CN110781999A

CN110781999A - Population generation method, and selection method and device of neural network architecture

Info

Publication number: CN110781999A
Application number: CN201911037319.0A
Authority: CN
Inventors: 初祥祥; 许瑞军; 张勃; 李吉祥; 李庆源; 王斌
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2019-10-29
Filing date: 2019-10-29
Publication date: 2020-02-11
Anticipated expiration: 2039-10-29
Also published as: CN110781999B

Abstract

The disclosure relates to a population generation method, a selection method of a neural network architecture and a device, wherein the method comprises the following steps: obtaining the t generation population R _t(ii) a For population R _tThe individuals contained in the method are subjected to non-dominated sorting to obtain k individual groups with different ranks; sequentially selecting i individual groups from the k individual groups; calculating weighted crowding distances of the jth individual under a plurality of targets according to the crowding distance of the jth individual under each target and the corresponding weight of each target; m individuals are selected from the ith individual group according to the weighted crowding distance, and the m individuals and all the individuals in the i-1 individual group form a t +1 generation population R _t+1(ii) a Let t be t +1 and again from the pair population R _tThe step of non-dominant ranking of the individuals contained in (1) is started when the T generation population R is generated _TWhen it is determinedPopulation R _TIs a target population. The method and the device for determining the crowding degree of the individual generate the population meeting the preference of a decision maker, and improve the flexibility of determining the crowding degree of the individual.

Description

Population generation method, and selection method and device of neural network architecture

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a population generation method, a selection method of a neural network architecture and a device thereof.

Background

NSGA-II (Non-dominant Sorting Genetic Algorithm with elite strategy-II) is an improved Algorithm for NSGA (Non-dominant Sorting Genetic Algorithm).

In NSGA-II, each individual in a population has two attributes: the non-dominant ranking attribute and the congestion degree attribute, when the non-dominant ranking attributes of the two individuals are inconsistent, namely the non-dominant rankings are different, the individuals with smaller non-dominant rankings are preferentially reserved; when the non-dominant ranking attributes of two individuals are consistent, i.e. the non-dominant rankings are the same, the crowdedness attribute is better, i.e. less crowded individuals around will be preferentially retained.

However, for individuals with consistent non-dominant ranking attributes, the crowdedness attribute is determined according to the crowdedness of the individuals on different optimization targets, and the determination mode is single.

Disclosure of Invention

The embodiment of the disclosure provides a population generation method, a selection method of a neural network architecture and a device thereof.

The technical scheme is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a population generating method, including:

obtaining the t generation population R _tSaid population R _tIncluding a population P _tAnd a population Q _tSaid population Q _tIs said population P _tObtained after treatment, the population P _tAnd said population Q _tThe number of individuals contained in the formula (I) is n, and t isThe initial value of t is 1, and n is a positive integer;

for the population R _tThe individuals contained in the method are subjected to non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1;

sequentially selecting i individual groups from the k individual groups according to the sequence from small to large, wherein the total number of individuals contained in the i individual groups is greater than or equal to n, and the total number of individuals contained in the i-1 individual groups is less than n;

for a jth individual in the ith individual group, calculating weighted crowding distances of the jth individual under multiple targets according to the crowding distance of the jth individual under each target and the corresponding weight of each target;

selecting m individuals from the ith individual group according to the weighted crowding distance of each individual in the ith individual group, wherein m is the difference value between n and the total number of individuals contained in the i-1 individual group;

generating the t +1 generation population R _t+1Said population R _t+1Including a population P _t+1And a population Q _t+1Said population P _t+1Including said m individuals and individuals in said i-1 group of individuals, said population Q _t+1Is said population P _t+1Obtained after treatment, the population Q _t+1And said population P _t+1The number of individuals contained in (a) is n;

let t be t +1 and again from the population R _tThe step of obtaining k individual groups with different ranks is started to be executed when the T generation population R is generated _TThen determining said population R _TAnd T is a preset value and is an integer greater than 1.

Optionally, the calculating the weighted crowding distance of the jth individual under the multiple targets according to the crowding distance of the jth individual under each target and the weight corresponding to each target includes: for a target x in the multiple targets, sorting each individual in the ith individual group according to a function value corresponding to the target x, wherein x is a positive integer; calculating the crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and the maximum value and the minimum value in the sequencing results; and calculating the weighted crowding distance of the jth individual under the plurality of targets according to the crowding distance of the jth individual under the target x and the weight corresponding to the target x.

Optionally, the calculating a crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and a maximum value and a minimum value in the sorting results includes: calculating a difference value of the function values of two adjacent individuals of the jth individual; calculating a difference between the maximum value and the minimum value; and dividing the difference value of the function values by the difference value of the maximum value and the minimum value to obtain the crowding distance of the j-th individual under the target x.

Optionally, the calculating the weighted crowding distance of the jth individual under the multiple targets according to the crowding distance of the jth individual under each target and the weight corresponding to each target includes: multiplying the crowding distance of the jth individual under the target x by the weight corresponding to the target x; and accumulating the multiplication results of the jth individual and the multiple targets to obtain the weighted crowding distance of the jth individual under the multiple targets.

Optionally, said determining said population R _TAfter the target population is obtained, the method further comprises the following steps: acquiring preset indexes of all individuals in the target population; and selecting target individuals from the target population according to the preset index.

According to a second aspect of embodiments of the present disclosure, there is provided a method of selecting a neural network architecture, the method comprising:

obtaining a t-th generation architecture population R _tSaid architecture population R _tIncluding an architecture group P _tAnd architecture group Q _tSaid architecture group Q _tIs the architecture population P _tTreated byObtained later, the architecture population P _tAnd said architecture population Q _tThe number of the neural network architectures contained in the method is n, t is a positive integer, the initial value of t is 1, and n is a positive integer;

for the architecture population R _tThe neural network architecture contained in the method carries out non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1;

sequentially selecting i individual groups from the k individual groups according to the sequence from small to large, wherein the total number of neural network architectures contained in the i individual groups is greater than or equal to n, and the total number of neural network architectures contained in the i-1 individual groups is less than n;

for a jth neural network architecture in the ith individual group, calculating weighted crowding distances of the jth neural network architecture under multiple targets according to the crowding distance of the jth neural network architecture under each target and the corresponding weight of each target;

selecting m neural network architectures from the ith individual group according to the weighted crowding distance of each neural network architecture in the ith individual group, wherein m is the difference between n and the total number of the neural network architectures contained in the i-1 individual group;

generating a t +1 th generation architecture population R _t+1Said architecture population R _t+1Including an architecture group P _t+1And architecture group Q _t+1Said architecture population P _t+1Including the m neural network architectures and the neural network architectures in the i-1 individual groups, the architecture population Q _t+1Is the architecture population P _t+1Obtained after processing, the architecture population Q _t+1And the architecture population P _t+1The number of the neural network architectures contained in the step (a) is n;

let t be t +1 and again from the pair of the architecture populations R _tThe neural network architecture contained in the method carries out non-dominated sorting, the step of obtaining k individual groups with different ranks is started to be executed, and when a T generation architecture population R is generated _TThen determining the architecture population R _TIs a target architectureThe T is a preset value and is an integer greater than 1;

selecting a target neural network architecture from the target architecture population;

deploying the target neural network architecture in a terminal.

