WO2020164271A1

WO2020164271A1 - Pooling method and device for convolutional neural network, storage medium and computer device

Info

Publication number: WO2020164271A1
Application number: PCT/CN2019/117863
Authority: WO
Inventors: 房树明; 王健宗
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-02-13
Filing date: 2019-11-13
Publication date: 2020-08-20
Also published as: CN109948651A

Abstract

A pooling method and device for a convolutional neural network, a storage medium and a computer device, the method comprising: obtaining a convolutional neural network training sample, and inputting the training sample into a convolutional neural network model (S100); inputting a sample data matrix outputted by a convolutional layer of the convolutional neural network model into a pooling layer of the convolutional neural network model, and dividing the sample data matrix into a plurality of data sub-matrices in the pooling layer (S200); randomly extracting sample data from each data submatrix (S300); and generating a pooling matrix according to said extracted sample data, and using the pooling matrix as the output of the pooling layer (S400). According to the present method, pooled data samples may be expanded, and the input information of the convolutional neural network is enriched.

Description

Convolutional neural network pooling method, device, storage medium, and computer equipment

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on February 13, 2019, the application number is 201910113187.9, and the application name is "Convolutional Neural Network Pooling Method, Device, Storage Medium, and Computer Equipment". The entire content is incorporated into this application by reference.

Technical field

This application relates to the technical field of convolutional neural network models. Specifically, this application relates to a pooling method, device, storage medium, and computer equipment of a convolutional neural network.

Background technique

Convolutional Neural Network (CNN) is a feedforward neural network. Convolutional neural networks use a large number of artificial neurons, which can respond to surrounding units in a part of the coverage area, and are often used for large-scale image processing. Convolutional neural networks include convolutional layer and pooling layer.

The current general pooling function uses max-pooling or mean-pooling. The disadvantage of max pooling is that every time you pool you will lose information other than the maximum position; the disadvantage of average pooling is that it cannot reflect some important information that is far from the average. Therefore, the current pooling method adopted by the convolutional neural network reduces the input information of the convolutional neural network, resulting in a decrease in the accuracy of the output result of the convolutional neural network model.

Summary of the invention

This application proposes a convolutional neural network pooling method, device, storage medium, and computer equipment to expand the pooled data samples and enrich the input information of the convolutional neural network.

This application provides the following solutions:

A convolutional neural network pooling method, including: obtaining training samples of the convolutional neural network, inputting the training samples into the convolutional neural network model; inputting the sample data matrix output by the convolutional layer of the convolutional neural network model into the convolution The pooling layer of the neural network model divides the sample data matrix into multiple data sub-matrices in the pooling layer; randomly extracts a sample data from each data sub-matrix; generates a pooling matrix according to each sample data extracted, Use this pooling matrix as the output of the pooling layer.

A pooling device for a convolutional neural network, comprising: an acquisition module for acquiring training samples of the convolutional neural network, and inputting the training samples into a convolutional neural network model; a division module for convolutional neural network model The sample data matrix output by the product layer is input to the pooling layer of the convolutional neural network model, where the sample data matrix is divided into multiple data sub-matrices; the extraction module is used to randomly extract one from each data sub-matrix Sample data; a generation module, used to generate a pooling matrix according to each sample data extracted, and use the pooling matrix as the output of the pooling layer.

A computer nonvolatile storage medium, on which a computer program is stored; the computer program is suitable for being loaded by a processor and executing the convolutional neural network pooling method described in any of the above embodiments.

A computer device includes: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be operated by the one or more Executed by a processor, and the one or more application programs are configured to execute the convolutional neural network pooling method according to any one of the foregoing embodiments.

In the convolutional neural network pooling method provided in the above embodiments, each data sub-matrix of the sample data is randomly collected in the pooling layer and then pooled. A sample data matrix of M*M can be M*M *M*M, compared with the traditional maximum pooling or average pooling, expands the pooled data samples and enriches the input information of the convolutional neural network.

The additional aspects and advantages of this application will be partly given in the following description, which will become obvious from the following description, or be understood through the practice of this application.

