WO2020006881A1

WO2020006881A1 - Butterfly identification network construction method and apparatus, and computer device and storage medium

Info

Publication number: WO2020006881A1
Application number: PCT/CN2018/106395
Authority: WO
Inventors: 刘奡智; 夏子敏; 王健宗; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-07-06
Filing date: 2018-09-19
Publication date: 2020-01-09
Also published as: CN109063742A; CN109063742B

Abstract

Disclosed are a butterfly identification network construction method and apparatus, and a computer device and a storage medium. The method comprises: resampling an original butterfly image to obtain a target butterfly image for training; if a loss function value, calculated in a loss function layer, of an output vector that is obtained by means of first convolutional calculation of a convolution layer of a capsule network and second convolutional calculation of a capsule layer is not more than a preset threshold, using the capsule network as a training network for butterfly identification, otherwise, updating each capsule neuron in the capsule network by means of back propagation to obtain an updated capsule network; and performing the first convolutional calculation, the second convolutional calculation and the loss function calculation on the target butterfly image for training again in the updated capsule network until the loss function value is not more than the loss threshold, so that the ambiguity expression of butterfly images is realized, that is, the same butterfly species from different angles of view can be distinguished, and the accuracy of butterfly identification by the capsule network is improved.

Description

Method and device for constructing butterfly recognition network, computer equipment and storage medium

This application is based on a Chinese invention patent application filed on July 6, 2018 with application number 201810735895.1, entitled "Butterfly recognition network construction method, device, computer equipment, and storage medium", and claims its priority.

Technical field

The present application relates to the field of computer technology, and in particular, to a method, a device, a computer device, and a storage medium for constructing a butterfly recognition network.

Background technique

In recent years, with the development of artificial intelligence, deep learning has achieved great success in many areas such as speech recognition, natural language processing, and image and video analysis. At present, deep learning is an end-to-end machine learning system. Convolutional neural network (CNN) models in deep learning methods perform well in large-scale image recognition tasks. The biggest difference from traditional pattern recognition methods is that It can automatically extract features from the image layer by layer, and can contain thousands of parameters. These good feature expressions play a vital role in deep learning.

Improving the butterfly recognition rate has great practical significance for practical biological research, for example, butterfly recognition can be used as a study of biological diversity and species analysis. Due to the limited number of butterfly images in the existing image databases, there are few butterfly species, and the size of butterfly images is too small, which is not conducive to traditional convolutional neural networks to identify butterflies. Because the traditional convolutional neural network requires a large number of training images, and lacks the observation position and perspective information, that is, it cannot handle the polysemous expression of the image well. Because the traditional convolutional neural network cannot distinguish the same butterfly species based on different perspectives of the same butterfly, the accuracy of butterfly recognition is low.

Summary of the invention

The embodiments of the present application provide a method, a device, a computer device, and a storage medium for constructing a butterfly recognition network, so as to solve the problem that the traditional butterfly convolutional neural network recognizes the same type of butterflies from different perspectives as different kinds of butterflies, resulting in the accuracy of butterfly recognition Low problem.

A method for constructing a butterfly recognition network includes:

Obtain the original butterfly image corresponding to each butterfly species from a preset butterfly database;

Performing resampling processing on the original butterfly image to obtain a target butterfly image;

For each of the butterfly species, the target butterfly image used for training in the butterfly species is input into a capsule network, and passes through a first convolution calculation of a convolution layer of the capsule network and the capsule network. Calculation of the second convolution of the capsule layer to obtain the output vector of the butterfly species;

Performing a loss function calculation on the output vector of each of the butterfly species in a loss function layer in the capsule network to obtain a loss function value of each of the output vectors;

When the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, using the capsule network as a training network for identifying butterflies;

When the value of the loss function is greater than the preset loss threshold, each capsule neuron in the capsule network is updated by back propagation to obtain the updated capsule network, and each type of the butterfly species is updated. The target butterfly image used in training is re-input to the updated capsule network, and the first convolution calculation, the second convolution calculation, and the loss function calculation are performed until the loss function The value is less than or equal to the preset loss threshold, wherein the capsule neuron represents the attribute of the butterfly species.

A butterfly recognition network construction device includes:

An acquisition module for acquiring an original butterfly image corresponding to each butterfly species from a preset butterfly database;

A resampling module for resampling the original butterfly image to obtain a target butterfly image;

A convolution module, for each of the butterfly species, inputting the target butterfly image used for training in the butterfly species into a capsule network, and passing a first convolution calculation of a convolution layer of the capsule network And a second convolution calculation of a capsule layer of the capsule network to obtain an output vector of the butterfly species;

A loss calculation module, configured to perform a loss function calculation on the output vector of each of the butterfly species in a loss function layer in the capsule network to obtain a loss function value of each of the output vectors;

A training module, configured to use the capsule network as a training network for identifying a butterfly when the loss function value of each of the output vectors is less than or equal to a preset loss threshold;

An update module is configured to update each capsule neuron in the capsule network by back propagation when the loss function value is greater than the preset loss threshold, obtain the updated capsule network, and update each capsule network. The target butterfly image used for training among the butterfly species is re-input into the updated capsule network, and performs the first convolution calculation, the second convolution calculation, and the loss function calculation, Until the value of the loss function is less than or equal to the preset loss threshold, wherein the capsule neuron represents the attribute of the butterfly species.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and the processor implements the computer-readable instructions to implement the above-mentioned butterfly recognition network construction Method steps.

One or more non-volatile readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to execute the butterfly recognition network described above Steps in building the method.