Optionally, the selecting a target neural network architecture from the target architecture population includes: acquiring parameter indexes of each neural network architecture in the target architecture population; and selecting the target neural network architecture from the target architecture population according to the parameter index.

Optionally, the selecting a target neural network architecture from the target architecture population according to the parameter index includes: selecting z neural network architectures from the target architecture population according to the operation speed, wherein z is a positive integer; and selecting the target neural network architecture from the z neural network architectures according to an evaluation index, wherein the evaluation index comprises a business evaluation index and/or a floating point operand.

According to a third aspect of embodiments of the present disclosure, there is provided a cluster generation apparatus, the apparatus comprising:

a population acquisition module configured to acquire a t-th generation population R _tSaid population R _tIncluding a population P _tAnd a population Q _tSaid population Q _tIs said population P _tObtained after treatment, the population P _tAnd said population Q _tThe number of individuals contained in the formula (I) is n, t is a positive integer, the initial value of t is 1, and n is a positive integer;

an individual group generation module configured to generate the population R _tThe individuals contained in the method are subjected to non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1;

an individual group selecting module configured to sequentially select i individual groups from the k individual groups according to a descending order of the rank, wherein the total number of individuals included in the i individual groups is greater than or equal to the n, and the total number of individuals included in the i-1 individual groups is less than the n;

a weighted crowding distance calculation module configured to calculate, for a jth individual in the ith individual group, weighted crowding distances of the jth individual under multiple targets according to the crowding distance of the jth individual under each target and a weight corresponding to each target;

an individual selecting module configured to select m individuals from the ith individual group according to the weighted crowding distance of each individual in the ith individual group, wherein m is a difference value between n and a total number of individuals included in the i-1 individual group;

a population generation module configured to generate a t +1 th generation population R _t+1Said population R _t+1Including a population P _t+1And a population Q _t+1Said population P _t+1Including said m individuals and individuals in said i-1 group of individuals, said population Q _t+1Is said population P _t+1Obtained after treatment, the population Q _t+1And said population P _t+1The number of individuals contained in (a) is n;

a population determination module configured to let t ═ t +1, and to determine the population R again from the pair _tThe step of obtaining k individual groups with different ranks is started to be executed when the T generation population R is generated _TThen determining said population R _TAnd T is a preset value and is an integer greater than 1.

Optionally, the weighted congestion distance calculating module includes: the individual sorting submodule is configured to, for a target x in the multiple targets, sort each individual in the ith individual group according to a function value corresponding to the target x, wherein x is a positive integer; a crowding distance calculation sub-module configured to calculate a crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and a maximum value and a minimum value in the sorting results; and the weighted crowding distance calculation sub-module is configured to calculate weighted crowding distances of the jth individual under the multiple targets according to the crowding distance of the jth individual under the target x and the weight corresponding to the target x.

Optionally, the congestion distance calculation sub-module is configured to: calculating a difference value of the function values of two adjacent individuals of the jth individual; calculating a difference between the maximum value and the minimum value; and dividing the difference value of the function values by the difference value of the maximum value and the minimum value to obtain the crowding distance of the j-th individual under the target x.

Optionally, the weighted congestion distance calculation sub-module is configured to: multiplying the crowding distance of the jth individual under the target x by the weight corresponding to the target x; and accumulating the multiplication results of the jth individual and the multiple targets to obtain the weighted crowding distance of the jth individual under the multiple targets.

Optionally, the apparatus further comprises: the preset index acquisition module is configured to acquire preset indexes of all individuals in the target population; and the target individual selecting module is configured to select a target individual from the target population according to the preset index.

According to a fourth aspect of embodiments of the present disclosure, there is provided a selection apparatus of a neural network architecture, the apparatus including:

an architecture population acquisition module configured to acquire a tth-generation architecture population R _tSaid architecture population R _tIncluding an architecture group P _tAnd architecture group Q _tSaid architecture group Q _tIs the architecture population P _tObtained after processing, the architecture population P _tAnd said architecture population Q _tThe number of the neural network architectures contained in the method is n, t is a positive integer, the initial value of t is 1, and n is a positive integer;

an individual group generation module configured to generate the architecture population R _tThe neural network architecture contained in the method carries out non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1;

an individual group selection module configured to sequentially select i individual groups from the k individual groups according to a descending order of the rank, wherein a total number of neural network architectures included in the i individual groups is greater than or equal to the n, and a total number of neural network architectures included in the i-1 individual groups is less than the n;

a weighted crowding distance calculation module configured to calculate, for a jth neural network architecture in the ith individual group, weighted crowding distances of the jth neural network architecture under a plurality of targets according to the crowding distance of the jth neural network architecture under each target and a weight corresponding to each target;

an individual selecting module configured to select m neural network architectures from the ith individual group according to the weighted crowding distance of each neural network architecture in the ith individual group, wherein m is a difference value between n and a total number of neural network architectures included in the i-1 individual group;

an architecture population generation module configured to generate a t +1 th generation architecture population R _t+1Said architecture population R _t+1Including an architecture group P _t+1And architecture group Q _t+1Said architecture population P _t+1Including the m neural network architectures and the neural network architectures in the i-1 individual groups, the architecture population Q _t+1Is the architecture population P _t+1Obtained after processing, the architecture population Q _t+1And the architecture population P _t+1The number of the neural network architectures contained in the step (a) is n;

an architecture population determination module configured to let t ═ t +1, and again from the pair of the architecture populations R _tThe neural network architecture contained in the method carries out non-dominated sorting, the step of obtaining k individual groups with different ranks is started to be executed, and when a T generation architecture population R is generated _TThen determining the architecture population R _TThe target architecture population is shown, and T is a preset value and is an integer greater than 1;

a neural network architecture selection module configured to select a target neural network architecture from the target architecture population;

a neural network architecture deployment module configured to deploy the target neural network architecture in a terminal.

Optionally, the neural network architecture selecting module includes: a parameter index obtaining submodule configured to obtain a parameter index of each neural network architecture in the target architecture population; and the neural network architecture selecting submodule is configured to select the target neural network architecture from the target architecture population according to the parameter index.

