are individually trained.
Wherein, by data enhancing, treated is input to the second branching networks to training dataset, to the second branching networks
It is individually trained, comprising: the convolution initiation parameter of the second branching networks of setting；Fix multiple convolution of the first branching networks
The parameter of module, by data enhancing, treated is input to the second branching networks to training dataset, to the second branching networks into
Row individually training.
Another technical solution that the application uses is: a kind of image-recognizing method is provided, this method comprises: obtaining wait know
Other image；Images to be recognized is input to setting neural network model；Wherein, setting neural network model is using such as above-mentioned
Method training obtains；Export recognition result.
Another technical solution that the application uses is: providing a kind of pattern recognition device, which includes
Processor and memory connected to the processor, memory is for storing program data, and processor is for executing program data
To realize such as above-mentioned method.
Another technical solution that the application uses is: providing a kind of computer storage medium, the computer storage medium
In be stored with program data, program data is when being executed by processor, to realize such as above-mentioned method.
The training method of neural network model provided by the present application includes: acquisition neural network model；Wherein, neural network
Model is the neural network model being trained, and neural network model includes at least the first branching networks；In nerve
The second branching networks are added in network model；The second branching networks will be input to training dataset, to the second branching networks
Individually trained；First branching networks and the second branching networks are merged, to complete the training of neural network model.It is logical
Aforesaid way is crossed, when needing to identify new feature using existing neural network model, without newly one neural network of training
Model trains original neural network model again, improves the efficiency of neural network model training, and not
It will affect the recognition effect of original neural network model.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.Wherein:
Fig. 1 is the flow diagram of the training method of neural network model provided by the embodiments of the present application；
Fig. 2 is neural network model schematic diagram provided by the embodiments of the present application；
Fig. 3 is the flow diagram of the training of the second branching networks provided by the embodiments of the present application；
Fig. 4 is another flow diagram of the training of the second branching networks provided by the embodiments of the present application；
Fig. 5 is the flow diagram of image-recognizing method provided by the present application；
Fig. 6 is the structural schematic diagram of pattern recognition device provided by the embodiments of the present application；
Fig. 7 is the structural schematic diagram of computer storage medium provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description.It is understood that specific embodiment described herein is only used for explaining the application, rather than to the limit of the application
It is fixed.It also should be noted that illustrating only part relevant to the application for ease of description, in attached drawing and not all knot
Structure.Based on the embodiment in the application, obtained by those of ordinary skill in the art without making creative efforts
Every other embodiment, shall fall in the protection scope of this application.
Term " first ", " second " in the application etc. be for distinguishing different objects, rather than it is specific suitable for describing
Sequence.In addition, term " includes " and " having " and their any deformations, it is intended that cover and non-exclusive include.Such as comprising
The process, method, system, product or equipment of a series of steps or units are not limited to listed step or unit, and
It is optionally further comprising the step of not listing or unit, or optionally further comprising for these process, methods, product or equipment
Intrinsic other step or units.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Refering to fig. 1, Fig. 1 is the flow diagram of the training method of neural network model provided by the embodiments of the present application, should
Method includes:
Step 11: obtaining neural network model；Wherein, neural network model is the neural network mould being trained
Type, and neural network model includes at least the first branching networks.
Wherein, neural network model is a carrier for deep learning (Deep Learning, DL), deep learning
It is one of technology and the research field of machine learning, there is the artificial neural network (Artifitial of hierarchical structure by establishing
Neural Networks, ANNs), artificial intelligence is realized in computing systems.Since stratum ANN can carry out input information
It successively extracts and screens, therefore deep learning has representative learning (representation learning) ability, may be implemented
Supervised learning and unsupervised learning end to end.In addition, deep learning may also participate in building intensified learning (reinforcement
Learning) system forms deeply study.