Description of the drawings

The above and/or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, in which:

FIG. 1 is a schematic diagram of the internal structure in an embodiment of a convolutional neural network model provided by this application;

FIG. 2 is a schematic diagram in an embodiment of the maximum pooling method provided by this application;

FIG. 3 is a schematic diagram in an embodiment of the average pooling method provided by this application;

4 is a method flowchart in an embodiment of a convolutional neural network pooling method provided by this application;

FIG. 5 is a flowchart of a method in an embodiment of step S200 provided in this application;

FIG. 6 is a schematic diagram in an embodiment of the random pooling method provided by this application;

FIG. 7 is a structural block diagram of an embodiment of a convolutional neural network pooling device provided by this application;

FIG. 8 is a schematic structural diagram in an embodiment of a computer device provided by this application.

detailed description

The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

This application provides a pooling method of a convolutional neural network, which is applied to the pooling layer of a convolutional neural network. The following first gives a leading explanation of the background technology of the convolutional neural network pooling method described in this application:

As shown in Figure 1, the convolutional neural network includes two convolutional layers, two pooling layers, and a fully connected hidden layer between the input layer and the output layer. Generally speaking, the input of the pooling layer comes from the previous convolutional layer, which mainly provides strong robustness. While reducing the number of deep learning parameters, it can also prevent overfitting. The reduction in the number of parameters means that the training speed of the convolutional neural network will be faster, the model file after training will be smaller, and the inference speed will be faster when predicting samples. Therefore, the pooling function is of great significance to convolutional neural networks.

Pooling functions in convolutional neural networks generally use max-pooling and mean-pooling methods. For the maximum pooling method, as shown in Figure 2. After a 4 by 4 matrix is pooled by a 2 by 2 maximum pooling function, it becomes a 2 by 2 matrix. The pooling calculation step is: split the 4 by 4 matrix into 4 2 by 2 sub-matrices, and obtain the maximum value of each sub-matrix to form a new matrix, which is the maximum pooling. For the average pooling method, as shown in Figure 3. After a 4 by 4 matrix is pooled by a 2 by 2 average pooling function, it becomes a 2 by 2 matrix. Pooling calculation steps: split the 4 by 4 matrix into 4 2 by 2 sub-matrices, and obtain the average value of each sub-matrix to form a new matrix, which is average pooling. However, with the maximum pooling method, information other than the maximum position will be lost every time the pooling is performed. Using the average pooling method cannot reflect some important information that is far from the average.

This application provides a pooling method for convolutional neural networks to expand pooled data samples and enrich the input information of the convolutional neural network. In an embodiment, as shown in FIG. 4, the pooling method of the convolutional neural network includes the following steps:

S100: Obtain training samples of the convolutional neural network, and input the training samples into the convolutional neural network model.

In this embodiment, before performing data operations on the convolutional neural network structure, the server first obtains training samples of characteristic data. The training sample is the target feature calculated by the server through the convolutional neural network. Further, the training samples are input into the convolutional neural network model. Among them, the convolutional neural network model includes convolutional layer, sampling layer, activation layer, pooling layer and fully connected layer. The convolutional layer is used to extract the spatial features of the input data. The convolutional layer may include multiple convolution kernels to extract multiple spatial features of the input data. The activation layer can adopt a nonlinear activation function. The pooling layer is used to avoid overfitting in the convolution process. The fully connected layer is used for the adjacent connection between neurons and neurons in the network, and can be calculated by the softmax function and output to obtain different probability values.

In an embodiment, the training samples are image sample data. Step S100 includes: acquiring the image sample data as a training sample of the convolutional neural network model.

In this embodiment, the sample data for model training may be image sample data, and the model output is the classification of image sample data. Further, the acquiring the image sample data as the training sample of the convolutional neural network model includes: acquiring the image sample data in the image sample data as the training sample of the convolutional neural network model.