Optionally, the neural network architecture selection sub-module is configured to: selecting z neural network architectures from the target architecture population according to the operation speed, wherein z is a positive integer; and selecting the target neural network architecture from the z neural network architectures according to an evaluation index, wherein the evaluation index comprises a business evaluation index and/or a floating point operand.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer device comprising a processor and a memory, the memory having stored therein a computer program, the computer program being loaded and executed by the processor to implement the steps of the population generating method according to the first aspect as described above, or to implement the steps of the selecting method of the neural network architecture according to the second aspect as described above.

According to a sixth aspect of embodiments of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the population generation method according to the first aspect or implements the steps of the selection method of the neural network architecture according to the second aspect.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

the weighted crowding distance of each individual is calculated according to the crowding distance of each individual in the individual group under each target and the weight corresponding to each target, then the individuals with the required number are selected from the individual group according to the weighted crowding distance to generate the target population, a population generation mode is expanded, the crowding degree of the individuals is determined according to the weights of the targets, then the individuals with the required number are selected from the individual group according to the crowding degree to generate the target population, therefore, the priority of the targets can be adjusted according to the preference of a decision maker to the targets, the population meeting the preference of the decision maker is generated, and the flexibility of determining the crowding degree of the individuals is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

FIG. 1 is a flow diagram illustrating a population generation method in accordance with an exemplary embodiment;

FIG. 2 is a schematic diagram illustrating an individual selection method according to an exemplary embodiment;

FIG. 3 is a flow diagram illustrating a method of selecting a neural network architecture in accordance with an exemplary embodiment;

FIG. 4 is a block diagram illustrating a cluster generation apparatus in accordance with an exemplary embodiment;

FIG. 5 is a block diagram illustrating a cluster generation apparatus in accordance with another exemplary embodiment;

FIG. 6 is a block diagram illustrating a selection device of a neural network architecture in accordance with an exemplary embodiment;

FIG. 7 is a block diagram illustrating a selection apparatus of a neural network architecture, in accordance with another exemplary embodiment;

FIG. 8 is a block diagram illustrating a computer device in accordance with an exemplary embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

According to the technical scheme provided by the embodiment of the disclosure, the execution main body of each step can be a computer device, such as a server with computing and storing capabilities, and optionally, the computer device can be one server, a server cluster composed of a plurality of servers, or a cloud computing service center. For convenience of explanation, in the following method embodiments, the steps are described as being executed by a server, but the present invention is not limited thereto.

FIG. 1 is a flow diagram illustrating a population generation method according to an exemplary embodiment. The method comprises the following steps (steps 101-107):

step 101, obtaining the t generation population R _tT is a positive integer and the initial value of t is 1.

T generation population R _tIncluding a population P _tAnd a population Q _tPopulation Q _tIs a population P _tObtained after treatment. Alternatively, the population Q _tIs a population P _tSequentially carrying out a series of treatments such as selection treatment, cross treatment, mutation treatment and the like.

The selection process, also referred to as a replication process, is to select a certain number of individuals from a population according to a certain probability, so as to use the individuals as parents and perform subsequent reproduction to generate new individuals, optionally, the size of the probability and the number of the individuals are specifically set according to an actual application scenario, and the specific manner of the selection process includes roulette selection (roulette wheel selection), tournament selection (sport selection), steady-state replication (steady-state replication), scaling and sorting selection, sharing (sharing) method, and the like, which is not limited in the embodiment of the present disclosure.

The interleaving processing refers to replacing and recombining the partial structures of each pair of individuals selected as parents by the selection processing, and optionally, the specific manner of the interleaving processing is influenced by the encoding manner of each pair of individuals as parents, for example, when the encoding manner is binary encoding or gray code encoding, the manner of the interleaving processing is interleaving, when the encoding manner is real number encoding, the manner of the interleaving processing is recombining, and when the encoding manner is integer or letter permutation encoding, the manner of the interleaving processing is rearranging.

The mutation processing refers to selecting a certain number of individuals from the population after the cross processing according to a certain probability, and randomly selecting one of the selected individuals to perform negation, optionally, the size of the probability and the number of the individuals are specifically set according to an actual application scenario, and the mutation processing mode includes binary mutation, real number mutation, serial number mutation, and the like, which is not limited in the embodiment of the present disclosure.

In the disclosed embodiment, the population Q _tThe number of individuals and the population P contained in _tThe number of individuals contained in (a) is the same, i.e. the population P _tAnd a population Q _tThe number of individuals contained in the formula (I) is n, and n is a positive integer.

Step 102, for population R _tThe individuals contained in the Chinese patent application are subjected to non-dominated sorting to obtain k individual groups with different ranks, and k is a positive integer greater than 1.

The rank refers to the order, and the obtained k individual groups with different ranks are the obtained k individual groups with different orders. Non-dominated sorting refers to sorting by population R _tThe dominant and non-dominant relationships of the individuals contained in (a) are ordered. Assuming that the population comprises an individual A and an individual B, when all the objective function values of the individual A are larger than those of the individual B, the individual A and the individual B are considered to be in a dominance relationship, and the individual A dominates the individual B; when individual a has an objective function value less than individual B, individual a is considered to be in a non-dominant relationship with individual B.

For example, first, a population R is found _tAll the non-dominant individuals are stored into an individual group with the rank of 0, namely, the individuals without dominant relationship with other individuals are found and stored into the individual group with the rank of 0, and each individual in the individual group with the rank of 0 is endowed with the same non-dominant sequence 0; then, for each individual in the individual group with the rank of 0, if an individual dominated by the individual does not exist in the individual group dominated by other individuals except the individual, storing the individuals in the individual group into the individual group with the rank of 1, and assigning the same non-dominated order 1 to each individual in the individual group with the rank of 1; then, for each individual in the individual group of rank 1, the same operation as for each individual in the individual group of rank 0 is performed, and the selected individuals are stored in the individual group of rank 2, and for the individuals of rank 2Each individual in the body group was assigned the same non-dominant order 2; and so on until the population R _tAll individuals in (a) are stored in a corresponding group of individuals and assigned a corresponding non-dominant order.

And 103, sequentially selecting i individual groups from the k individual groups according to the sequence from small to large, wherein the total number of the individuals in the i individual groups is greater than or equal to n, and the total number of the individuals in the i-1 individual groups is less than n.

Each of the k individual groups corresponds to a rank, and optionally, a value of the rank is a natural number. And the server sequentially selects i individual groups from the k individual groups with different ranks according to the rank from small to large.