By taking convolutional neural networks as an example, convolutional neural networks (Convolutional Neural Networks, CNN) are
One kind includes convolutional calculation and the feedforward neural network (Feedforward Neural Networks) with depth structure, is
One of the representative algorithm of deep learning (deep learning).
Wherein, convolutional neural networks include input layer, hidden layer and output layer.Hidden layer therein include convolution module,
Pond layer, full articulamentum.
1) input layer of convolutional neural networks can handle multidimensional data, and the input layer of one-dimensional convolutional neural networks receives one
Dimension or two-dimensional array, wherein one-dimension array is usually time or spectral sample；Two-dimensional array may include multiple channels；Two dimension volume
The input layer of product neural network receives two dimension or three-dimensional array；The input layer of Three dimensional convolution neural network receives four-dimensional array.
In the present embodiment, which is mainly used for handling image, it is therefore possible to use three-dimensional volume
Product neural network comprising three-dimensional data channel, i.e. two-dimensional image vegetarian refreshments and RGB (RGB) data channel.
2) function of convolution module is that feature extraction is carried out to input data, and internal includes multiple convolution kernels, and group is coiled
Each element of product core corresponds to a weight coefficient and a departure (bias vector), is similar to a feed forward neural
The neuron (neuron) of network.Multiple nerves in the region being closely located in each neuron and preceding layer in convolution module
Member is connected, and the size in region depends on the size of convolution kernel.
After convolution module carries out feature extraction, the characteristic pattern of output can be passed to pond layer and carry out feature selecting and letter
Breath filtering.Pond layer includes presetting pond function, and function is that the result of a single point in characteristic pattern is replaced with its is adjacent
The characteristic pattern statistic in region.Pond layer choosing takes pond region identical as convolution kernel scanning feature figure step, You Chihua size, step
Long and filling control.
Full articulamentum in convolutional neural networks is equivalent to the hidden layer in conventional feed forward neural network.Full articulamentum is usual
The decline in convolutional neural networks hidden layer is built, and only transmits signal to other full articulamentums.Characteristic pattern is connecting entirely
Three-dimensional structure can be lost in layer, vector is expanded as and next layer is transferred to by excitation function.
3) upstream of output layer is usually full articulamentum in convolutional neural networks, therefore its structure and working principle and tradition
Output layer in feedforward neural network is identical.For image classification problem, output layer uses logical function or normalization index letter
Number (softmax function) output category label.
For example, carrying out identification output layer to image in the present embodiment may be designed as the center seat of output objects in images
Mark, size and classification.In image, semantic segmentation, output layer directly exports the classification results of each pixel.
Step 12: the second branching networks are added in neural network model.
Optionally, step 12 can specifically include: determine the output scale of multiple convolution modules of the first branching networks；Base
The second branching networks are added to the specific convolution module in the first branching networks in output scale demand.
As shown in Fig. 2, Fig. 2 is neural network model schematic diagram provided by the embodiments of the present application.
Wherein, the first branching networks include: input layer (INPUT)；First convolution module (ConvBlock)；First pond
Layer (Pooling)；Second convolution module；Second pond layer；Third convolution module；Volume Four volume module；5th convolution module；The
One global average pond layer (Global Average Pooling, GAP)；First full articulamentum (fully connected
layers,FC)；First sorter network layer (Softmax)；First branching networks output layer (Main_output).
Wherein, the second branching networks include: feature selecting layer (SelectBlock), connect Volume Four volume module；Volume six
Volume module；Second global average pond layer；Second full articulamentum；Second sorter network layer；Second branching networks output layer
(Branch_output)。
In addition, further including fused layer (Fusing) and fusion output layer (Fusing_output), fused layer connects first point
Branch network output layer and the second branching networks output layer.