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below, and other features and advantages of the present application will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings used in the description of the embodiments of the application will be briefly introduced below. Obviously, the drawings in the following description are just some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

1 is a schematic diagram of an application environment of a method for constructing a butterfly recognition network according to an embodiment of the present application;

2 is an implementation flowchart of a method for constructing a butterfly recognition network according to an embodiment of the present application;

3 is an implementation flowchart of step S2 in a method for constructing a butterfly recognition network according to an embodiment of the present application;

4 is an implementation diagram of step S3 in a method for constructing a butterfly recognition network according to an embodiment of the present application;

5 is an implementation diagram of a training network for testing and identifying butterflies in a method for constructing a butterfly recognition network according to an embodiment of the present application;

6 is a schematic diagram of an apparatus for constructing a butterfly recognition network according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a computer device in an embodiment of the present application.

detailed description

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

The method for constructing a butterfly recognition network provided in this application can be applied in the application environment shown in FIG. 1, in which a server and a client are connected through a network, and the server performs a first convolution of a target butterfly image in a capsule network The training, the second convolution calculation, and the loss function calculation process are used to obtain the training network for identifying the butterfly. The user modifies the training parameters of the capsule network through the client. The client can specifically, but not limited to, various personal computers, laptops, smartphones, tablets For computers and portable wearable devices, the server can be implemented by an independent server or a server cluster composed of multiple servers.

In an embodiment, as shown in FIG. 2, a method for constructing a butterfly recognition network is provided. The method is applied to the server in FIG. 1 as an example, and includes the following steps:

S1: Obtain the original butterfly image corresponding to each butterfly type from a preset butterfly database.

Specifically, the preset butterfly database stores all original butterfly images in the existing butterfly database. The preset butterfly database includes, but is not limited to, the Leeds butterfly database, the Ecuador butterfly database, and Costarica (Costa Rica). Butterfly database. In addition, the preset butterfly database can also use the Fine-Grained (fine-grained) butterfly database, of which the Leeds butterfly database includes 14,270 original butterfly images corresponding to 636 butterfly species, and the Ecuador butterfly database includes 10 Butterfly types: 832 original butterfly images corresponding to butterfly types, Costarica (Costa Rica) includes 2120 original butterfly images corresponding to 675 butterfly types, and Fine-Grained (fine-grained) butterfly database includes 3,224 original butterfly images corresponding to 331 butterfly types The butterfly database is not limited here.

S2: Resampling the original butterfly image to obtain the target butterfly image.

Specifically, in the image field, resampling is resampling a digital image composed of discrete data formed after sampling according to a preset pixel position or pixel interval to form a new image after geometric transformation.

Resampling each original butterfly image and dividing the obtained target butterfly image into two parts, one part of the target butterfly image is used as training sample data for training the capsule network, and the other part of the butterfly image is used for training to identify the butterfly Test sample data for the network.

Further, after resampling the original butterfly image, a target butterfly image of the same size is obtained, and the target butterfly image carries the corresponding butterfly type mark, which is beneficial for subsequent training or testing the training network that recognizes the butterfly. The output result and the original input are obtained. The target butterfly image is compared with the corresponding butterfly species mark to determine whether the output result is correct.

S3: For each butterfly type, the target butterfly image used for training in this butterfly type is input into the capsule network, and passes through the first convolution calculation of the convolution layer of the capsule network and the second volume of the capsule layer of the capsule network. Product calculation to get the output vector of this butterfly species.

Specifically, the capsule network consists of a parse tree. The neurons in each layer of the neuron layer in the capsule network will be divided into multiple neuron groups. Each neuron group is called a capsule. Each node in the parse tree will correspond to an activated capsule ( active capsule). An activated capsule is composed of multiple activated capsule neurons. Each capsule neuron contains a convolution kernel. The convolution kernel is a type of (filter) matrix or feature detector. The weight in the convolution kernel is the characteristic expression of the attribute, that is, the capsule neuron represents the attribute of a certain butterfly species, among which the attributes can be different perspectives corresponding to each butterfly species such as different angles, positions and directions. In summary, the training network for butterfly recognition improves the accuracy of butterfly recognition by continuously modifying the weights in the convolution kernel in the capsule neurons and other training parameters, among which other training parameters include coupling coefficients.

Further, for each butterfly species, a target butterfly image of the butterfly species used for training is input to a convolution layer in a capsule network to perform a first convolution calculation. The first convolution calculation is to calculate the target butterfly image and the convolution kernel in the convolution layer. The convolution kernel calculation refers to the element value at each position in the convolution kernel and the corresponding point on the target butterfly image. Multiply and accumulate the element values of, that is, the element values of the points between the two matrices are multiplied and superimposed separately to obtain the value of each element in the output matrix, and the result of the first convolution calculation is obtained in the capsule of the capsule network A second convolution calculation is performed in the layer, where the second convolution calculation is a convolution calculation of the result obtained by the first convolution calculation with the activated capsule neuron to obtain an output vector of the butterfly species.

It should be noted that the vector length in the output vector indicates the probability that the target butterfly image is recognized as the corresponding butterfly type in the capsule network, and the vector direction of the output vector indicates the attributes of the butterfly type, such as different perspectives of the butterfly.

S4: In the loss function layer in the capsule network, perform a loss function calculation on the output vector of each butterfly species to obtain the loss function value of each output vector.

Specifically, the loss function describes the loss of the training model under different parameter values, and is used to estimate the degree of inconsistency between the predicted value and the true value of the training model. The loss function calculation is performed on the output vector of each butterfly species, and the loss function value of the output vector is a non-negative function value. According to the size of the loss function value, adjusting the training parameters of the training network for identifying the butterfly can reduce the value of the loss function. The smaller the value of the loss function, the better the robustness of the training network for identifying the butterfly. The training parameters include convolution. Weights in the kernel.

S5: When the loss function value of each output vector is less than or equal to a preset loss threshold, the capsule network is used as a training network for identifying butterflies.

Specifically, when the loss function value of each output vector obtained in step S4 is less than or equal to a preset loss threshold, that is, the robustness of the training network for butterfly recognition at this time has reached the expected effect of butterfly recognition, The current capsule network is used as the training network for the final recognition of butterflies. The preset loss threshold may be 0.3 or a decimal from 0 to 1.

S6: When the value of the loss function is greater than a preset loss threshold, each capsule neuron in the capsule network is updated by back propagation to obtain the updated capsule network, and the butterfly image used as a training target in each butterfly species Re-enter the updated capsule network and perform the first convolution calculation, the second convolution calculation, and the loss function calculation until the loss function value is less than or equal to the preset loss threshold, where the capsule neuron represents the butterfly species. Attributes.