For example, as shown in FIG. 2, population P _tAnd a population Q _tThe number of individuals contained in (1) is n, and the population P _tAnd a population Q _tConstituent population R _tThe number of individuals contained in (1) is 2n, and the population R _tThe k individual groups are arranged according to the sequence of the ranks from small to large, and are sequentially the individual groups F with the rank of 0 ₀ Rank 1 of the group F ₁Rank 2 of the group F ₂… … hypothesis Individual group F ₀And individual group F ₁In which the total number of individuals contained is less than n, group of individuals F ₀Group of individuals F ₁And individual group F ₂If the total number of individuals contained in the group is greater than or equal to n, 3 individual groups are determined to be sequentially selected from the k individual groups, and are respectively an individual group F ₀Group of individuals F ₁And individual group F ₂The remaining group of individuals and individuals in the group of individuals are eliminated, i.e., discarded.

And 104, calculating the weighted congestion distance of the jth individual in the ith individual group under a plurality of targets according to the congestion distance of the jth individual under each target and the corresponding weight of each target.

In the disclosed embodiment, the slave population R is required _tN individuals are selected to generate the next generation population, but when the total number of the individuals included in the i individual groups selected in step 103 is larger than n, and the number of the individuals in the i-1 individual groups is larger than nWhen the total number of individuals contained in the group is less than n, a certain number of individuals need to be eliminated from the individuals contained in the i individual groups, and at the moment, the server needs to select proper individuals from the i individual groups according to certain data to be reserved. In the disclosed embodiment, the server determines whether each individual in the group of i individuals survives based on the weighted crowding distance of the individual.

The weighted congestion distance is based on the individual congestion degrees of a plurality of targets. The weighted crowding distance of an individual is calculated based on the weight corresponding to each target and the crowding distance of the individual under each target. Optionally, in order to facilitate the calculation of the weighted congestion distance by the server and reduce the processing overhead of the server, in the embodiment of the present disclosure, the sum of the weights corresponding to each target is 1. Optionally, in order to embody the preference degree of the decision maker for each target and satisfy the requirement that the decision maker flexibly sets the weight according to different application scenarios, the weight corresponding to each target in the embodiment of the present disclosure may be set according to an actual application scenario, or according to the importance degree of the target, for example, three targets, denoted as target 1, target 2, and target 3, are used in common in calculating the weighted congestion distance, and assuming that the decision maker best sees the goodness and badness degree of the weighted individuals on target 2, that is, the decision maker prefers that the individuals better performing on target 2 are retained, the weight corresponding to target 2 may be set higher than the weights corresponding to targets 1 and 3, for example, the weight corresponding to target 1 is set to 0.2, the weight corresponding to target 2 is set to 0.7, and the weight corresponding to target 3 is set to 0.1.

And 105, selecting m individuals from the ith individual group according to the weighted crowding distance of each individual in the ith individual group, wherein m is the difference between n and the total number of individuals in the i-1 individual group.

After the server calculates the weighted crowding distance of each individual in the ith individual group, m remaining individuals are selected from the ith individual group according to the weighted crowding distance, and the rest individuals are eliminated. Optionally, in order to facilitate the server to select the individuals in the ith individual group, selecting m individuals from the ith individual group according to the weighted congestion distance of each individual in the ith individual group includes: according to the ith individual groupThe weighted crowding distance of each individual, sorting the individuals in the ith individual group; and selecting m individuals from the ith individual group according to the sorting result. For example, as shown in FIG. 2, the ith individual group is individual group F ₂From the individual group F ₂Selecting m individuals, and calculating an individual group F ₂Weighted congestion distance of each individual; then, the individuals are sorted according to the weighted crowding distance, in the embodiment of the disclosure, the individuals can be sorted in the order from the weighted crowding distance to be smaller, or sorted in the order from the weighted crowding distance to be smaller; and then selecting m individuals with larger weighted congestion distances from the sorting result, namely selecting the individuals corresponding to the first m weighted congestion distances from the sorting result to reserve if the individuals are sorted according to the sequence of the weighted congestion distances from large to small, and selecting the individuals corresponding to the last m weighted congestion distances from the sorting result to reserve if the individuals are sorted according to the sequence of the weighted congestion distances from small to large.

In the disclosed embodiment, in order to ensure the slave population R _tThe number of individuals selected in (1) for generating the next generation population is n, and m is the difference between n and the total number of individuals included in the i-1 individual group.

106, generating a t +1 generation population R _t+1。

T +1 th generation population R _t+1Including a population P _t+1And a population Q _t+1Population Q _t+1Is a population P _t+1Obtained after treatment. Alternatively, the population Q _t+1Is a population P _t+1The detailed descriptions of the selection processing, the crossover processing, and the mutation processing are referred to in step 101, and are not repeated here.

In the disclosed embodiment, the population P _t+1Including m individuals and i-1 individuals in the group of individuals, as shown in FIG. 2, the ith group of individuals is group F of individuals ₂I-1 Individual groups are individually groups F ₀And individual group F ₁According to individual group F ₂Weighted crowding distance of each individual in (1), from the individual group F ₂Selecting m individuals and eliminatingBody group F ₂And the other individuals in (1) and the group of individuals F ₀Group of individuals F ₁And individual group F ₂A group of individuals other than the group, and the m individuals are combined with an individual group F ₀And individual group F ₁The individuals in (A) make up a population P _t+1Then according to the population P _t+1Generating a population Q _t+1And the population P is divided into _t+1And a population Q _t+1Are combined into a population R _t+1. In the disclosed embodiment, the population Q _t+1The number of individuals and the population P contained in _t+1The number of individuals contained in (a) is the same, i.e. the population P _t+1And a population Q _t+1The number of individuals contained in (a) is n.

Step 107, let t equal t +1, and again from the pair population R _tThe step of obtaining k individual groups with different ranks is started to be executed when the T generation population R is generated _TThen, the population R is determined _TT is a preset value and is an integer larger than 1.

Based on the introduction of the non-dominated sorting in step 102 and the process of obtaining k individual groups with different ranks, the relevant introduction in step 107 is obtained, and will not be described herein again. Optionally, in order to meet the personalized requirement of the actual application scenario, the server specifically determines a value of T according to the requirement of the actual application scenario, for example, the value of T is 50.

Optionally, in order to further select the required individuals from the target population, step 107 further includes: acquiring preset indexes of each individual in a target population; and selecting target individuals from the target population according to preset indexes. For example, when the technical scheme of the embodiment of the present disclosure is applied to a neural network architecture, the preset index may include a running speed, a running precision, a floating point operand, and the like, and for detailed description, reference is made to the following embodiments, which are not repeated herein. Optionally, in order to facilitate the server to select a needed individual from the target population, selecting the target individual from the target population according to a preset index includes: sequencing each individual in the target population according to a preset index; and selecting target individuals from the target population according to the sequencing result. Optionally, in order to introduce a preference degree of the decision maker for a preset index, the sorting, according to the preset index, each individual in the target population includes: and sequencing each individual in the target population according to the preset indexes and the weights corresponding to the preset indexes. For example, in a neural network architecture, there are three preset indexes, which are an operation speed, a service evaluation index and a floating point operand, respectively, and a decision maker focuses on how fast the operation speed is, sets the maximum weight corresponding to the operation speed, so as to sort each individual in a target population, and then selects a target individual from the target population according to a sorting result, where the target individual meets the requirement of the decision maker on the operation speed.