In one embodiment, the output scale of the first convolution module can be arranged according to demand, for example, it exports scale
It can be N*N, wherein 100 < N < 300.For example, the common value of N can be 227.Further, the output ruler of the first pond layer
Degree is N/2*N/2；The output scale of second convolution module is N/2*N/2；The output scale of second pond layer is N/4*N/4；The
The output scale of three convolution modules is N/8*N/8；The output scale of Volume Four volume module is N/16*N/16；5th convolution module
Output scale be N/16*N/16.Feature selecting layer connects Volume Four volume module, and it is N/16* that the output scale of the two is identical
N/16。
In a specific embodiment, the output scale of the first convolution module is 168*168；The output ruler of first pond layer
Degree is 84*84；The output scale of second convolution module is 84*84；The output scale of second pond layer is 42*42；Third convolution
The output scale of module is 21*21；The output scale of Volume Four volume module is 11*11；The output scale of 5th convolution module is
11*11.The output scale of feature selecting layer is 11*11.
In the present embodiment, the second branching networks need to carry out bifurcated when penultimate characteristic pattern scale declines,
That is the scale of 11*11, because shallow-layer is mainly used for extracting feature, deep layer network is mainly used for being changed feature, extracts high
Grade semantic information；If only doing bifurcated using the last one full articulamentum, extracted information will receive final result
First branching networks are affected, and final effect is bad；Right side is the second branching networks part as shown in Figure 2, is first passed around
One feature selecting layer (SelectBlock), is weighted recombination to feature, acts on big feature to new samples and assigns weight more
Greatly, the convolution transform several times of legacy network is then carried out again, then is connect full articulamentum and classified.
Step 13: the second branching networks will be input to, to training dataset individually to be trained to the second branching networks.
Optionally, as shown in figure 3, Fig. 3 is the process signal of the training of the second branching networks provided by the embodiments of the present application
Figure, step 12 can specifically include:
Step 131: obtaining to training dataset.
It wherein, should be the data with new feature to training dataset.By taking image as an example, in an application scenarios, need
Then the first branching networks, which are to be trained to obtain to the image with A feature, is identified to the image in image with A feature
's.Further, to newly add B feature, then the second branching networks are added, inputting, there is the image of B feature to be trained.
Step 132: treating training dataset and carry out data enhancing processing.
In general, neural network needs a large amount of parameter, the parameter of various neural network is all millions of
Meter, and allows these parameters correctly to work, and a large amount of data is needed to be trained, and data are not in actual conditions
It is so much in our imaginations.Data are enhanced, i.e., such as overturns, translate or rotates using existing data, create
More data are come so that neural network has better extensive effect.
Step 133: by data enhancing, treated is input to the second branching networks to training dataset, to the second branched network
Network is individually trained.
In addition, as shown in figure 4, another process that Fig. 4 is the training of the second branching networks provided by the embodiments of the present application is shown
It is intended to, step 12 can specifically include:
Step 136: the convolution initiation parameter of the second branching networks of setting.
Convolution module parameter includes convolution kernel size, step-length and filling, and three has codetermined convolution module output feature
The size of figure is the hyper parameter of convolutional neural networks.Wherein convolution kernel size can specify as appointing less than input image size
Meaning value, convolution kernel is bigger, and extractible input feature vector is more complicated.
Wherein, the distance of position when convolution step-length defines convolution kernel adjacent inswept characteristic pattern twice, convolution step-length are 1
When, convolution kernel can inswept characteristic pattern one by one element, n-1 pixel can be skipped in scanning next time when step-length is n.
Calculated by the crosscorrelation of convolution kernel it is found that with convolution module stacking, the size of characteristic pattern can gradually reduce,
Such as 16 × 16 input picture after the convolution kernel of one step, packless 5 × 5,12 × 12 feature can be exported
Figure.For this purpose, filling is artificially to increase its size before characteristic pattern is by convolution kernel to offset dimensional contraction in calculating and influence
Method.Common fill method is by 0 filling and to repeat boundary value filling (replication padding).
Step 137: fixing the parameter of multiple convolution modules of the first branching networks, treated wait train by data enhancing
Data set is input to the second branching networks, is individually trained to the second branching networks.