Specifically, when the value of the loss function obtained in step S4 is greater than the loss threshold, each capsule neuron in the capsule network is updated by back propagation, where the back propagation is to obtain the loss function for each neuron layer by layer. The partial derivative of the weight value, so as to obtain the ladder function of the loss function to the output vector. The ladder function is used as a basis for modifying the weight value in each capsule neuron, so that the developer can adjust each capsule neuron in the capsule network according to the ladder The capsule network is updated, and the target butterfly image used for training in each butterfly species is re-entered into the updated capsule network, and step S3 is continued until the loss function value is less than or equal to the loss threshold. Among them, the attributes of capsule neurons representing butterfly species include different perspectives corresponding to each butterfly species.

In this embodiment, the original butterfly image corresponding to each butterfly type is obtained from a preset butterfly database, and the original butterfly image is resampled to obtain a target butterfly image; the target butterfly image used for training in this butterfly type is input Into the capsule network, and after the first convolution calculation of the convolution layer of the capsule network and the second convolution calculation of the capsule layer of the capsule network, the output vector of the butterfly species is calculated by the loss function to obtain the loss function value; when the loss When the function value is greater than a preset value, each capsule neuron in the capsule network is updated by back propagation, thereby obtaining an updated capsule network. The target butterfly image used as training is input to the updated capsule network for the first time. Convolution calculation, second convolution calculation, and loss function calculation, until the loss function value is less than or equal to the loss threshold, realizes the use of a small number of target butterfly images to process the ambiguity expression of the butterfly image, that is, the target butterfly image and the Each capsule neuron in the capsule network representing the attributes of the butterfly species is obtained by training processing When the missing value meets the loss threshold, that is, regardless of whether the actual attributes of the input target butterfly image are from different perspectives, the butterfly species corresponding to the classification result of the target butterfly image are finally obtained, thereby realizing the same butterfly species that can distinguish between different perspectives, thereby improving The accuracy of the capsule network to identify butterflies.

In an embodiment, as shown in FIG. 3, in step S2, the original butterfly image is resampled to obtain the target butterfly image, which specifically includes the following steps:

S21: Determine the zoom ratio of the original butterfly image according to the preset target size.

Specifically, the scaling ratio of the original butterfly image is determined according to a preset target size, so that the obtained target butterfly image has the same size, which is beneficial for the capsule network to identify butterfly species, and reduces interference factors caused by inconsistent size. Prevent overfitting.

For example, all original butterfly images are resampled to obtain a size of 32 × 32 × 3, where 32 pixels are in the row direction, 32 pixels are in the column direction, and 3 refers to three channels of RGB. When an original butterfly image is 64 × 64 × 3, the resulting zoom ratio is

That is, the original butterfly image is reduced by two times.

Specifically, a channel is used to represent a certain composition of an image. For example, an image taken by a standard digital camera will have three channels-red, green, and blue. Think of them as a two-dimensional matrix stacked on top of each other. Each channel represents a color, and the pixel value of each channel ranges from 0 to In the range of 255.

S22: According to the scaling ratio, the original pixels of the original butterfly image are divided to obtain a set of original pixels corresponding to each target pixel of the target butterfly image in the original butterfly image, and a set of each original pixel is established. Correspondence with each pixel of the target butterfly image.

Specifically, referring to the example in step S21, starting from the target image, the original pixel points of the original butterfly image are divided according to the zoom ratio 2 to obtain each target pixel point of the target butterfly image corresponding to the original butterfly image. A set of original pixels, and establish a correspondence between each set of original pixels and each pixel of the target butterfly image, for example, the first pixel in the upper left corner of the target image corresponds to the original butterfly image The upper left corner of is 2 × 2 = 4 pixels, that is, these 4 pixels are the set of original pixels.

S23: Calculate the average RGB value of each original pixel in the set of original pixels, and use the average RGB value as the RGB value of the target pixel corresponding to the set of original pixels according to the corresponding relationship.

Specifically, according to the set of original pixel points obtained in step S22, the RGB values of each original pixel point are accumulated and averaged to obtain an average RGB value, and according to the correspondence between the original pixel point and each pixel point of the target butterfly image , Taking the average RGB value as the RGB value of the target pixel corresponding to the set of original pixels, where the average RGB value is a positive integer. For example, referring to the example of step S22, if the RGB values of 4 pixels are {215,0,64,0}, the average RGB value is

In this embodiment, the scaling ratio of the original butterfly image is determined according to a preset target size, a set of original pixels corresponding to each target pixel point of the target butterfly image in the original butterfly image is obtained, and the set of original pixels is calculated The average RGB value of each original pixel in the image, and use the average RGB value as the RGB value of the target pixel corresponding to the set of original pixels, to achieve the goal of scaling all original butterfly images of different sizes to a uniform standard size Butterfly images are beneficial to provide good training sample data for the capsule network in the future, and avoid overfitting problems caused by the different sizes of the original butterfly images.

In an embodiment, as shown in FIG. 4, in step S3, for each of the butterfly species, the target butterfly image used for training in the butterfly species is input into a capsule network and passes through the capsule. The first convolution calculation of the convolution layer of the network and the second convolution calculation of the capsule layer of the capsule network to obtain the output vector of the butterfly species include the following steps:

S31: Perform the first convolution calculation on the convolution layer of the capsule network by using the target butterfly image input into the butterfly species for training to obtain a feature vector.

Specifically, a target butterfly image used for training in a butterfly species is input to a convolution layer of a capsule network, and a first convolution calculation is performed on a convolution kernel of the target butterfly image and each capsule neuron in the convolution layer, The first convolution calculation is to multiply the element value at each position in the convolution kernel with the element value of the corresponding point on the target butterfly image, and the resulting feature vector is called a Convolved Feature or a feature map ( Feature map). For example, the depth is 256 and the convolution window size is 9 * 9, that is, a convolution kernel of 256 9 * 9 matrices is constructed.

It should be noted that when an out-of-bounds problem occurs during the first convolution calculation, zero supplementation is used, which is also called zero-padding. Fill the edges of the target butterfly image with zero values to filter the edges of the input target butterfly image to control the size of the feature map.