In summary, according to the technical scheme provided by the embodiment of the present disclosure, the weighted congestion distance of each individual is calculated according to the congestion distance of each individual in the individual group under each target and the weight corresponding to each target, and then the required number of individuals are selected from the individual group to generate the target population according to the weighted congestion distance, so that a population generation manner is extended, the congestion degree of the individual is determined according to the weights of multiple targets, and then the required number of individuals are selected from the individual group to generate the target population according to the congestion degree, so that the priorities of the multiple targets can be adjusted according to the preference of a decision maker for the multiple targets, the population meeting the preference of the decision maker is generated, and the flexibility of determining the congestion degree of the individual is improved.

In addition, according to the technical scheme provided by the embodiment of the disclosure, the preset indexes of the individuals in the generated population are obtained, and then the needed individuals are selected from the generated population according to the preset indexes and applied to the actual application scene, so that the needed individuals are flexibly selected according to different application scenes, and the individual requirements of a decision maker on the individuals are met.

In one possible implementation, the step 104 includes: for a target x in a plurality of targets, sorting each individual in the ith individual group according to a function value corresponding to the target x, wherein x is a positive integer; calculating the crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and the maximum value and the minimum value in the sequencing result; and calculating the weighted congestion distances of the jth individual under a plurality of targets according to the congestion distance of the jth individual under the target x and the weight corresponding to the target x.

In the embodiment of the present disclosure, each target is represented in the form of a function, and each individual in the ith individual group has a function value corresponding to each target. For an object x in the multiple objects, the individuals in the ith individual group may be sorted according to the magnitude of the function value, and the server may sort the individuals according to the function value from small to large, or sort the individuals according to the function value from large to small, which is not limited in this embodiment of the disclosure. For the jth individual in the ith individual group, the server may calculate the congestion distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and the maximum value and the minimum value in the ranking result, where the two adjacent individuals of the jth individual refer to two individuals whose function values are closest to the function value of the jth individual in the ranking result. After the server calculates the congestion distance of the jth individual at object x, the server can calculate the weighted congestion distances of the jth individual at a plurality of objects based on the congestion distance and the weight corresponding to object x.

Optionally, the calculating a crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and the maximum value and the minimum value in the sorting result includes: calculating the difference value of the function values of two adjacent individuals of the jth individual; calculating the difference between the maximum value and the minimum value; and dividing the difference value of the function values by the difference value of the maximum value and the minimum value to obtain the crowding distance of the jth individual under the target x.

After the server obtains two adjacent individuals of the jth individual and the function values of the two adjacent individuals on the target x, the difference between the function values of the two adjacent individuals can be calculated according to the function values of the two adjacent individuals, and optionally, in order to facilitate subsequent calculation and processing by the server, the difference between the function values of the two adjacent individuals is calculated by subtracting the smaller function value from the larger function value of the two adjacent individuals. It should be noted that, the step of calculating the difference between the function values of two adjacent individuals of j individuals by the server, and the step of calculating the difference between the maximum value and the minimum value by the server may be executed simultaneously or sequentially. And the server obtains the crowding distance of the j-th individual under the target x after the difference value of the function values is in the difference value of the maximum value and the minimum value. Optionally, the formula for the server to calculate the crowding distance of the jth individual under the target x is as follows:

where D represents the crowding distance of the jth individual under the target x, and O ₊ ^xRepresents the larger of the function values of two adjacent ones of the jth individual, O _- ^xRepresents the smaller of the function values of two adjacent ones of the j-th individual, O _max ^xRepresenting the maximum value, O, in the ranking result based on the target x _min ^xRepresenting the minimum value in the ranking result based on the target x.

Optionally, the calculating the weighted congestion distances of the jth individual under the multiple targets according to the congestion distances of the jth individual under the targets and the weights corresponding to the targets includes: multiplying the crowding distance of the jth individual under the target x by the weight corresponding to the target x; and accumulating the multiplication results of the jth individual and the plurality of targets to obtain the weighted congestion distance of the jth individual under the plurality of targets.

In the embodiment of the present disclosure, for the congestion distance of the jth individual in other targets than the target x among the multiple targets, the same calculation method as the congestion distance in the target x is also adopted, and the related calculation process is described above and is not described herein again. After calculating the congestion distances of the jth individual on the multiple targets, the server multiplies the congestion distances by the weights of the corresponding targets, and obtains the weighted congestion distances of the jth individual on the multiple targets by adopting a weighted summation mode. Optionally, the server calculates the weighted congestion distance of the jth individual under multiple targets according to the following formula:

wherein D (j) represents the weighted congestion distance of the jth individual, O ₊ ^xThe larger of the function values of two adjacent ones of the jth individual under the target x, O _- ^xRepresents the smaller of the function values of two adjacent individuals of the jth individual under the target x, O _max ^xRepresenting the maximum value, O, in the ranking result based on the target x _min ^xRepresenting the minimum value, w, in the ranking result based on the target x _xThe weight corresponding to the target x is shown, y represents the number of targets, and y is a positive integer.

In summary, according to the technical scheme provided by the embodiment of the present disclosure, the crowding distance of an individual under a single target is calculated according to the adjacent individuals of the individual under the single target and the maximum value and the minimum value under the single target, and then the weighted crowding distance of the individual under multiple targets is calculated according to the crowding distance of the individual under the single target and the weight corresponding to the single target, so that a manner of determining the crowding degree of the individual is expanded, the weight corresponding to the single target is flexibly set according to actual requirements, and the crowding degree of the individual is determined according to the preference degree of a decision maker to each target is introduced.

FIG. 3 is a flow chart illustrating a method of selecting a neural network architecture, according to an example embodiment. The method can comprise the following steps (steps 301 to 307)

Step 301, obtaining the t-th generation architecture population R _tBuilding of population R _tIncluding an architecture group P _tAnd architecture group Q _tArchitecture group Q _tIs an architecture group P _tObtained after processing, architecture population P _tAnd architecture group Q _tThe number of the neural network architectures included in the method is n, t is a positive integer, the initial value of t is 1, and n is a positive integer.

Step 302, for the architecture population R _tThe neural network architecture contained in the method carries out non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1.

Step 303, sequentially selecting i individual groups from the k individual groups according to the sequence from small to large, wherein the total number of the neural network architectures included in the i individual groups is greater than or equal to n, and the total number of the neural network architectures included in the i-1 individual groups is less than n.