Step 14: the first branching networks and the second branching networks being merged, to complete the training of neural network model.
The training method of neural network model provided in this embodiment includes: acquisition neural network model；Wherein, nerve net
Network model is the neural network model being trained, and neural network model includes at least the first branching networks；In mind
Through adding the second branching networks in network model；The second branching networks will be input to training dataset, to the second branched network
Network is individually trained；First branching networks and the second branching networks are merged, to complete the training of neural network model.
By the above-mentioned means, when needing to identify new feature using existing neural network model, without newly one nerve net of training
Network model trains original neural network model again, improves the efficiency of neural network model training, and
It will not influence the recognition effect of original neural network model.
It is to be appreciated that the method for the present embodiment can be applied to that the illegal picture or video of network are trained and are known
Not.For example, have been used for the external yellow model with short-sighted frequency mirror Huang that reflects, if application scenarios are different, can determine externally when the output of mirror Huang
Different output is made, can be adapted to using branching networks；Occur the violation picture of some bursts, existing model in short-sighted frequency
Can not identify, be added training set will affect it is effective if, such problems, such as short-sighted frequency can be solved using branching networks
Using the violation video of leakage, can constantly be propagated on platform, in another example there is a kind of watermark of porn site；For these
Problem is that have certain features, and specific some pictures, after method of the invention, violation picture discrimination is high, and misrecognition is very
It is few.
It is as shown in the table by taking SE-BN-Inception model as an example:
The model provided in this embodiment for increasing by the second branching networks on the basis of the first branching networks, at single picture
When reason, individual calculates time-consuming averagely increase 4.8ms, and video memory consumption increases 69MB, when batchs size is 12, individual calculating
Time-consuming averagely to increase 1ms, video memory consumption increases 129MB.It can find out from above-mentioned data, using the new mind with branching networks
When carrying out picture processing through network model, time-consuming compared to original neural network model increases seldom, and video memory consumption increases
It is relatively low, for through two different neural network models progress picture processing twice, greatly shorten processing
Time reduces memory consumption.
It is the flow diagram of image-recognizing method provided by the present application refering to Fig. 5, Fig. 5, this method comprises:
Step 51: obtaining images to be recognized.
Wherein, which can be single picture, can also be with a picture frame in video flowing, here with no restriction.
Step 52: images to be recognized is input to setting neural network model.
Wherein, setting neural network model is using as the training of the method for above-described embodiment obtains, and which is not described herein again.
Step 53: output recognition result.
It is the structural schematic diagram of pattern recognition device provided by the embodiments of the present application, image recognition dress refering to Fig. 6, Fig. 6
It sets 60 and includes processor 61 and the memory 62 connecting with processor 61, memory 62 is for storing program data, processor
61 for executing program data to realize following method:
Obtain neural network model；Wherein, neural network model is the neural network model being trained, and mind
The first branching networks are included at least through network model；The second branching networks are added in neural network model；It will be to training data
Collection is input to the second branching networks, individually to be trained to the second branching networks；By the first branching networks and the second branched network
Network is merged, to complete the training of neural network model.
Optionally, in another embodiment, processor 61 is for executing program data to realize following method: obtain to
Identify image；Images to be recognized is input to setting neural network model；Export recognition result.
It is the structural schematic diagram of computer storage medium provided by the embodiments of the present application refering to Fig. 7, Fig. 7, which deposits
Program data 71 is stored in storage media 70, program data 71 is when being executed by processor, to realize following method:
Obtain neural network model；Wherein, neural network model is the neural network model being trained, and mind
The first branching networks are included at least through network model；The second branching networks are added in neural network model；It will be to training data
Collection is input to the second branching networks, individually to be trained to the second branching networks；By the first branching networks and the second branched network
Network is merged, to complete the training of neural network model.