S32: Substituting the feature vector into a modified linear activation function to obtain a local feature vector.

Specifically, the modified linear activation function, namely the ReLU (Rectified Linear Unit) activation function, is a neuron activation function and a piecewise linear function. It can set all the pixel values less than 0 in the feature map to zero. While leaving other pixels with positive values, this operation is called unilateral suppression, so that the relevant features can be better mined in the sparse capsule network to avoid overfitting.

Further, the feature vector is substituted into the modified linear activation function, that is, the pixel gray value of the feature map is converted into the activation value of the local feature.

S33: By using an iterative routing processing method, a second convolution calculation is performed on the local feature vector and each capsule neuron in the capsule layer of the capsule network to obtain an output vector of the butterfly type.

Specifically, the capsule layer of the capsule network in this embodiment is a 32-channel capsule, and each capsule includes 8 capsule neurons, and each capsule neuron includes 9 × 9 Convolution kernel with stride of 2. The second convolution calculation refers to the convolution calculation of each capsule neuron and all local feature vectors of the convolution layer, and by using an iterative routing process, it is finally output by 32 × 32 × n capsules, and each capsule is 8-dimensional output vector, that is, each capsule actually outputs a set of output vectors.

Further, an iterative routing process (iterative dynamic routing) can obtain an output vector through formulas (1) to (4). The output vector represents the probability of each butterfly species from different perspectives, including:

Among them, b _ij refers to the softmax activation function between the i-th capsule neuron and the j-th capsule neuron. A softmax activation function is a method that maps each value of a multidimensional vector into (0, 1) The function of the interval is used for classification here, c _ij is the coupling coefficient,

Is the local feature vector, W _ij is the weight matrix, and S _j is all the local feature vectors

Weighted sum, V _j is the output vector of the j-th capsule neuron.

c _ij is the coupling coefficient determined by the iterative routing process. The sum of the coupling coefficient between Capsule and the capsules in the previous layer is 1. This coefficient, along with other weights, is determined during training and depends on the position and type of the two capsules. When the iterative routing process is initialized, each capsule neuron in the capsule layer has the same coupling coefficient to each capsule neuron in the convolution layer; each capsule neuron in the capsule layer is calculated for each possible parent node The local feature vector is used as the input of the parent node. If the inner product of the local feature vector and the output vector of a parent node is large, the coupling coefficient of the parent node will be increased through a top-down feedback, and at the same time it will be reduced. The coupling coefficient of the other parent nodes is small, and the result of dynamic selection is achieved. In addition, the sum of all coupling coefficients of a capsule neuron is 1.

It should be noted that low-level capsule neurons tend to be aligned with high-level capsule neurons, that is, a high coupling coefficient indicates a large tendency to predict the local characteristics of the butterfly species, and a low coupling coefficient indicates a local tendency to predict the butterfly characteristics. small. Assume that the coupling coefficient c _ij of capsule neuron i to capsule neuron j is 1. Since all the coupling coefficients of capsule neuron i are 1, the coupling coefficient of capsule neuron i to other capsule neurons is zero. That is, all local feature vectors of the capsule neuron i are only passed to the capsule neuron j.

Further, because the vector length represents the probability of the occurrence of each butterfly species, that is, V _j is a probability value, a non-linear "squeeze" function is used to ensure that the short output vector is "compressed" to a length close to 0, The long vector is "compressed" to a value close to one in length.

In this embodiment, the target butterfly image inputted into the butterfly species is used for training. The first convolution calculation is performed in the convolution layer of the capsule network, and the obtained feature vector is substituted into the modified linear activation function to obtain local features. Vector; by using an iterative routing process, a second convolution calculation is performed on the local feature vector with each capsule neuron in the capsule layer of the capsule network to obtain an output vector. The prediction tendency is more obvious, and the generalization of the target butterfly image is achieved, for example, the generalization includes perspective information such as likelihood, direction, and size, thereby improving the discrimination ability of different butterfly perspectives of the same butterfly species.

Further, in an embodiment, in the loss function layer in the capsule network mentioned in step S4, a loss function calculation is performed on an output vector of each butterfly species, and a specific implementation process of obtaining a loss function value of the output vector is obtained. Details are as follows:

Put each output vector in the loss function layer in the capsule network, and calculate the loss function value of the output vector according to formula (5):

_{_{L c = T c max (0}} , m + - || V c ||) 2 + λ (1-T c) max (0, || V c || -m -) 2 (5)

Among them, c is the butterfly type, L _c is the loss function value, T _c is the indicator function of the butterfly type, and max (0, m ⁺ -|| V _c ||) ² is taken as 0 and m ⁺ -|| V _c | | two maximum values in _{square, max (0, || V c} || -m -) 2 is set to 0 and || Vc || -m ^- the square of the maximum of the two values, m ⁺ Is the upper boundary of the preset vector length, || V _c || is the vector length of the output vector V _c , λ is the preset parameter value, and m ^- is the lower boundary of the preset vector length.

Specifically, the indication function is also called a feature function. In this embodiment, the indication function is to customize each butterfly type into a set, and the set includes a subset of various attributes of the butterfly type. When the target butterfly corresponding to the butterfly type The images belong to a certain subset in the collection, and the subset can be a certain attribute of the butterfly species.

Further, if the instruction function judges that the output vector is the same as the actual target butterfly image, the output is 1, otherwise it is 0. For example, the total length of a column vector is used to identify the total number of butterfly species, and the element of the column vector is 1. The position represents the classification result of the butterfly species corresponding to the position, and 0 in the column vector indicates that it is not the butterfly species. When the output vector belongs to a certain subset, and the subset belongs to a set of certain butterfly species, the number of column items corresponding to the species is 1, however, in actual classification, the value in the column vector is the corresponding butterfly species. Probability. For example, the length of the output vector || V _c || of the capsule corresponds to the probability that it belongs to the c-th butterfly species.