And step 304, for the jth neural network architecture in the ith individual group, calculating weighted congestion distances of the jth neural network architecture under a plurality of targets according to the congestion distance of the jth neural network architecture under each target and the corresponding weight of each target.

Step 305, according to the weighted crowding distance of each neural network architecture in the ith individual group, selecting m neural network architectures from the ith individual group, wherein m is the difference between n and the total number of the neural network architectures contained in the i-1 individual group.

Step 306, generating the t +1 th generation architecture population R _t+1Building of population R _t+1Including an architecture group P _t+1And architecture group Q _t+1Architecture group P _t+1Comprises m neural network architectures and a neural network architecture in i-1 individual groups, and an architecture group Q _t+1Is an architecture group P _t+1Obtained after processing, architecture group Q _t+1And an architecture group P _t+1The number of the neural network architectures included in the above is n.

Step 307, let t be t +1, and again from the pair framework population R _tThe neural network architecture contained in the method carries out non-dominated sorting, the step of obtaining k individual groups with different ranks is started to be executed, and when a T generation architecture population R is generated _TThen, determining the architecture population R _TFor the target architecture population, T is a preset value and is an integer greater than 1.

Based on the descriptions of steps 101 to 107 in the embodiment shown in fig. 1, the descriptions of steps 301 to 307 in this embodiment are obtained, and for details of steps 301 to 307, please refer to the embodiment shown in fig. 1, which is not repeated herein.

And 308, selecting a target neural network architecture from the target architecture population.

Optionally, the selecting the target neural network architecture from the target architecture population includes: and selecting a target neural network architecture from the target architecture population according to a preset index. The preset index is an index for evaluating each neural network architecture in the target architecture population, and the preset index may be a value corresponding to one parameter index for evaluating the quality of the neural network architecture or a value obtained by integrating multiple parameter indexes for evaluating the quality of the neural network architecture, which is not limited in the embodiments of the present disclosure. Optionally, in order to facilitate the server to select the target neural network architecture from the target architecture population, the selecting the target neural network architecture from the target architecture population according to the preset index includes: sorting the neural network architectures in the target architecture population according to a preset index; and selecting a target neural network architecture from the target architecture population according to the sequencing result. In the embodiment of the present disclosure, the neural network architectures may be sorted from small to large according to the preset index, and may also be sorted from large to small according to the preset index.

Optionally, in order to clarify a specific selection manner of the neural network architecture, the step 308 includes: acquiring parameter indexes of each neural network architecture in a target architecture population; and selecting a target neural network architecture from the target architecture population according to the parameter index. For example, in the embodiment of the present disclosure, the parameter index is applied to a selection method of a neural network architecture, optionally, the parameter index may at least include any one of a running speed, a service evaluation index, and a floating point operand, the embodiment of the present disclosure does not limit the number of the parameter indexes, and in the actual application, the neural network architecture in the target architecture population may be evaluated only according to the parameter index on the one hand, or the neural network architecture in the target architecture population may be evaluated according to the parameter indexes in various aspects, for example, the neural network architecture in the target architecture population may be evaluated only according to the running speed, the neural network architecture in the target population architecture may be evaluated according to the running speed and the floating point operand, or the neural network architecture in the target population architecture may be evaluated according to the service evaluation index and the floating point operand, or the like .

Optionally, in order to simplify the selection of the target neural network architecture from the target architecture population by the server, the selecting of the target neural network architecture from the target architecture population according to the parameter index includes: selecting z neural network architectures from the target architecture population according to the operation speed; selecting a target neural network architecture from the z neural network architectures according to an evaluation index, wherein the evaluation index comprises a business evaluation index and/or a floating point operand, and the business evaluation index comprises any one of the following items: accuracy, mAP (Mean Average Precision), PSNR (Peak Signal to Noise Ratio), IoU (Intersection over Unit). In the embodiment of the present disclosure, the server may preset a speed threshold, and for a neural network architecture in the target architecture population, if the operating speed of the neural network architecture is less than the speed threshold, the neural network architecture is discarded, and if the operating speed of the neural network architecture is greater than or equal to the speed threshold, the neural network architecture is retained; the server can also sequence the neural network architectures in the target architecture population from large to small according to the operation speed, and then take the first z neural network architectures with the operation speed. After the server selects the z neural network architectures, a required target neural network architecture can be selected from the z neural network architectures according to the service evaluation index and/or the floating point operand.

Step 309, deploying the target neural network architecture in the terminal.

In the embodiment of the disclosure, after the server selects the target neural network architecture, the neural network architecture is deployed in the terminal. Optionally, the server selects the target neural network architecture according to the performance of the deployed terminal, for example, if the target neural network architecture is applied to a terminal with lower performance, if it is required that the neural network architecture can also exert the same operation speed as that of the terminal with higher performance in the terminal with lower performance, the target neural network architecture with lower service evaluation index may be selected from z neural network architectures and applied to the terminal with lower performance. Optionally, the target neural network architecture selected by the server may be deployed in the terminal and used in the technical fields of image recognition, voice recognition, and the like, which is not limited in the embodiment of the present disclosure.

To sum up, according to the technical scheme provided by the embodiment of the present disclosure, the weighted congestion distance of each neural network architecture is calculated according to the congestion distance of each neural network architecture in each target in the individual group and the weight corresponding to each target, then the neural network architectures of the required number are selected from the individual group to generate the target architecture population according to the weighted congestion distance, and finally the target neural network architecture is selected from the target architecture population according to the preset index, so that a manner of selecting the neural network architecture is extended, the target neural network architecture meeting the application condition is selected from the target architecture population according to the preset index set by the decision maker, and the selected target neural network architecture is more suitable for the demand of the decision maker.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.

FIG. 4 is a block diagram illustrating a cluster generation apparatus according to an exemplary embodiment. The device has the functions of realizing the method examples, and the functions can be realized by hardware or by hardware executing corresponding software. The apparatus may be the computer device described above, or may be provided in a computer device. As shown in fig. 4, the apparatus 400 may include: the population obtaining module 410, the individual group generating module 420, the individual group selecting module 430, the weighted congestion distance calculating module 440, the individual selecting module 450, the population generating module 460 and the population determining module 470.

A population obtaining module 410 configured to obtain a t-th generation population R _tSaid population R _tIncluding a population P _tAnd a population Q _tSaid population Q _tIs said population P _tObtained after treatment, the population P _tAnd said population Q _tThe number of individuals contained in the formula (1) is n, t is a positive integer and the initial value of t is 1, and n is a positive integer.

An individual group generating module 420 configured to generate the population R _tThe individuals contained in the step (1) are subjected to non-dominated sorting to obtain k individual groups with different ranks, and k is a positive integer greater than 1.