Optionally, in another embodiment, program data 71 is when being executed by processor, also to realize following side
Method: the output scale of multiple convolution modules of the first branching networks is determined；The second branching networks are added based on output scale demand
Add to the specific convolution module in the first branching networks.
Wherein, the first branching networks include: input layer；First convolution module, output scale are 168*168；First pond
Change layer, output scale is 84*84；Second convolution module, output scale are 84*84；Second pond layer, output scale are
42*42；Third convolution module, output scale are 21*21；Volume Four volume module, output scale are 11*11；5th convolution
Module, output scale are 11*11；First global average pond layer；First full articulamentum；First sorter network layer；First point
Branch network output layer.
Wherein, the second branching networks include: feature selecting layer, connect Volume Four volume module, scale 11*11；6th
Convolution module；Second global average pond layer；Second full articulamentum；Second sorter network layer；Second branching networks output layer.
Wherein, network mode further include: fused layer connects the first branching networks output layer and the output of the second branching networks
Layer；Merge output layer.
Optionally, in another embodiment, program data 71 is when being executed by processor, also to realize following side
Method: it obtains to training dataset；It treats training dataset and carries out data enhancing processing；By data enhancing treated number to be trained
The second branching networks are input to according to collection, the second branching networks are individually trained.
Optionally, in another embodiment, program data 71 is when being executed by processor, also to realize following side
Method: the convolution initiation parameter of the second branching networks of setting；The parameter for fixing multiple convolution modules of the first branching networks, will count
According to enhancing, treated is input to the second branching networks to training dataset, is individually trained to the second branching networks.
In several embodiments provided herein, it should be understood that disclosed method and equipment, Ke Yitong
Other modes are crossed to realize.For example, equipment embodiment described above is only schematical, for example, the module or
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units
Or component can be combined or can be integrated into another system, or some features can be ignored or not executed.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize present embodiment scheme according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the application can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit in above-mentioned other embodiments is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, the application
Technical solution substantially all or part of the part that contributes to existing technology or the technical solution can be in other words
It is expressed in the form of software products, which is stored in a storage medium, including some instructions are used
So that a computer equipment (can be personal computer, server or the network equipment etc.) or processor
(processor) all or part of the steps of each embodiment the method for the application is executed.And storage medium packet above-mentioned
It includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random
Access Memory), the various media that can store program code such as magnetic or disk.
The foregoing is merely presently filed embodiments, are not intended to limit the scope of the patents of the application, all according to this
Equivalent structure or equivalent flow shift made by application specification and accompanying drawing content, it is relevant to be applied directly or indirectly in other
Technical field similarly includes in the scope of patent protection of the application.
Claims (10)
1. a kind of training method of neural network model, which is characterized in that the described method includes:
Obtain neural network model；Wherein, the neural network model is the neural network model being trained, and institute
Neural network model is stated including at least the first branching networks；
The second branching networks are added in the neural network model；
Second branching networks will be input to, to training dataset individually to be trained to the second branching networks；
First branching networks and second branching networks are merged, to complete the training of neural network model.
2. the method according to claim 1, wherein
It is described that the second branching networks are added in the neural network model, comprising:
Determine the output scale of multiple convolution modules of first branching networks；
Second branching networks are added to the specific convolution module in first branching networks based on output scale demand.
3. according to the method described in claim 2, it is characterized in that,
First branching networks include:
Input layer；
First convolution module；
First pond layer；
Second convolution module；
Second pond layer；
Third convolution module；
Volume Four volume module；
5th convolution module；
First global average pond layer；
First full articulamentum；
First sorter network layer；
First branching networks output layer.
4. according to the method described in claim 3, it is characterized in that,
Second branching networks include:
Feature selecting layer connects the Volume Four volume module；
6th convolution module；
Second global average pond layer；
Second full articulamentum；
Second sorter network layer；
Second branching networks output layer.