In the embodiment of the present application, the loss function value is calculated by calculating the loss function layer of each output vector in the capsule network, and the prediction effect of the capsule network on the butterfly species is measured according to the size of the loss function value, which is beneficial to further adjustment. Parameters in the capsule network.

In an embodiment, as shown in FIG. 5, after step S6, the method for constructing a butterfly recognition network further includes the following steps:

S7: The target butterfly image used as a test is input into a training network for recognition of a butterfly, and the loss function value of the test output vector is obtained through the first convolution calculation, the second convolution calculation, and the loss function calculation.

Specifically, the target butterfly image used as the test, that is, the test sample data is input into the training network for identifying the butterfly obtained in steps S1 to S5, and according to step S3, the first convolution calculation, the second Convolution calculation and loss function calculation, output the loss function value of the test output vector.

S8: Take a test output vector corresponding to a loss function value that is greater than or equal to a preset upper boundary of the vector length, and reconstruct the test output vector through the decoder network to obtain an output image, and use the output image as the test target. The butterfly images are compared to get the accuracy of the training network for butterfly recognition.

Specifically, a test output vector corresponding to a loss function value that is greater than or equal to a preset upper boundary of the vector length is obtained. For example, if a type c butterfly type exists and the preset vector length is 0.9, the type c butterfly type When an output vector with a vector length of at least 0.9 is output, it can be indicated that the target butterfly image corresponding to the output vector belongs to the type c butterfly category, where 0.9 represents the upper boundary of the vector length.

Further, the test output vector is reconstructed through a decoder network. The decoder network is composed of three fully connected layers, and an output image is obtained through the decoder network reconstruction. Reconstruction refers to reconstructing a test output vector into an actual image corresponding to the test output vector, thereby constructing a complete output image. According to the reconstruction method, all test output vectors are obtained through the decoder network to obtain the output image, and the image comparison method is used to filter out the same output image as the target butterfly image used for testing. The image comparison method includes but is not limited to perception Hash algorithm, gray-scale histogram similarity comparison method, or PSNR (Peak Signal-to-Noise Ratio) method, and calculate the total number of output images that are the same as the target butterfly image used for testing and the total of the target butterfly image used for testing The proportion of the amount is the accuracy rate of the training network for butterfly recognition. If the accuracy rate obtained is less than the preset accuracy rate, it indicates that the recognition effect of the training network for butterfly recognition is not good, and the recognition butterfly needs to be further improved. Otherwise, there is no need to adjust the training network for butterfly recognition. The preset accuracy rate can be set to 95% or a percentage value greater than 95%.

In this embodiment, a target butterfly image used as a test is input to a training network that recognizes butterflies, and a test output vector corresponding to a loss function value that is greater than or equal to the upper boundary of the vector length is obtained. The test output vector is reconstructed to obtain the output image, and then the accuracy rate of the training network for butterfly recognition is obtained. The accuracy rate can intuitively determine the recognition effect of the butterfly recognition training network on the butterfly species, and determine whether to recognize the butterfly based on the recognition effect. Training network to make further improvements.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

In one embodiment, a device for constructing a butterfly recognition network is provided. The device for constructing a butterfly recognition network corresponds to the method for constructing a butterfly recognition network in the above-mentioned embodiment. As shown in FIG. 6, the apparatus for constructing a butterfly recognition network includes an acquisition module 61, a resampling module 62, a convolution module 63, a calculation module 64, a training module 65, and an update module 66. The detailed description of each function module is as follows:

An obtaining module 61, configured to obtain an original butterfly image corresponding to each butterfly type from a preset butterfly database;

A resampling module 62, configured to resample the original butterfly image to obtain a target butterfly image;

A convolution module 63, for each butterfly species, inputs a butterfly image used for training in the butterfly species into a capsule network, and passes the first convolution calculation of the convolution layer of the capsule network and the capsules of the capsule network The second convolution calculation of the layer to obtain the output vector of the butterfly species;

A loss calculation module 64 is configured to perform a loss function calculation on an output vector of each butterfly species in a loss function layer in the capsule network to obtain a loss function value of each output vector;

A training module 65, configured to use the capsule network as a training network for identifying butterflies when the loss function value of each output vector is less than or equal to a preset loss threshold;

An update module 66 is configured to update each capsule neuron in the capsule network by back propagation when the loss function value is greater than a preset loss threshold, to obtain the updated capsule network, and use each butterfly species as training The target butterfly image is re-input into the updated capsule network, and the first convolution calculation, the second convolution calculation, and the loss function calculation are performed until the loss function value is less than or equal to a preset loss threshold, where the capsule neuron Attributes representing butterfly species.

Further, the resampling module 62 includes:

A scaling unit 621, configured to determine a scaling ratio of the original butterfly image according to a preset target size;

An obtaining unit 622 is configured to obtain the original pixel points of the original butterfly image according to the scaling ratio, obtain a set of original pixel points corresponding to each target pixel point of the target butterfly image in the original butterfly image, and establish each original pixel point. A correspondence between a set of pixels and each pixel of the target butterfly image;

A calculation unit 623 is configured to calculate an average RGB value of each original pixel in the set of original pixels, and use the average RGB value as an RGB value of a target pixel corresponding to the set of original pixels according to a corresponding relationship.

Further, the convolution module 63 includes:

A first convolution unit 631, configured to perform a first convolution calculation in a convolution layer of a capsule network on a target butterfly image input into a butterfly species for training, to obtain a feature vector;

An activation unit 632, configured to substitute the feature vector into a modified linear activation function to obtain a local feature vector;

A second convolution unit 633 is configured to perform a second convolution calculation using a local feature vector with each capsule neuron in a capsule layer of the capsule network by using an iterative routing processing method to obtain an output vector of a butterfly type.

Further, the calculation loss module 64 includes:

A formula unit 641 is configured to calculate each loss vector of the output vector in a loss function layer in the capsule network according to formula (6):

_{_{L c = T c max (0}} , m + - || V c ||) 2 + λ (1-T c) max (0, || V c || -m -) 2 Equation (6)

Among them, c is the butterfly type, L _c is the loss function value, T _c is the indicator function of the butterfly type, and max (0, m ⁺ -|| V _c ||) ² is taken as 0 and m ⁺ -|| V _c | | square of the maximum of two _{numbers, max (0, || V c} || -m -) 2 is taken and || -m 0 || V _c ^- the square of the maximum of the two values, m ⁺ Is the upper boundary of the preset vector length, || V _c || is the vector length of the output vector V _c , λ is the preset parameter value, and m ^- is the lower boundary of the preset vector length.