Wherein, the sample data matrix output by the convolution layer of the convolutional neural network model is input into the pooling layer of the convolutional neural network model, and the sample data matrix is divided into a plurality of data sub-matrices in the pooling layer. A sample data is randomly extracted from the data sub-matrix, a pooling matrix is generated according to each sample data extracted, and the pooling matrix is used as the output of the pooling layer, including: the output of the first convolutional layer of the convolutional neural network model After the image sample data matrix is activated, enter the first pooling layer of the convolutional neural network model. In the first pooling layer, the sample data matrix is divided into multiple data sub-matrices, and one is randomly extracted from each data sub-matrix Picture sample data, after the pooling matrix is generated according to the extracted picture sample data for the output of the first pooling layer, the data output by the first pooling layer is input into the second convolutional layer for convolution, and the second The data output by the convolutional layer is randomly activated, and the randomly activated data is input to the second pooling layer for pooling training, and the pooling training result is used as the output of the system pooling layer.

S200: Input the sample data matrix output by the convolution layer of the convolutional neural network model into the pooling layer of the convolutional neural network model, and divide the sample data matrix into multiple data sub-matrices in the pooling layer.

In this embodiment, when the server inputs training samples into the convolutional neural network model, first the training samples are input into the convolutional layer of the convolutional neural network model. The convolution layer performs convolution training on the training samples, extracts different spatial features of the input training samples, and outputs a sample data matrix containing multiple features. The sample data matrix of features with larger dimensions is usually obtained after the convolutional layer. At this time, cut the feature into several regions, and take the maximum or average value to obtain a new feature with a smaller dimension. That is, the pooling operation of the convolutional neural network. When performing the pooling layer operation of the convolutional neural network, the sample data matrix output by the convolutional layer is divided into sub-matrices. Specifically, a convolution kernel of a preset size (less than the size of the sample data matrix) is set. The convolution kernel window is a window with the same length and width. Of course, the convolution kernel of windows with different length and width values is not excluded. The sample data matrix can be divided into multiple sub-matrices through the convolution kernel.

In an embodiment, the plurality of data sub-matrices include data sub-matrices with the same number of rows and columns. As shown in FIG. 5, in step S200, dividing the sample data matrix into multiple data sub-matrices in the pooling layer includes:

S210: Obtain the number of rows and the number of columns of the sample data matrix.

S230: According to the number of rows and columns of the sample data matrix, divide the sample data matrix into a plurality of data sub-matrices with the same number of rows and columns in the pooling layer.

The convolution kernel in the convolutional neural network generally takes a small square matrix. Mainstream deep learning frameworks generally support convolution kernels with the same length and width. For example, a 3 by 3 convolution kernel or a 2 by 2 convolution kernel can be used. In this embodiment, the number of rows M and the number of columns N of the sample data matrix are obtained, and the sample data matrix is divided into a plurality of data sub-matrices with the same number of rows and columns according to the number of rows M and N of columns. Among them, the number of rows M and the number of columns N can be the same.

In other embodiments, the multiple data sub-matrices include a first data sub-matrix with the same number of rows and columns, and a second data sub-matrix with different rows and columns. That is, when the sample data matrix is divided, multiple first data sub-matrices with the same number of rows and columns and multiple second data sub-matrices with different numbers of rows and columns can be simultaneously divided. Specifically, in step S200, the sample data matrix is divided into multiple data sub-matrices in the pooling layer, including: obtaining the number of rows and columns of the sample data matrix; pooling according to the number of rows and columns of the sample data matrix The sample data matrix is divided into a plurality of the first data sub-matrices and a plurality of the second data sub-matrices in the layer.

S300: Randomly extract a sample data from each data sub-matrix.

In this embodiment, when the server performs the pooling operation in the convolutional neural network model, it randomly extracts one sample data from each data sub-matrix, so that a new matrix can be formed according to the data extracted from each data sub-matrix. Here, the data randomly extracted each time can be any data value in the data sub-matrix, and each data value can also be extracted repeatedly.

In an embodiment, the data sub-matrix is a matrix with multiple rows and multiple columns. Step S300 includes: randomly selecting any row of data from the multiple rows of each data sub-matrix; randomly selecting data corresponding to any column from the row of data as the sample data; or, from each data Randomly select any column of data from the multiple columns of the sub-matrix; from the column of data, randomly select data corresponding to any row as the sample data.

In this embodiment, the server first randomly selects any row of data from a data sub-matrix of multiple rows and multiple columns, and then selects any column from the row of data, and the data corresponding to the column is the sample data. Alternatively, the server first randomly selects any column of data from the data sub-matrix of multiple rows and multiple columns, and then selects any row from the column of data, and the data corresponding to the row is the sample data.