5. according to the method described in claim 4, it is characterized in that,
The network mode further include:
Fused layer connects the first branching networks output layer and the second branching networks output layer；
Merge output layer.
6. the method according to claim 1, wherein
It is described that second branching networks will be input to training dataset, individually to be trained to the second branching networks, packet
It includes:
It obtains to training dataset；
Data enhancing processing is carried out to training dataset to described；
By data enhancing treated it is described be input to second branching networks to training dataset, to second branched network
Network is individually trained.
7. according to the method described in claim 6, it is characterized in that,
It is described by data enhancing treated it is described be input to second branching networks to training dataset, to described second point
Branch network is individually trained, comprising:
The convolution initiation parameter of second branching networks is set；
The parameter of multiple convolution modules of fixed first branching networks, by data enhancing, that treated is described to training data
Collection is input to second branching networks, is individually trained to second branching networks.
8. a kind of image-recognizing method, which is characterized in that the described method includes:
Obtain images to be recognized；
The images to be recognized is input to setting neural network model；Wherein, the setting neural network model is using such as
The described in any item method training of claim 1-7 obtain；
Export recognition result.
9. a kind of pattern recognition device, which is characterized in that described image identification device include processor and with the processor
The memory of connection, the memory is for storing program data, and the processor is for executing described program data to realize
The method according to claim 1.
10. a kind of computer storage medium, which is characterized in that program data is stored in the computer storage medium, it is described
Program data by the processor when being executed, to realize the method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910651552.1A CN110443286B (en) | 2019-07-18 | 2019-07-18 | Training method of neural network model, image recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910651552.1A CN110443286B (en) | 2019-07-18 | 2019-07-18 | Training method of neural network model, image recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110443286A true CN110443286A (en) | 2019-11-12 |
| CN110443286B CN110443286B (en) | 2024-06-04 |
Family
ID=68430731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910651552.1A Active CN110443286B (en) | 2019-07-18 | 2019-07-18 | Training method of neural network model, image recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110443286B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866565A (en) * | 2019-11-26 | 2020-03-06 | 重庆邮电大学 | Multi-branch image classification method based on convolutional neural network |
| CN110929616A (en) * | 2019-11-14 | 2020-03-27 | 北京达佳互联信息技术有限公司 | Human hand recognition method and device, electronic equipment and storage medium |
| CN111428671A (en) * | 2020-03-31 | 2020-07-17 | 杭州博雅鸿图视频技术有限公司 | Face structured information identification method, system, device and storage medium |
| CN111695616A (en) * | 2020-05-29 | 2020-09-22 | 平安科技（深圳）有限公司 | Multi-modal data-based lesion classification method and related product |
| CN112052949A (en) * | 2020-08-21 | 2020-12-08 | 北京市商汤科技开发有限公司 | Target model obtaining method and device, electronic equipment and storage medium |
| CN112712126A (en) * | 2021-01-05 | 2021-04-27 | 南京大学 | Picture identification method |
| CN113537484A (en) * | 2020-04-14 | 2021-10-22 | 中国人民银行数字货币研究所 | Neural network training method, image coding and decoding method and related products |
| CN114092649A (en) * | 2021-11-25 | 2022-02-25 | 马上消费金融股份有限公司 | Picture generation method and device based on neural network |