Further, the apparatus for constructing a butterfly recognition network further includes:

A test calculation module 67 is configured to input a target butterfly image used as a test into a training network for recognition of a butterfly, and obtain a loss function value of a test output vector through a first convolution calculation, a second convolution calculation, and a loss function calculation. ;

A reconstruction module 68 is configured to take a test output vector corresponding to a loss function value that is greater than or equal to a preset upper boundary of the vector length, and reconstruct the test output vector through a decoder network to obtain an output image, and compare the output image with The target butterfly images used for testing are compared to get the accuracy of the training network for butterfly recognition.

Regarding the specific definition of the device for constructing the butterfly recognition network, please refer to the limitation on the method for constructing the butterfly recognition network mentioned above, which will not be repeated here. Each module in the above-mentioned butterfly recognition network construction device may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware in or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 7. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in a non-volatile storage medium. The computer equipment database is used to store the original butterfly image. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement a method for constructing a butterfly recognition network.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the butterfly recognition of the foregoing embodiment is implemented. Steps of the network construction method, for example, steps S1 to S6 shown in FIG. 2 or, when the processor executes computer-readable instructions, the functions of each module / unit of the butterfly recognition network construction device in the above embodiment are implemented, as shown in FIG. 6 Modules 61 to 66 function. To avoid repetition, we will not repeat them here.

In one embodiment, one or more non-volatile readable storage media are provided, and computer-readable instructions are stored thereon. When the computer-readable instructions are executed by one or more processors, the butterfly in the foregoing method embodiment is implemented. The identification network construction method, or when the computer-readable instructions are executed by one or more processors, the functions of each module / unit in the butterfly identification network construction device in the above device embodiment are implemented. To avoid repetition, we will not repeat them here.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by using computer-readable instructions to instruct related hardware. The computer-readable instructions can be stored in one or more non-easy instructions. In the volatile readable storage medium, the computer-readable instructions, when executed, may include the processes of the embodiments of the methods described above. Wherein, any reference to the storage, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile storage. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

Those skilled in the art can clearly understand that, for the convenience and brevity of the description, only the above-mentioned division of functional units and modules is used as an example. In practical applications, the above functions can be assigned by different functional units, Module completion, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

The above embodiments are only used to describe the technical solutions of the present application, and are not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still apply the foregoing embodiments. The recorded technical solutions are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of this application, and shall be included in this application. Within the scope of protection.

Claims

A method for constructing a butterfly recognition network, comprising:

Obtain the original butterfly image corresponding to each butterfly species from a preset butterfly database;

Performing resampling processing on the original butterfly image to obtain a target butterfly image;

For each of the butterfly species, the target butterfly image used for training in the butterfly species is input into a capsule network, and passes through a first convolution calculation of a convolution layer of the capsule network and the capsule network. Calculation of the second convolution of the capsule layer to obtain the output vector of the butterfly species;

Performing a loss function calculation on the output vector of each of the butterfly species in a loss function layer in the capsule network to obtain a loss function value of each of the output vectors;

When the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, using the capsule network as a training network for identifying butterflies;

When the value of the loss function is greater than the preset loss threshold, each capsule neuron in the capsule network is updated by back propagation to obtain the updated capsule network, and each type of the butterfly species is updated. The target butterfly image used in training is re-input to the updated capsule network, and the first convolution calculation, the second convolution calculation, and the loss function calculation are performed until the loss function The value is less than or equal to the preset loss threshold, wherein the capsule neuron represents the attribute of the butterfly species.
The method for constructing a butterfly recognition network according to claim 1, wherein the resampling the original butterfly image to obtain a target butterfly image comprises:

Determining a scaling ratio of the original butterfly image according to a preset target size;

Dividing the original pixel points of the original butterfly image according to the scaling ratio to obtain a set of original pixel points, and establishing a distance between each of the original pixel point sets and each pixel point of the target butterfly image Correspondence

Calculate an average RGB value of each of the original pixel points in the set of original pixel points, and use the average RGB value as the target pixel point corresponding to the set of original pixel points according to the correspondence relationship RGB value.
The method for constructing a butterfly recognition network according to claim 1, wherein, for each of the butterfly species, the target butterfly image used for training in the butterfly species is input into a capsule network and passed through The first convolution calculation of the convolution layer of the capsule network and the second convolution calculation of the capsule layer of the capsule network, and the output vector of the butterfly species includes:

Performing the first convolution calculation in the convolution layer of the capsule network on the target butterfly image input into the butterfly species for training, to obtain a feature vector;

Substituting the feature vector into a modified linear activation function to obtain a local feature vector;

By using an iterative routing processing method, the local feature vector is subjected to the second convolution calculation with each of the capsule neurons in the capsule layer of the capsule network to obtain an output vector of the butterfly species.
The method for constructing a butterfly recognition network according to claim 1, wherein in the loss function layer in the capsule network, a loss function calculation is performed on the output vector of each butterfly species to obtain each The loss function values of the output vectors include:

Calculate each of the output vectors in the loss function layer in the capsule network according to the following formula:

L c = T c max (0 , m + - || V c ||) 2 + λ (1-T c) max (0, || V c || -m -) 2

Where c is the butterfly type, L c is the loss function value, T c is the indicator function of the butterfly type, and max (0, m + -|| V c ||) 2 is 0 and m + - the maximum value of the square of the two values of || V c ||, max (0, || V c || -m -) 2 is set to 0 and || V c || -m - of the two values The square of the maximum value, m + is the preset upper bound of the vector length, || V c || is the vector length of the output vector V c , λ is the preset parameter value, and m - is the preset vector length Lower border.
The method for constructing a butterfly recognition network according to claim 4, wherein, when the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, the capsule network is used as recognition After training the butterfly network, the method further includes:

Inputting the target butterfly image used as a test into the training network for identifying the butterfly, and obtaining the test output vector by the first convolution calculation, the second convolution calculation, and the loss function calculation The loss function value;

Taking the test output vector corresponding to the loss function value on the upper boundary of the preset vector length and reconstructing the test output vector through a decoder network to obtain an output image, and The output image is compared with the target butterfly image used as a test to obtain the accuracy of the training network for identifying the butterfly.
A butterfly recognition network construction device, characterized in that the butterfly recognition network construction device includes:

An acquisition module for acquiring an original butterfly image corresponding to each butterfly species from a preset butterfly database;

A resampling module for resampling the original butterfly image to obtain a target butterfly image;

A convolution module, for each of the butterfly species, inputting the target butterfly image used for training in the butterfly species into a capsule network, and passing a first convolution calculation of a convolution layer of the capsule network And a second convolution calculation of a capsule layer of the capsule network to obtain an output vector of the butterfly species;

A loss calculation module, configured to perform a loss function calculation on the output vector of each of the butterfly species in a loss function layer in the capsule network to obtain a loss function value of each of the output vectors;

A training module, configured to use the capsule network as a training network for identifying a butterfly when the loss function value of each of the output vectors is less than or equal to a preset loss threshold;

An update module is configured to update each capsule neuron in the capsule network by back propagation when the loss function value is greater than a preset loss threshold of the loss, to obtain the updated capsule network, and The target butterfly image used for training in each of the butterfly species is re-input into the updated capsule network, and the first convolution calculation, the second convolution calculation, and the loss function calculation are performed. Until the value of the loss function is less than or equal to the preset loss threshold, wherein the capsule neuron represents the attribute of the butterfly species.
The apparatus for constructing a butterfly recognition network according to claim 6, wherein the resampling module comprises:

A scaling unit, configured to determine a scaling ratio of the original butterfly image according to a preset target size;

An obtaining unit, configured to obtain the original pixel points of the original butterfly image according to the scaling ratio, to obtain a set of original pixel points corresponding to each target pixel point of the target butterfly image in the original butterfly image, And establish a correspondence between each set of the original pixel points and each pixel point of the target butterfly image;

A calculation unit, configured to calculate an average RGB value of each of the original pixel points in the set of original pixel points, and use the average RGB value as a corresponding value of the original pixel point set according to the correspondence relationship; Describe the RGB value of the target pixel.
The apparatus for constructing a butterfly recognition network according to claim 6, wherein the convolution module comprises:

A first convolution unit, configured to perform the first convolution calculation in the convolution layer of the capsule network on the target butterfly image input into the butterfly species for training, to obtain a feature vector;

An activation unit, configured to substitute the feature vector into a modified linear activation function to obtain a local feature vector;

A second convolution unit, configured to perform the second convolution calculation by using the iterative routing processing method to perform the second convolution calculation with the local feature vector and each of the capsule neurons in the capsule layer of the capsule network The output vector of the butterfly species.
The apparatus for constructing a butterfly recognition network according to claim 6, wherein the calculation loss module comprises:

A formula unit, configured to calculate each of the output vectors in a loss function layer in the capsule network according to the following formula:

L c = T c max (0 , m + - || V c ||) 2 + λ (1-T c) max (0, || V c || -m -) 2

Where c is the butterfly type, L c is the loss function value, T c is the indicator function of the butterfly type, and max (0, m + -|| V c ||) 2 is 0 and m + - the maximum value of the square of the two values of || V c ||, max (0, || V c || -m -) 2 is set to 0 and || V c || -m - of the two values The square of the maximum value, m + is the preset upper bound of the vector length, || V c || is the vector length of the output vector V c , λ is the preset parameter value, and m - is the preset vector length Lower border.
The apparatus for constructing a butterfly recognition network according to claim 9, wherein the apparatus for constructing a butterfly recognition network further comprises:

A test calculation module, configured to input the target butterfly image used as a test into the training network for recognizing butterflies, and calculate the first convolution calculation, the second convolution calculation, and the loss function calculation To obtain the loss function value of the test output vector;

A reconstruction module, configured to take the test output vector corresponding to the loss function value that is greater than or equal to the preset upper boundary of the vector length, and reconstruct the test output vector through a decoder network to obtain an output Image, and comparing the output image with the target butterfly image used as a test to obtain the accuracy of the training network for identifying the butterfly.
A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and is characterized in that the processor implements the computer-readable instructions as follows step:

Obtain the original butterfly image corresponding to each butterfly species from a preset butterfly database;

Performing resampling processing on the original butterfly image to obtain a target butterfly image;

For each of the butterfly species, the target butterfly image used for training in the butterfly species is input into a capsule network, and passes through a first convolution calculation of a convolution layer of the capsule network and the capsule network. Calculation of the second convolution of the capsule layer to obtain the output vector of the butterfly species;

Performing a loss function calculation on the output vector of each of the butterfly species in a loss function layer in the capsule network to obtain a loss function value of each of the output vectors;

When the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, using the capsule network as a training network for identifying butterflies;

When the value of the loss function is greater than the preset loss threshold, each capsule neuron in the capsule network is updated by back propagation to obtain the updated capsule network, and each type of the butterfly species is updated. The target butterfly image used in training is re-input to the updated capsule network, and the first convolution calculation, the second convolution calculation, and the loss function calculation are performed until the loss function The value is less than or equal to the preset loss threshold, wherein the capsule neuron represents the attribute of the butterfly species.
The computer device according to claim 11, wherein the resampling the original butterfly image to obtain the target butterfly image comprises:

Determining a scaling ratio of the original butterfly image according to a preset target size;

Dividing the original pixel points of the original butterfly image according to the scaling ratio to obtain a set of original pixel points, and establishing a distance between each of the original pixel point sets and each pixel point of the target butterfly image Correspondence

Calculate an average RGB value of each of the original pixel points in the set of original pixel points, and use the average RGB value as the target pixel point corresponding to the set of original pixel points according to the correspondence relationship RGB value.
The computer device according to claim 11, characterized in that, for each of said butterfly species, said target butterfly image used for training in said butterfly species is input into a capsule network and passes through said capsule network The first convolution calculation of the convolution layer and the second convolution calculation of the capsule layer of the capsule network, and the output vector of the butterfly species includes:

Performing the first convolution calculation in the convolution layer of the capsule network on the target butterfly image input into the butterfly species for training, to obtain a feature vector;

Substituting the feature vector into a modified linear activation function to obtain a local feature vector;

By using an iterative routing processing method, the local feature vector is subjected to the second convolution calculation with each of the capsule neurons in the capsule layer of the capsule network to obtain an output vector of the butterfly species.
The computer device according to claim 11, wherein in the loss function layer in the capsule network, a loss function calculation is performed on the output vector of each of the butterfly species to obtain each of the butterfly vectors. The loss function values of the output vector include:

Calculate each of the output vectors in the loss function layer in the capsule network according to the following formula:

L c = T c max (0 , m + - || V c ||) 2 + λ (1-T c) max (0, || V c || -m -) 2

Where c is the butterfly type, L c is the loss function value, T c is the indicator function of the butterfly type, and max (0, m + -|| V c ||) 2 is 0 and m + - the maximum value of the square of the two values of || V c ||, max (0, || V c || -m -) 2 is set to 0 and || V c || -m - of the two values The square of the maximum value, m + is the preset upper bound of the vector length, || V c || is the vector length of the output vector V c , λ is the preset parameter value, and m - is the preset vector length Lower border.
The computer device according to claim 14, wherein when the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, the capsule network is used as training for identifying a butterfly After the network, when the processor executes the computer-readable instructions, the following steps are further implemented:

Inputting the target butterfly image used as a test into the training network for identifying the butterfly, and obtaining the test output vector by the first convolution calculation, the second convolution calculation, and the loss function calculation The loss function value;

Taking the test output vector corresponding to the loss function value on the upper boundary of the preset vector length and reconstructing the test output vector through a decoder network to obtain an output image, and The output image is compared with the target butterfly image used as a test to obtain the accuracy of the training network for identifying the butterfly.
One or more non-volatile readable storage media storing computer readable instructions, characterized in that when the computer readable instructions are executed by one or more processors, the one or more processors are caused to execute The following steps:

Obtain the original butterfly image corresponding to each butterfly species from a preset butterfly database;

Performing resampling processing on the original butterfly image to obtain a target butterfly image;

For each of the butterfly species, the target butterfly image used for training in the butterfly species is input into a capsule network, and passes through a first convolution calculation of a convolution layer of the capsule network and the capsule network. Calculation of the second convolution of the capsule layer to obtain the output vector of the butterfly species;

Performing a loss function calculation on the output vector of each of the butterfly species in a loss function layer in the capsule network to obtain a loss function value of each of the output vectors;

When the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, using the capsule network as a training network for identifying butterflies;

When the value of the loss function is greater than the preset loss threshold, each capsule neuron in the capsule network is updated by back propagation to obtain the updated capsule network, and each type of the butterfly species is updated. The target butterfly image used in training is re-input to the updated capsule network, and the first convolution calculation, the second convolution calculation, and the loss function calculation are performed until the loss function The value is less than or equal to the preset loss threshold, wherein the capsule neuron represents the attribute of the butterfly species.
The non-volatile readable storage medium of claim 16, wherein the resampling the original butterfly image to obtain a target butterfly image comprises:

Determining a scaling ratio of the original butterfly image according to a preset target size;

Dividing the original pixel points of the original butterfly image according to the scaling ratio to obtain a set of original pixel points, and establishing a distance between each of the original pixel point sets and each pixel point of the target butterfly image Correspondence

Calculate an average RGB value of each of the original pixel points in the set of original pixel points, and use the average RGB value as the target pixel point corresponding to the set of original pixel points according to the correspondence relationship RGB value.
The non-volatile readable storage medium according to claim 16, wherein for each of said butterfly species, said target butterfly image used for training in said butterfly species is input into a capsule network, After passing the first convolution calculation of the convolution layer of the capsule network and the second convolution calculation of the capsule layer of the capsule network, the output vector of the butterfly species includes:

Performing the first convolution calculation in the convolution layer of the capsule network on the target butterfly image input into the butterfly species for training, to obtain a feature vector;

Substituting the feature vector into a modified linear activation function to obtain a local feature vector;

By using an iterative routing processing method, the local feature vector is subjected to the second convolution calculation with each of the capsule neurons in the capsule layer of the capsule network to obtain an output vector of the butterfly species.
The non-volatile readable storage medium according to claim 16, wherein in the loss function layer in the capsule network, a loss function calculation is performed on the output vector of each butterfly species To obtain the loss function value of each of the output vectors includes:

Calculate each of the output vectors in the loss function layer in the capsule network according to the following formula:

L c = T c max (0 , m + - || V c ||) 2 + λ (1-T c) max (0, || V c || -m -) 2

Where c is the butterfly type, L c is the loss function value, T c is the indicator function of the butterfly type, and max (0, m + -|| V c ||) 2 is 0 and m + - the maximum value of the square of the two values of || V c ||, max (0, || V c || -m -) 2 is set to 0 and || V c || -m - of the two values The square of the maximum value, m + is the preset upper bound of the vector length, || V c || is the vector length of the output vector V c , λ is the preset parameter value, and m - is the preset vector length Lower border.
The non-volatile readable storage medium according to claim 19, wherein when the value of the loss function of each of the output vectors is less than or equal to a preset loss threshold, the capsule is After the network is used as a training network for butterfly recognition, when the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

Inputting the target butterfly image used as a test into the training network for identifying the butterfly, and obtaining the test output vector by the first convolution calculation, the second convolution calculation, and the loss function calculation The loss function value;

Taking the test output vector corresponding to the loss function value on the upper boundary of the preset vector length and reconstructing the test output vector through a decoder network to obtain an output image, and The output image is compared with the target butterfly image used as a test to obtain the accuracy of the training network for identifying the butterfly.