In an embodiment, the data sub-matrix is a matrix with multiple rows and multiple columns. Step S300 includes: randomly selecting data corresponding to any row and any column from multiple rows and multiple columns of each data sub-matrix as the sample data. In this embodiment, the server randomly selects any row value and column value, and the data corresponding to the row value and column value is the sample data. If the server randomly selects the row value and the column value (4, 3), the data in the data sub-matrix corresponding to (4, 3) is the sample data.

S400: Generate a pooling matrix according to each extracted sample data, and use the pooling matrix as an output of the pooling layer.

In this embodiment, a new matrix can be generated based on the sample data extracted from each data sub-matrix, that is, a pooling matrix, and the pooling matrix is used as the output of the pooling layer to output to the convolutional neural network model The fully connected hidden layer. In a specific embodiment, as shown in FIG. 6, a 4-by-4 sample data matrix is pooled into a random pool function divided into 2-by-2 data sub-matrices to become multiple 2-by-2 matrices. Specifically, the calculation steps of random pooling are: split the 4 by 4 matrix into 4 2 by 2 sub-matrices, and randomly select a value in each sub-matrix to form a new matrix, which is random Pooling matrix. By using random pooling, a 4 by 4 matrix will produce 4*4*4*4=1024 different pooling results, which is equivalent to expanding the sample by 1024 times, which greatly enriches the input information of the convolutional neural network .

The pooling method of the convolutional neural network provided in the above embodiment inputs training samples into the convolutional neural network model, and after convolution processing is performed on the convolutional layer of the convolutional neural network model, the sample data matrix output by the convolutional layer Enter the pooling layer of the convolutional neural network model. In the pooling layer, the sample data matrix is divided into multiple data sub-matrices, and a data sample is randomly extracted from each data sub-matrix to generate a pooling matrix. Therefore, by randomly collecting and pooling each data sub-matrix of the sample data in the pooling layer, an M*M sample data matrix can get M*M*M*M, which is different from the traditional maximum pooling or Compared with the average pooling method, the pooled data samples are expanded and the input information of the convolutional neural network is enriched.

In an embodiment, the pooling method of the convolutional neural network described above can be used in image classification. Specifically, the image classification method using the pooling method of the convolutional neural network includes: acquiring image data of a target image; inputting the image data into a convolutional neural network model to obtain the result data of the target image to be classified; The convolutional neural network model is used to perform image feature category analysis on the image data, and output the result data to be classified; wherein, the pooling layer in the convolutional neural network model is used to combine the convolutional neural network model The image data output by the convolutional layer in is divided into multiple data matrices, and one image sample data is randomly extracted from each data sub-matrix, and a pooling matrix is generated according to the extracted image sample data, and the pooling matrix is regarded as pooling Output; classify the target image according to the result data to be classified.

Further, the convolutional neural network model further includes a first activation unit and a second activation unit; the convolutional layer includes a first convolutional layer and a second convolutional layer; the pooling layer includes a first pooling Layer and a second pooling layer; wherein the first pooling layer and the second pooling layer are both used to divide the image data output by the convolutional layer in the convolutional neural network model into multiple data Matrix, and randomly extract an image sample data from each data sub-matrix, generate a pooling matrix according to the extracted image sample data, and output the pooling matrix as a pooling; the first activation unit is used to transfer the first After non-random activation of the image data output by a convolutional layer, the result value is input to the first pooling layer; the first pooling layer is used to pool the input image data and output it to the first pooling layer. Two convolutional layers; the second convolutional layer is used to convolve the input image data and output to the second activation unit; the second activation unit is used to randomly activate the input image data and output To the fully connected layer of the convolutional neural network model, the fully connected layer is used to output the result data to be classified.

Specifically, a typical convolutional neural network has a convolutional layer, an activation layer, a pooling layer, and a fully connected layer. A three-layer convolutional neural network can be expressed as: input image -> convolution -> activation -> pool Conversion->Convolution->Activation->Pooling->Convolution->Activation->Pooling->Fully connected layer->Output to be classified. If random pooling is applied to the convolutional neural network, the structure of the network becomes: input image -> convolution -> activation -> random pooling -> convolution -> random activation -> pooling -> convolution- > Random activation -> Pooling -> Fully connected layer -> Output to be classified.