| CN115511124A (en) * | 2022-09-27 | 2022-12-23 | 上海网商电子商务有限公司 | Customer grading method based on after-sale maintenance records |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295521A (en) * | 2016-07-29 | 2017-01-04 | 厦门美图之家科技有限公司 | A kind of gender identification method based on multi output convolutional neural networks, device and the equipment of calculating |
| CN106845549A (en) * | 2017-01-22 | 2017-06-13 | 珠海习悦信息技术有限公司 | A kind of method and device of the scene based on multi-task learning and target identification |
| CN106934456A (en) * | 2017-03-16 | 2017-07-07 | 山东理工大学 | A kind of depth convolutional neural networks model building method |
| WO2018065158A1 (en) * | 2016-10-06 | 2018-04-12 | Siemens Aktiengesellschaft | Computer device for training a deep neural network |
| WO2019001209A1 (en) * | 2017-06-28 | 2019-01-03 | 苏州比格威医疗科技有限公司 | Classification algorithm for retinal oct image based on three-dimensional convolutional neural network |
| US20190130218A1 (en) * | 2017-11-01 | 2019-05-02 | Salesforce.Com, Inc. | Training a neural network using augmented training datasets |
| CN109871798A (en) * | 2019-02-01 | 2019-06-11 | 浙江大学 | A kind of remote sensing image building extracting method based on convolutional neural networks |
-
2019
- 2019-07-18 CN CN201910651552.1A patent/CN110443286B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295521A (en) * | 2016-07-29 | 2017-01-04 | 厦门美图之家科技有限公司 | A kind of gender identification method based on multi output convolutional neural networks, device and the equipment of calculating |
| WO2018065158A1 (en) * | 2016-10-06 | 2018-04-12 | Siemens Aktiengesellschaft | Computer device for training a deep neural network |
| CN106845549A (en) * | 2017-01-22 | 2017-06-13 | 珠海习悦信息技术有限公司 | A kind of method and device of the scene based on multi-task learning and target identification |
| CN106934456A (en) * | 2017-03-16 | 2017-07-07 | 山东理工大学 | A kind of depth convolutional neural networks model building method |
| WO2019001209A1 (en) * | 2017-06-28 | 2019-01-03 | 苏州比格威医疗科技有限公司 | Classification algorithm for retinal oct image based on three-dimensional convolutional neural network |
| US20190130218A1 (en) * | 2017-11-01 | 2019-05-02 | Salesforce.Com, Inc. | Training a neural network using augmented training datasets |
| CN109871798A (en) * | 2019-02-01 | 2019-06-11 | 浙江大学 | A kind of remote sensing image building extracting method based on convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 顾佳玲;彭宏京;: "增长式卷积神经网络及其在人脸检测中的应用", 系统仿真学报, no. 08, pages 2441 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929616A (en) * | 2019-11-14 | 2020-03-27 | 北京达佳互联信息技术有限公司 | Human hand recognition method and device, electronic equipment and storage medium |
| CN110866565B (en) * | 2019-11-26 | 2022-06-24 | 重庆邮电大学 | Multi-branch image classification method based on convolutional neural network |
| CN110866565A (en) * | 2019-11-26 | 2020-03-06 | 重庆邮电大学 | Multi-branch image classification method based on convolutional neural network |
| CN111428671A (en) * | 2020-03-31 | 2020-07-17 | 杭州博雅鸿图视频技术有限公司 | Face structured information identification method, system, device and storage medium |
| CN113537484B (en) * | 2020-04-14 | 2024-01-02 | 中国人民银行数字货币研究所 | Network training, encoding and decoding method, device and medium for digital watermarking |
| CN113537484A (en) * | 2020-04-14 | 2021-10-22 | 中国人民银行数字货币研究所 | Neural network training method, image coding and decoding method and related products |
| CN111695616A (en) * | 2020-05-29 | 2020-09-22 | 平安科技（深圳）有限公司 | Multi-modal data-based lesion classification method and related product |
| TWI785739B (en) * | 2020-08-21 | 2022-12-01 | 大陸商北京市商湯科技開發有限公司 | Method of acquiring target model, electronic device and storage medium |
| WO2022036921A1 (en) * | 2020-08-21 | 2022-02-24 | 北京市商汤科技开发有限公司 | Acquisition of target model |
| JP2022548341A (en) * | 2020-08-21 | 2022-11-18 | ベイジン・センスタイム・テクノロジー・デベロップメント・カンパニー・リミテッド | Get the target model |
| CN112052949B (en) * | 2020-08-21 | 2023-09-08 | 北京市商汤科技开发有限公司 | Image processing method, device, equipment and storage medium based on transfer learning |
| CN112052949A (en) * | 2020-08-21 | 2020-12-08 | 北京市商汤科技开发有限公司 | Target model obtaining method and device, electronic equipment and storage medium |
| CN112712126A (en) * | 2021-01-05 | 2021-04-27 | 南京大学 | Picture identification method |