And an individual group selecting module 430, configured to sequentially select i individual groups from the k individual groups according to the order from small to large, wherein the total number of individuals included in the i individual groups is greater than or equal to n, and the total number of individuals included in the i-1 individual groups is less than n.

A weighted crowding distance calculating module 440 configured to calculate, for a jth individual in the ith individual group, weighted crowding distances of the jth individual under multiple targets according to the crowding distance of the jth individual under each target and the weight corresponding to each target.

An individual selecting module 450 configured to select m individuals from the ith individual group according to the weighted crowding distance of each individual in the ith individual group, wherein m is a difference between n and a total number of individuals included in the i-1 individual group.

A population generation module 460 configured to generate a t +1 th generation population R _t+1Said population R _t+1Including a population P _t+1And a population Q _t+1Said population P _t+1Including said m individuals and individuals in said i-1 group of individuals, said population Q _t+1Is said population P _t+1Obtained after treatment, the population Q _t+1And said population P _t+1In which comprisesThe number of individuals of (A) is n.

A population determination module 470 configured to let t ═ t +1, and again from the pair of the populations R _tThe step of obtaining k individual groups with different ranks is started to be executed when the T generation population R is generated _TThen determining said population R _TAnd T is a preset value and is an integer greater than 1.

Optionally, as shown in fig. 5, the weighted congestion distance calculating module 440 includes: the individual sorting submodule 441 is configured to, for a target x in the multiple targets, sort each individual in the ith individual group according to a function value corresponding to the target x, where x is a positive integer; a crowding distance calculating sub-module 442 configured to calculate a crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and the maximum value and the minimum value in the sorting results; the weighted crowding distance calculating sub-module 443 is configured to calculate the weighted crowding distances of the jth individual under the multiple targets according to the crowding distance of the jth individual under the target x and the weight corresponding to the target x.

Optionally, as shown in fig. 5, the congestion distance calculation sub-module 443 is configured to: calculating a difference value of the function values of two adjacent individuals of the jth individual; calculating a difference between the maximum value and the minimum value; and dividing the difference value of the function values by the difference value of the maximum value and the minimum value to obtain the crowding distance of the j-th individual under the target x.

Optionally, as shown in fig. 5, the weighted congestion distance calculation sub-module 443 is configured to: multiplying the crowding distance of the jth individual under the target x by the weight corresponding to the target x; and accumulating the multiplication results of the jth individual and the multiple targets to obtain the weighted crowding distance of the jth individual under the multiple targets.

Optionally, as shown in fig. 5, the apparatus 400 further includes: a preset index obtaining module 480 configured to obtain preset indexes of the individuals in the target population; and the target individual selecting module 490 is configured to select a target individual from the target population according to the preset index.

FIG. 6 is a block diagram illustrating a selection device of a neural network architecture, in accordance with an exemplary embodiment. The device has the functions of realizing the method examples, and the functions can be realized by hardware or by hardware executing corresponding software. The apparatus may be the computer device described above, or may be provided in a computer device. As shown in fig. 6, the apparatus 600 may include: the system comprises an architecture population acquisition module 610, an individual group generation module 620, an individual group selection module 630, a weighted congestion distance calculation module 640, an individual selection module 650, an architecture population generation module 660, an architecture population determination module 670, a neural network architecture selection module 680 and a neural network architecture deployment module 690.

An architecture population acquisition module 610 configured to acquire a tth generation architecture population R _tSaid architecture population R _tIncluding an architecture populationP _tAnd architecture group Q _tSaid architecture group Q _tIs the architecture population P _tObtained after processing, the architecture population P _tAnd said architecture population Q _tThe number of the neural network architectures included in the method is n, t is a positive integer, the initial value of t is 1, and n is a positive integer.

An individual group generating module 620 configured to generate the architecture population R _tThe neural network architecture contained in the method carries out non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1.

An individual group selecting module 630, configured to sequentially select i individual groups from the k individual groups according to a descending order of the rank, where a total number of neural network architectures included in the i individual groups is greater than or equal to the n, and a total number of neural network architectures included in the i-1 individual groups is less than the n.

A weighted crowding distance calculation module 640 configured to calculate, for a jth neural network architecture in the ith individual group, weighted crowding distances of the jth neural network architecture under multiple targets according to the crowding distance of the jth neural network architecture under each target and a weight corresponding to each target.

An individual selecting module 650 configured to select m neural network architectures from the ith individual group according to the weighted crowding distance of each neural network architecture in the ith individual group, wherein m is a difference between n and a total number of neural network architectures included in the i-1 individual group.

An architecture population generation module 660 configured to generate a t +1 th generation architecture population R _t+1Said architecture population R _t+1Including an architecture group P _t+1And architecture group Q _t+1Said architecture population P _t+1Including the m neural network architectures and the neural network architectures in the i-1 individual groups, the architecture population Q _t+1Is the architecture population P _t+1Obtained after processing, the architecture population Q _t+1And the architecture population P _t+1The number of neural network architectures contained inThe amounts are all n.

An architecture population determination module 670 configured to let t ═ t +1, and again from the pair of architecture populations R _tThe neural network architecture contained in the method carries out non-dominated sorting, the step of obtaining k individual groups with different ranks is started to be executed, and when a T generation architecture population R is generated _TThen determining the architecture population R _TAnd T is a preset value and is an integer greater than 1, and is a target architecture population.

A neural network architecture selection module 680 configured to select a target neural network architecture from the target architecture population.

A neural network architecture deployment module 690 configured to deploy the target neural network architecture in a terminal.

Optionally, as shown in fig. 7, the neural network architecture selecting module 680 includes: a parameter index obtaining sub-module 681 configured to obtain a parameter index of each neural network architecture in the target architecture population; a neural network architecture selection submodule 682 configured to select the target neural network architecture from the target architecture population according to the parameter index.

Optionally, the neural network architecture selection sub-module 682 is configured to: selecting z neural network architectures from the target architecture population according to the operation speed, wherein z is a positive integer; and selecting the target neural network architecture from the z neural network architectures according to an evaluation index, wherein the evaluation index comprises a business evaluation index and/or a floating point operand.

An exemplary embodiment of the present disclosure also provides a cluster generation apparatus, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to:

obtaining the t generation population R _tSaid population R _tIncluding a population P _tAnd a population Q _tSaid population Q _tIs said population P _tObtained after treatment, the population P _tAnd said population Q _tThe number of individuals contained in the formula (I) is n, t is a positive integer, the initial value of t is 1, and n is a positive integer;

An exemplary embodiment of the present disclosure also provides a selecting apparatus of a neural network architecture, the apparatus including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to:

obtaining a t-th generation architecture population R _tSaid architecture population R _tIncluding an architecture group P _tAnd architecture group Q _tSaid architecture group Q _tIs the architecture population P _tObtained after processing, the architecture population P _tAnd said architecture population Q _tThe number of the neural network architectures contained in the method is n, t is a positive integer, the initial value of t is 1, and n is a positive integer;

let t be t +1 and again from the pair of the architecture populations R _tThe neural network architecture contained in the method carries out non-dominated sorting, the step of obtaining k individual groups with different ranks is started to be executed, and when a T generation architecture population R is generated _TThen determining the architecture population R _TThe target architecture population is shown, and T is a preset value and is an integer greater than 1;

deploying the target neural network architecture in a terminal.

FIG. 8 is a block diagram illustrating a computer device 800 according to an example embodiment. For example, the computer device 800 may be provided as a server. Referring to fig. 8, computer device 800 includes a processing component 822, which further includes one or more processors, and memory resources, represented by memory 832, for storing computer programs that are executable by processing component 822. The memory 832 stores the computer programs described above. Furthermore, the processing component 822 is configured to execute a computer program to implement the population generating method described above, or to implement the selecting method of the neural network architecture described above.

The computer device 800 may also include a power supply component 826 configured to perform power management of the computer device 800, a wired or wireless network interface 850 configured to connect the computer device 800 to a network, and an input/output (I/O) interface 858. Computer device 800 may operate based on an operating system stored in memory 832, such as Windows Server (TM), Mac OS XTM, Unix (TM), Linux (TM), FreeBSD (TM), or the like.

An exemplary embodiment of the present disclosure also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the population generating method as described above, or implements the steps of the selecting method of the neural network architecture as described above.

It should be understood that reference to "a plurality" herein means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A population generation method, comprising:

let t be t +1 and thenSecondary pair of said population R _tThe step of obtaining k individual groups with different ranks is started to be executed when the T generation population R is generated _TThen determining said population R _TAnd T is a preset value and is an integer greater than 1.

2. The method of claim 1, wherein said calculating weighted crowding distances for said jth individual at said plurality of destinations based on crowding distances for said jth individual at each destination and a weight corresponding to each destination comprises:

for a target x in the multiple targets, sorting each individual in the ith individual group according to a function value corresponding to the target x, wherein x is a positive integer;

calculating the crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and the maximum value and the minimum value in the sequencing results;

and calculating the weighted crowding distance of the jth individual under the plurality of targets according to the crowding distance of the jth individual under each target and the weight corresponding to each target.

3. The method of claim 2, wherein said calculating the crowding distance of the jth individual under the target x according to the function values of two adjacent ones of the jth individual and the maximum and minimum values in the ranking results comprises:

calculating a difference value of the function values of two adjacent individuals of the jth individual;

calculating a difference between the maximum value and the minimum value;

and dividing the difference value of the function values by the difference value of the maximum value and the minimum value to obtain the crowding distance of the j-th individual under the target x.

4. The method of claim 2, wherein said calculating weighted crowding distances for said jth individual at said plurality of destinations based on crowding distances for said jth individual at each of said destinations and weights corresponding to each of said destinations comprises:

multiplying the crowding distance of the jth individual under the target x by the weight corresponding to the target x;

and accumulating the multiplication results of the jth individual and the multiple targets to obtain the weighted crowding distance of the jth individual under the multiple targets.

5. The method of any one of claims 1 to 4, wherein said determining said population R _TAfter the target population is obtained, the method further comprises the following steps:

acquiring preset indexes of all individuals in the target population;

and selecting target individuals from the target population according to the preset index.

6. A method of selecting a neural network architecture, the method comprising:

deploying the target neural network architecture in a terminal.

7. The method of claim 6, wherein the selecting a target neural network architecture from the target architecture population comprises:

acquiring parameter indexes of each neural network architecture in the target architecture population;

and selecting the target neural network architecture from the target architecture population according to the parameter index.

8. The method of claim 7, wherein selecting a target neural network architecture from the target architecture population according to the parameter index comprises:

selecting z neural network architectures from the target architecture population according to the operation speed, wherein z is a positive integer;

and selecting the target neural network architecture from the z neural network architectures according to an evaluation index, wherein the evaluation index comprises a business evaluation index and/or a floating point operand.

9. A population generating device, the device comprising:

10. The apparatus of claim 9, wherein the weighted congestion distance calculation module comprises:

the individual sorting submodule is configured to, for a target x in the multiple targets, sort each individual in the ith individual group according to a function value corresponding to the target x, wherein x is a positive integer;

a crowding distance calculation sub-module configured to calculate a crowding distance of the jth individual under the target x according to the function values of two adjacent individuals of the jth individual and a maximum value and a minimum value in the sorting results;

and the weighted crowding distance calculation sub-module is configured to calculate weighted crowding distances of the jth individual under the multiple targets according to the crowding distance of the jth individual under the target x and the weight corresponding to the target x.

11. The apparatus of claim 10, wherein the congestion distance calculation sub-module is configured to:

calculating a difference between the maximum value and the minimum value;

12. The apparatus of claim 10, wherein the weighted congestion distance calculation sub-module is configured to:

13. The apparatus of any one of claims 9 to 12, further comprising:

the preset index acquisition module is configured to acquire preset indexes of all individuals in the target population;

and the target individual selecting module is configured to select a target individual from the target population according to the preset index.

14. An apparatus for selecting a neural network architecture, the apparatus comprising:

individualsA group generation module configured to generate the architecture population R _tThe neural network architecture contained in the method carries out non-dominated sorting to obtain k individual groups with different ranks, wherein k is a positive integer greater than 1;

an architecture population determination module configured to let t ═ t +1, and again from the pair of the architecture populations R _tThe neural network architecture contained in the method carries out non-dominated sorting, the step of obtaining k individual groups with different ranks is started to be executed, and when a T generation architecture population R is generated _TThen determining the architecture population R _TFor the target architecture population, T isThe preset value is an integer greater than 1;

15. The apparatus of claim 14, wherein the neural network architecture selection module comprises:

a parameter index obtaining submodule configured to obtain a parameter index of each neural network architecture in the target architecture population;

and the neural network architecture selecting submodule is configured to select the target neural network architecture from the target architecture population according to the parameter index.

16. The apparatus of claim 15, wherein the neural network architecture selection submodule is configured to:

17. A computer device comprising a processor and a memory, the memory having stored thereon a computer program which is loaded and executed by the processor to carry out the steps of the population generating method according to any one of claims 1 to 5 or the steps of the selecting method of the neural network architecture according to any one of claims 6 to 8.

18. A non-transitory computer readable storage medium, having stored thereon a computer program, wherein the computer program, when being executed by a processor, is adapted to carry out the steps of the population generating method according to any one of claims 1 to 5, or the steps of the selecting method of the neural network architecture according to any one of claims 6 to 8.