This application also provides a pooling device for the convolutional neural network. In an embodiment, as shown in FIG. 7, the pooling device of the convolutional neural network includes an acquisition module 10, a division module 20, an extraction module 30 and a generation module 40.

The obtaining module 10 is used to obtain training samples of the convolutional neural network, and input the training samples into the convolutional neural network model. In this embodiment, before performing data operations on the convolutional neural network structure, the server first obtains training samples of characteristic data. The training sample is the target feature calculated by the server through the convolutional neural network. Further, the training samples are input into the convolutional neural network model. Among them, the convolutional neural network model includes convolutional layer, sampling layer, activation layer, pooling layer and fully connected layer. The convolutional layer is used to extract the spatial features of the input data. The convolutional layer may include multiple convolution kernels to extract multiple spatial features of the input data. The activation layer can adopt a nonlinear activation function. The pooling layer is used to avoid overfitting in the convolution process. The fully connected layer is used for the adjacent connection between neurons and neurons in the network, and can be calculated by the softmax function and output to obtain different probability values.

The dividing module 20 is configured to input the sample data matrix output by the convolution layer of the convolutional neural network model into the pooling layer of the convolutional neural network model, and divide the sample data matrix into a plurality of data sub-matrices in the pooling layer. In this embodiment, when the server inputs training samples into the convolutional neural network model, first the training samples are input into the convolutional layer of the convolutional neural network model. The convolution layer performs convolution training on the training samples, extracts different spatial features of the input training samples, and outputs a sample data matrix containing multiple features. The sample data matrix of features with larger dimensions is usually obtained after the convolutional layer. At this time, the feature is cut into several regions, and the maximum or average value is selected to obtain a new feature with a smaller dimension. That is, the pooling operation of the convolutional neural network. When performing the pooling layer operation of the convolutional neural network, the sample data matrix output by the convolutional layer is divided into sub-matrices. Specifically, a convolution kernel of a preset size (less than the size of the sample data matrix) is set. The convolution kernel window is a window with the same length and width. Of course, the convolution kernel of windows with different length and width values is not excluded. The sample data matrix can be divided into multiple sub-matrices through the convolution kernel.

The extraction module 30 is used to randomly extract a sample data from each data sub-matrix. In this embodiment, when the server performs the pooling operation in the convolutional neural network model, it randomly extracts one sample data from each data sub-matrix, so that a new matrix can be formed according to the data extracted from each data sub-matrix. Here, the data randomly extracted each time can be any data value in the data sub-matrix, and each data value can also be extracted repeatedly.

The generating module 40 is configured to generate a pooling matrix according to each extracted sample data, and use the pooling matrix as the output of the pooling layer. In this embodiment, a new matrix can be generated based on the sample data extracted from each data sub-matrix, that is, a pooling matrix, and the pooling matrix is used as the output of the pooling layer to output to the convolutional neural network model The fully connected hidden layer.

In other embodiments, each module in the convolutional neural network pooling device provided in this application is also used to execute the operations performed corresponding to each step in the convolutional neural network pooling method described in this application, here No more detailed instructions.

The application also provides a storage medium. The storage medium stores a computer program; when the computer program is executed by a processor, the convolutional neural network pooling method described in any of the above embodiments is implemented. The storage medium may be a memory. For example, internal memory or external memory, or both internal memory and external memory. The internal memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. External storage can include hard disks, floppy disks, ZIP disks, U disks, tapes, etc. The storage medium disclosed in this application includes but is not limited to these types of memories. The memory disclosed in this application is only an example and not a limitation.

This application also provides a computer device. A computer device includes: one or more processors; memory; and one or more application programs. Wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to execute the one described in any of the above embodiments The pooling method of convolutional neural network.

FIG. 8 is a schematic structural diagram of a computer device in an embodiment of this application. The computer device described in this embodiment may be a server, a personal computer, and a network device. As shown in Figure 8, the device includes a processor 803, a memory 805, an input unit 807, a display unit 809 and other devices. Those skilled in the art can understand that the device structure shown in FIG. 8 does not constitute a limitation on all devices, and may include more or less components than those shown in the figure, or combine certain components. The memory 805 may be used to store an application program 801 and various functional modules, and the processor 803 runs the application program 801 stored in the memory 805 to execute various functional applications and data processing of the device. The memory may be internal memory or external memory, or include both internal memory and external memory. The internal memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. External storage can include hard disks, floppy disks, ZIP disks, U disks, tapes, etc. The memory disclosed in this application includes but is not limited to these types of memory. The memory disclosed in this application is only an example and not a limitation.

The input unit 807 is used to receive signal input and keywords input by the user. The input unit 807 may include a touch panel and other input devices. The touch panel can collect the user's touch operations on or near it (for example, the user uses any suitable objects or accessories such as fingers, stylus, etc., to operate on the touch panel or near the touch panel), and according to preset The program drives the corresponding connection device; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (such as playback control buttons, switch buttons, etc.), trackball, mouse, and joystick. The display unit 809 may be used to display information input by the user or information provided to the user and various menus of the computer device. The display unit 809 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 803 is the control center of the computer equipment. It uses various interfaces and lines to connect the various parts of the entire computer. It executes by running or executing the software programs and/or modules stored in the memory 805 and calling the data stored in the memory. Various functions and processing data.

In an embodiment, the device includes one or more processors 803, one or more memories 805, and one or more application programs 801. The one or more application programs 801 are stored in the memory 805 and configured to be executed by the one or more processors 803, and the one or more application programs 801 are configured to execute the above-mentioned embodiments. The pooling method of convolutional neural network.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer readable storage medium.

Those of ordinary skill in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by hardware, or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and the storage medium can include Storage, magnetic disk or optical disc, etc.

It should be understood that the functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. The above are only part of the implementation of this application. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and modifications can be made, and these improvements and modifications are also Should be regarded as the scope of protection of this application.

Claims

A pooling method of convolutional neural network, which is characterized in that it includes:

Obtain training samples of the convolutional neural network, and input the training samples into the convolutional neural network model;

Input the sample data matrix output by the convolution layer of the convolutional neural network model into the pooling layer of the convolutional neural network model, and divide the sample data matrix into multiple data sub-matrices in the pooling layer;

Randomly extract a sample data from each data sub-matrix;

A pooling matrix is generated according to each sample data extracted, and the pooling matrix is used as the output of the pooling layer.
The method according to claim 1, wherein the multiple data sub-matrices comprise data sub-matrices with the same number of rows and columns; and the sample data matrix is divided into multiple data sub-matrices in the pooling layer ,include:

Obtaining the number of rows and columns of the sample data matrix;

According to the number of rows and columns of the sample data matrix, the sample data matrix is divided into a plurality of data sub-matrices with the same number of rows and columns in the pooling layer.
The method according to claim 1, wherein the plurality of data sub-matrices comprise a first data sub-matrix with the same number of rows and columns and a second data sub-matrix with different rows and columns; the In the pooling layer, the sample data matrix is divided into multiple data sub-matrices, including:

Get the number of rows and columns of the sample data matrix;

The sample data matrix is divided into a plurality of the first data sub-matrices and a plurality of the second data sub-matrices in the pooling layer according to the number of rows and the number of columns of the sample data matrix.
The method according to claim 1, wherein the data sub-matrix is a matrix with multiple rows and multiple columns; and said randomly extracting a sample data from each data sub-matrix comprises:

Randomly select any row of data from multiple rows of each data sub-matrix; randomly select data corresponding to any column from the row of data as the sample data; or,

Randomly select any column of data from the multiple columns of each data sub-matrix; from the column of data, randomly select data corresponding to any row as the sample data.
The method according to claim 1, wherein the data sub-matrix is a matrix with multiple rows and multiple columns; and said randomly extracting a sample data from each data sub-matrix comprises:

From the multiple rows and multiple columns of each data sub-matrix, randomly select data corresponding to any row and any column as the sample data.
The method according to claim 1, wherein the training samples are image sample data; the obtaining training samples of the convolutional neural network and inputting the training samples into the convolutional neural network model comprises:

Obtain the image sample data as a training sample of the convolutional neural network model.
The method according to claim 6, wherein said acquiring the image sample data as a training sample of the convolutional neural network model comprises: acquiring image sample data in the image sample data as the volume Training samples of the product neural network model;

The sample data matrix output by the convolution layer of the convolutional neural network model is input into the pooling layer of the convolutional neural network model, and the sample data matrix is divided into a plurality of data sub-matrices in the pooling layer. A sample data is randomly extracted from the matrix, a pooling matrix is generated according to each sample data extracted, and the pooling matrix is used as the output of the pooling layer, including:

After the image sample data matrix output by the first convolution layer of the convolutional neural network model is activated, it is input to the first pooling layer of the convolutional neural network model, and the sample data matrix is divided into multiple in the first pooling layer Data sub-matrix, randomly extract a picture sample data from each data sub-matrix, generate a pooling matrix according to the extracted picture sample data, and output the first pooling layer, and then input the data output by the first pooling layer The second convolutional layer performs convolution, randomly activates the data output by the second convolutional layer, and inputs the randomly activated data into the second pooling layer for pooling training, and the pooling training result is used as the system The output of the pooling layer.
A pooling device for convolutional neural network, characterized in that it comprises:

The acquisition module is used to acquire training samples of the convolutional neural network, and input the training samples into the convolutional neural network model;

The division module is used to input the sample data matrix output by the convolution layer of the convolutional neural network model into the pooling layer of the convolutional neural network model, and divide the sample data matrix into multiple data sub-matrices in the pooling layer;

The extraction module is used to randomly extract a sample data from each data sub-matrix;

The generating module is used to generate a pooling matrix according to each extracted sample data, and use the pooling matrix as the output of the pooling layer.
8. The device according to claim 8, wherein the multiple data sub-matrices comprise data sub-matrices with the same number of rows and columns; and the division module executes the division of the sample data matrix in the pooling layer into When there are multiple data sub-matrices, it is specifically used for:

Obtaining the number of rows and columns of the sample data matrix;

According to the number of rows and columns of the sample data matrix, the sample data matrix is divided into a plurality of data sub-matrices with the same number of rows and columns in the pooling layer.
8. The device according to claim 8, wherein the multiple data sub-matrices comprise a first data sub-matrix with the same number of rows and columns and a second data sub-matrix with different rows and columns; the When the division module executes the division of the sample data matrix into multiple data sub-matrices in the pooling layer, it is specifically used for:

Get the number of rows and columns of the sample data matrix;

The sample data matrix is divided into a plurality of the first data sub-matrices and a plurality of the second data sub-matrices in the pooling layer according to the number of rows and the number of columns of the sample data matrix.
The device according to claim 8, wherein the data sub-matrix is a matrix with multiple rows and multiple columns; when the extraction module executes the random extraction of a sample data from each data sub-matrix, the specific Used for:

Randomly select any row of data from multiple rows of each data sub-matrix; randomly select data corresponding to any column from the row of data as the sample data; or,

Randomly select any column of data from the multiple columns of each data sub-matrix; from the column of data, randomly select data corresponding to any row as the sample data.
The device according to claim 8, wherein the data sub-matrix is a matrix with multiple rows and multiple columns; when the extraction module executes the random extraction of a sample data from each data sub-matrix, the specific Used for:

From the multiple rows and multiple columns of each data sub-matrix, randomly select data corresponding to any row and any column as the sample data.
The device according to claim 8, wherein the training sample is image sample data; the acquisition module is specifically configured to:

Obtain the image sample data as a training sample of the convolutional neural network model.
The device according to claim 13, wherein the acquiring module is specifically configured to: acquire the image sample data when executing the acquiring the image sample data as the training sample of the convolutional neural network model The picture sample data in as the training sample of the convolutional neural network model;

The dividing module performs the input of the sample data matrix output by the convolution layer of the convolutional neural network model into the pooling layer of the convolutional neural network model, and divides the sample data matrix into a plurality of data sub-matrices in the pooling layer When, it is specifically used to: activate the image sample data matrix output by the first convolutional layer of the convolutional neural network model, and then input it into the first pooling layer of the convolutional neural network model, and the samples in the first pooling layer The data matrix is divided into multiple data sub-matrices;

When the extraction module executes the random extraction of sample data from each data sub-matrix, it is specifically configured to: randomly extract a picture sample data from each data sub-matrix;

When the generating module executes the generation of a pooling matrix according to each extracted sample data, and the pooling matrix is used as the output of the pooling layer, it is specifically used for: generating a pooling matrix according to the extracted picture sample data to perform the first pooling After the layer is output, the data output by the first pooling layer is input into the second convolutional layer for convolution, the data output by the second convolutional layer is randomly activated, and the randomly activated data is input into the second convolutional layer. The second pooling layer performs pooling training, and the result of the pooling training is used as the output of the system pooling layer.
A computer non-volatile storage medium, characterized in that a computer program is stored thereon; the computer program is adapted to be loaded by a processor and execute the convolutional neural network according to any one of claims 1 to 7 The pooling method.
A computer device, characterized in that it includes:

One or more processors;

Memory

One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to execute The following steps:

Obtain training samples of the convolutional neural network, and input the training samples into the convolutional neural network model;

Input the sample data matrix output by the convolution layer of the convolutional neural network model into the pooling layer of the convolutional neural network model, and divide the sample data matrix into multiple data sub-matrices in the pooling layer;

Randomly extract a sample data from each data sub-matrix;

A pooling matrix is generated according to each sample data extracted, and the pooling matrix is used as the output of the pooling layer.
The computer device according to claim 16, wherein the multiple data sub-matrices comprise data sub-matrices with the same number of rows and columns; and the sample data matrix is divided into multiple data sub-matrices in the pooling layer. When matrixing, the one or more applications are configured to perform the following steps:

Obtaining the number of rows and columns of the sample data matrix;

According to the number of rows and columns of the sample data matrix, the sample data matrix is divided into a plurality of data sub-matrices with the same number of rows and columns in the pooling layer.
The computer device according to claim 16, wherein the plurality of data sub-matrices comprise a first data sub-matrix with the same number of rows and columns, and a second data sub-matrix with different rows and columns; When the sample data matrix is divided into multiple data sub-matrices in the pooling layer, the one or more application programs are configured to perform the following steps:

Get the number of rows and columns of the sample data matrix;

The sample data matrix is divided into a plurality of the first data sub-matrices and a plurality of the second data sub-matrices in the pooling layer according to the number of rows and the number of columns of the sample data matrix.
The computer device according to claim 16, wherein the data sub-matrix is a matrix with multiple rows and multiple columns; when one sample data is randomly extracted from each data sub-matrix, the one or more The application is configured to perform the following steps:

Randomly select any row of data from multiple rows of each data sub-matrix; randomly select data corresponding to any column from the row of data as the sample data; or,

Randomly select any column of data from the multiple columns of each data sub-matrix; from the column of data, randomly select data corresponding to any row as the sample data.
The computer device according to claim 16, wherein the training samples are image sample data; when the training samples of the convolutional neural network are obtained and the training samples are input into the convolutional neural network model, the one or more One application is configured to perform the following steps:

Acquiring picture sample data in the image sample data as a training sample of the convolutional neural network model;

The sample data matrix output by the convolution layer of the convolutional neural network model is input into the pooling layer of the convolutional neural network model, and the sample data matrix is divided into a plurality of data sub-matrices in the pooling layer. One sample data is randomly extracted from the matrix, a pooling matrix is generated according to each extracted sample data, and when the pooling matrix is used as the output of the pooling layer, the one or more applications are configured to perform the following steps:

After the image sample data matrix output by the first convolution layer of the convolutional neural network model is activated, it is input to the first pooling layer of the convolutional neural network model, and the sample data matrix is divided into multiple in the first pooling layer Data sub-matrix, randomly extract a picture sample data from each data sub-matrix, generate a pooling matrix according to the extracted picture sample data and output the first pooling layer, and then input the data output by the first pooling layer The second convolution layer performs convolution, randomly activates the data output by the second convolution layer, and inputs the randomly activated data into the second pooling layer for pooling training, and the pooling training result is used as the system The output of the pooling layer.