| CN112712126B (en) * | 2021-01-05 | 2024-03-19 | 南京大学 | Picture identification method |
| CN114092649A (en) * | 2021-11-25 | 2022-02-25 | 马上消费金融股份有限公司 | Picture generation method and device based on neural network |
| CN114092649B (en) * | 2021-11-25 | 2022-10-18 | 马上消费金融股份有限公司 | Picture generation method and device based on neural network |
| CN115511124A (en) * | 2022-09-27 | 2022-12-23 | 上海网商电子商务有限公司 | Customer grading method based on after-sale maintenance records |
| CN115511124B (en) * | 2022-09-27 | 2023-04-18 | 上海网商电子商务有限公司 | Customer grading method based on after-sale maintenance records |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110443286B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443286A (en) | Training method, image-recognizing method and the device of neural network model | |
| Zhong et al. | An end-to-end dense-inceptionnet for image copy-move forgery detection | |
| Wang et al. | RSNet: The search for remote sensing deep neural networks in recognition tasks | |
| Patterson et al. | The sun attribute database: Beyond categories for deeper scene understanding | |
| CN110349136A (en) | A kind of tampered image detection method based on deep learning | |
| CN104376326B (en) | A kind of feature extracting method for image scene identification | |
| CN109670528A (en) | The data extending method for blocking strategy at random based on paired samples towards pedestrian's weight identification mission | |
| CN109063724A (en) | A kind of enhanced production confrontation network and target sample recognition methods | |
| CN109543602A (en) | A kind of recognition methods again of the pedestrian based on multi-view image feature decomposition | |
| CN111339935B (en) | Optical remote sensing picture classification method based on interpretable CNN image classification model | |
| CN109063649A (en) | Pedestrian's recognition methods again of residual error network is aligned based on twin pedestrian | |
| CN110097090A (en) | A kind of image fine granularity recognition methods based on multi-scale feature fusion | |
| CN108447048B (en) | Convolutional neural network image feature processing method based on attention layer | |
| CN107180241A (en) | A kind of animal classification method of the profound neutral net based on Gabor characteristic with fractal structure | |
| CN112381764A (en) | Crop disease and insect pest detection method | |
| CN114386534A (en) | Image augmentation model training method and image classification method based on variational self-encoder and countermeasure generation network | |
| CN110009051A (en) | Feature extraction unit and method, DCNN model, recognition methods and medium | |
| CN108446605B (en) | Double interbehavior recognition methods under complex background | |
| CN113515669A (en) | Data processing method based on artificial intelligence and related equipment | |
| CN113095158A (en) | Handwriting generation method and device based on countermeasure generation network | |
| CN106355210A (en) | Method for expressing infrared image features of insulators on basis of depth neuron response modes | |
| CN113762326A (en) | Data identification method, device and equipment and readable storage medium | |
| CN112801063A (en) | Neural network system and image crowd counting method based on neural network system | |
| CN116416478A (en) | Bioinformatics classification model based on graph structure data characteristics | |
| Zhang et al. | Semisupervised center loss for remote sensing image scene classification |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210114 Address after: 511442 3108, 79 Wanbo 2nd Road, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Applicant after: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Address before: 511449 28th floor, block B1, Wanda Plaza, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20191112 Assignee: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. Assignor: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Contract record no.: X2021440000054 Denomination of invention: Neural network model training method, image recognition method and device License type: Common License Record date: 20210208 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |