WO2022030669A1

WO2022030669A1 - Query-based deep learning inference system and method therefor

Info

Publication number: WO2022030669A1
Application number: PCT/KR2020/010600
Authority: WO
Inventors: 이준혁
Original assignee: ㈜한국플랫폼서비스기술
Priority date: 2020-08-03
Filing date: 2020-08-11
Publication date: 2022-02-10
Also published as: KR102491755B1; KR20220016588A

Abstract

The present invention discloses a query-based deep learning inference system and method therefor, wherein a deep learning framework is connected to an information database, in a plugin form, such that data stored in the information database is learned via a deep learning method according to a request query of a user, thereby inferring data corresponding to a query. The disclosed query-based deep learning inference system may include: a database for storing a data set, a learning network model, a learning parameter, and a learning result; the deep learning framework connected to the database, in a plugin form, identifying and modifying information or data stored in the database, and adding new data; and a user terminal for inputting a query through the deep learning framework and receiving an inference result corresponding to the query from the database through the deep learning framework.

Description

Query-based deep learning inference system and method therefor

The present invention relates to a query-based deep learning inference system and a method therefor, and more particularly, a deep learning framework in the form of a plug-in to an information database so that even users without professional knowledge on deep learning can provide necessary information to users without difficulty It relates to a query-based deep learning inference system and a method for inferring data corresponding to the query by learning the data stored in the information database by a user's request query in a deep learning manner.

Recently, as deep learning technology has been in the spotlight, a learning engine based on deep learning technology is being used to provide intelligent functions in various fields such as security, control, autonomous driving, and crime prevention.

The learning engine using deep learning shows significantly superior intelligence performance than the learning engine based on other existing AI technologies.

However, in order to create a learning engine that provides intelligence based on deep learning technology, there are various difficulties such as deep network design, learning function setting, and parameter tuning. These problems cannot be easily done without a deep learning expert, so it is difficult for anyone to easily have a deep learning-based learning engine.

Also, whenever a learning engine is created, common elements of deep learning are used repeatedly, so there is a problem that the same process must be repeated.

It is an object of the present invention to solve the above-mentioned problems, that the deep learning framework is connected to the information database in the form of a plug-in so that even users without professional knowledge on deep learning can provide necessary information to the user without difficulty. An object of the present invention is to provide a query-based deep learning inference system and a method for inferring data corresponding to a query by learning data stored in an information database by a request query in a deep learning method.

Query-based deep learning inference system according to an embodiment of the present invention for achieving the above object, a database for storing a data set, a learning network model, learning parameters and learning results; a deep learning framework connected to the database in a plug-in manner, checking, correcting, and adding new data to information or data stored in the database; and a user terminal that inputs a query through the deep learning framework and receives an inference result corresponding to the query through the deep learning framework from the database.

The deep learning framework, upon receiving the query, generates a learning network model for checking, modifying, and new learning of the learning network model stored in the database, and according to the input query, information or data and a learning network Execute machine learning by selecting a model and setting learning parameters, providing an intermediate learning result and a final result, select data and a pre-trained learning network model through the input query to execute machine inference, and the inference can provide results.

The data set is a set of information or data having the same format, and the information or data may be any type of information or data used in machine learning, including numbers, text, images, images, and audio.

The learning network model is a model used for machine learning, and is composed of input/output and parameters defining the inside of the model, and parameters necessary for machine learning and inference, and is stored in the database in a relational data format, and other deep learning through a converter It may be convertible into a framework.

The database may store all input/output data used for machine learning and machine inference, store models used for machine learning and machine inference, and provide a procedure corresponding to a user's query request.

The procedure is, Insert Network, Insert Layer, Make Project, Input Data Loader, Train, Save Model, and Test ) may be included.

The deep learning framework is used for compatibility with external frameworks and includes ONNX, NNEF and learning parameter bias when importing a pre-trained model of an existing framework or exporting information or data from the database to the outside. It can include a model converter that uses the file in a structured format.

The model converter may convert a network structure and model data defined in the model format into a network model table format of the database, or vice versa, convert a network model of the database into the model format have.

The database may include a dataset table, a network table, a project table, a job table, and a common table.

The deep learning framework executes, when a learning query is input from the user terminal (Call Train), network initialization (Init Network), network configuration (Construct Network), and network update (Update Network), initialization for all layers When (Initialize all layers) is done, training is executed, and batch data is obtained until the end of training (Get Batch Data), and the result and model are stored by iteration (Store Result & Model), and training is completed when training is finished. A result may be provided to the user terminal.

When an inference query is input from the user terminal (Call Test), the deep learning framework executes network initialization (Init Network), network configuration (Construct Network), and network update (Update Network), and initialization for all layers When (Initialize all layers) is made, the test is executed, the test data is obtained (Get Test Data), the feedforward (feedforward), and the result is stored (Store Result), and the inference result is provided to the user terminal. can

On the other hand, the query-based deep learning inference method according to an embodiment of the present invention for achieving the above object is a query-based deep learning inference method of a deep learning framework interworking with a user terminal and a database, (a) the deep learning receiving, by the framework, a learning query (Call Train) or an inference query (Call Test) from the user terminal; (b) executing, by the deep learning framework, a network initialization (Init Network), a network configuration (Construct Network) and a network update (Update Network) according to the learning query or the inference query; (c) executing training or inference (Test) when the deep learning framework is initialized for all layers; and (d) providing, by the deep learning framework, a learning result or an inference result to the user terminal at the end of the learning or the inference.

In step (c), the deep learning framework may obtain batch data (Get Batch Data) and iterate until the end of the learning and store the results and model (Store Result & Model).

In step (c), the deep learning framework may execute the test, obtain test data (Get Test Data), feedforward, and store the inference result (Store Result).

When the deep learning framework in step (a) uses a model converter for compatibility with external frameworks, imports a pre-trained model of an existing framework, or exports information or data from the database to the outside It can be converted into a model format through the model converter.

According to the present invention, by using the query-based machine learning technology, the deep learning framework is connected to the database in the form of a plug-in, and machine learning, inference, etc. can be performed using data stored in the database according to a user's request query.

Therefore, even a user without professional knowledge on deep learning can easily provide necessary information without difficulty.

In addition, it is possible to check the learning parameters of the currently executing or waiting learning plan, and check the middle and results of the currently executing learning plan.

Also, you can stop the currently running learning plan and start a waiting learning plan.

In addition, by setting the registered network model and dataset, an inference plan can be created, and the result of the executed inference plan can be checked.

1 is a configuration diagram schematically showing the overall configuration of a query-based deep learning inference system according to an embodiment of the present invention.

2 is a flowchart illustrating an execution flow of a query-based machine learning technique according to an embodiment of the present invention.

3 is a diagram illustrating an internal data flow of a database according to an embodiment of the present invention.

4 is a diagram illustrating an operation flowchart for explaining a query-based deep learning inference method according to an embodiment of the present invention.

5 is a diagram illustrating an execution flow of a learning procedure according to an embodiment of the present invention.

6 is a diagram illustrating an execution flow of an inference procedure according to an embodiment of the present invention.

7 is a diagram illustrating a conversion operation of a model converter according to an embodiment of the present invention.

8 is a diagram schematically illustrating an internal structure of a QML framework according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings, the embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them. The present invention may be implemented in several different forms and is not limited to the embodiments described herein.

In order to clearly explain the present invention, parts irrelevant to the description are omitted, and the same reference numerals are assigned to the same or similar components throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated.

When a part is referred to as being “above” another part, it may be directly on the other part, or the other part may be involved in between. In contrast, when a part refers to being "directly above" another part, no other part is involved in between.

The terms first, second and third etc. are used to describe, but are not limited to, various parts, components, regions, layers and/or sections. These terms are used only to distinguish one part, component, region, layer or section from another part, component, region, layer or section. Accordingly, a first part, component, region, layer or section described below may be referred to as a second part, component, region, layer or section without departing from the scope of the present invention.

The terminology used herein is for the purpose of referring to specific embodiments only, and is not intended to limit the present invention. As used herein, the singular forms also include the plural forms unless the phrases clearly indicate the opposite. The meaning of "comprising," as used herein, specifies a particular characteristic, region, integer, step, operation, element and/or component, and includes the presence or absence of another characteristic, region, integer, step, operation, element and/or component. It does not exclude additions.

Terms indicating a relative space such as “below” and “above” may be used to more easily describe the relationship of one part shown in the drawing to another part. These terms, along with their intended meanings in the drawings, are intended to include other meanings or operations of the device in use. For example, if the device in the drawings is turned over, some parts described as being "below" other parts are described as being "above" other parts. Thus, the exemplary term “down” includes both the up and down directions. The device may be rotated 90 degrees or at other angles, and terms denoting relative space are to be interpreted accordingly.

Although not defined otherwise, all terms including technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention belongs. Commonly used terms defined in the dictionary are additionally interpreted as having a meaning consistent with the related technical literature and the presently disclosed content, and unless defined, are not interpreted in an ideal or very formal meaning.

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art can easily implement them. However, the present invention may be implemented in several different forms and is not limited to the embodiments described herein.

Referring to FIG. 1 , the query-based deep learning inference system 100 according to an embodiment of the present invention includes a database (DB, 110) and a deep learning framework (QML, 120) to apply a query-based machine learning technology. ) and a user terminal 130 .

Here, in the query-based machine learning technology, the deep learning framework 120 is connected to the database 110 in the form of a plug-in, and machine learning, inference, etc. are performed using data stored in the database 110 by a user's request query. It is a technique that is performed

The database 110 may store a data set, a learning network model, a learning parameter, and a learning result.

A data set is a set of information or data having the same format. Information or data may be any kind of information or data used in machine learning, including numbers, text, images, images, and voices.

A learning network model is a model used for machine learning, and it consists of input/output and parameters defining the inside of the model, and parameters necessary for machine learning and inference, and is stored in a database in a relational data format, and other deep learning frameworks through a converter may be converted into

The learning network model may recognize text input by a user, and may recognize voice and text included in images, audio and video. In addition, user intention can be analyzed from the recognized voice and text.

As for the learning result, the intermediate output value is stored in the database 110 while the machine learning is in progress so that the user can check it. During machine learning, the model parameter values are stored in the database 110 so that the user can check them. The evaluation index value of the model calculated while the machine learning is in progress is stored in the database 110 so that the user can check it. The machine reasoning result value is stored in the database 110 so that the user can check it.

The database 110 may store all input/output data used for machine learning and machine inference, store models used for machine learning and machine inference, and provide a procedure corresponding to a user's query request. . Procedures are: Insert Network, Insert Layer, Make Project, Input Data Loader, Train, Save Model and Test may include

The deep learning framework 120 is used for compatibility with external frameworks and when importing a pre-trained model of an existing framework or exporting information or data from the database to the outside, ONNX (Open Neural Network Exchange) model format It may include a model converter that is used.

The model converter may convert the network structure and model data defined in the ONNX model format into the network model table format of the database, or convert the network model of the database into the ONNX model format on the contrary.

In addition to the ONNX model format, it is also possible to convert Open Network Exchange (ONNX), Neural Network Exchange Format (NNEF), and a model weight file including training parameters and bias into a structured format.

By converting the above and the model Weigh file into a structured format, the learning model can be imported or outputted from the database.

The deep learning framework 120 is connected to the database 110 in a plug-in manner, and can check, correct, and add new data to information or data stored in the database 110 . The deep learning framework 120 may be, for example, QML.

QML is a deep learning framework installed as a plug-in in the database 110 and is executed by calling the database. When QML is called, it receives various data from the database 110 as an argument and returns an execution result. QML interprets the network model defined in the relational data format to construct the network inside the framework. QML receives learning parameters and learning data from the database 110 as factors, performs learning of the network configured in the framework, and returns a learning result. QML receives input data from the database 110 as an argument, performs machine inference using the network configured inside the framework, and returns a result.

In addition, when receiving a query from the user terminal 130, the deep learning framework 120 generates a learning network model for checking, modifying, and new learning for the learning network model stored in the database 110, and input Select information or data and a learning network model according to the query, set learning parameters, execute machine learning, provide intermediate and final results of learning, and select data and pre-trained learning network model through the input query Thus, machine reasoning can be performed and the inference result can be provided.

The user terminal 130 may input a query through the deep learning framework 120 and receive an inference result corresponding to the query from the database 110 through the deep learning framework 120 .

Also, the user terminal 130 requests various functions from the database 110 through a query, and receives a response from the database 110 . The user terminal 130 checks and corrects data stored in the database 110 through a query, and adds new data. The user terminal 130 checks and corrects the network model stored in the database 110 through a query, and creates a network model for new learning. The user terminal 130 selects data and a learning network model through a query, sets learning parameters, requests machine learning, and checks the intermediate and final results of learning. The user terminal 130 selects data and a pre-learned network model through a query, requests machine inference, and confirms the inference result.

Referring to FIG. 2 , the query-based machine learning technology according to an embodiment of the present invention stores a pre-learned model converted into ONNX format in QML format through a converter, and queries learning or inference from the user terminal 130 . is input, and the database 110 provides information as QML to perform learning and inference. And, when the learning or inference result is stored in the database 110 , the user terminal 130 checks the result stored in the database 110 .

First, the user terminal 130 may input (Import) the learning model or receive an output (Export) from the database 110 (①).

In addition, when inputting or outputting the learning model, it is converted according to the schema structure of the database 110 through the model converter (②).

In addition, the database 110 interprets the query and performs an appropriate operation (③).

In addition, the deep learning framework 120 performs a plug-in to the database 110, and performs learning and inference through the information received from the database 110 (④).

Also, the user terminal 130 may request learning or inference from the database 110 through a query (⑤).

In addition, the user terminal 130 may inquire the table of the database 110 to inquire the learning-related information (⑥).

Then, the model data is stored in the database 110 as a QML schema (⑦).

Referring to FIG. 3 , the database 110 according to an embodiment of the present invention stores data related to machine learning, provides functions necessary for machine learning as a procedure, and performs machine learning according to a user's request. do.

In the database 110 , the table may largely include a dataset table, a network table, a project table, a job table, and a common table. can

A data set includes a data type, a network includes a network type, and a lenet, and the project performs learning or inference work by copying information from the network. The work table includes user information, project status, log, and the like, and the common table includes lookup tables such as layer types and error codes.

Network model information is stored in the network table, and project information for actual learning or inference copied from the network table is stored in the project table. After the project is created, it has a configuration separate from the network table, so even if the underlying network used in the project is modified, it has no effect. A large number of variable data (input/output data and weight information) is a blob or text type, and a small number of variable data (each layer parameter, etc.) is divided and stored in records.

The procedures required for machine learning are Insert Network, Insert Layer, Make Project, Input Data Loader, Init Network, Train, It can include Save Model and Test.

The insert network creates a network including the network name, network type, dataset name, optimizer type, optimizer parameter, learning rate, batch size, number of trainings, and output layer index.

The insert layer registers a layer including a network ID, a layer name, a layer type, a layer index, a layer parameter, and an input layer index.

The make project creates a project containing the project name, dataset name, network name, training or inference flags, and number of GPUs.

The input data loader inputs a query according to the selection of the network input (layer index, query type (2: training table, 0: training data, 4: validation table, 3: validation data)).

Network initialization constitutes a network model.

The train starts learning, including project ID, number of learning generations, batch size, followed by whether or not to learn, save interval, verification interval, and GPU synchronization interval.

To save the model, the network information of the project table is copied to the network table (project name, network name).

The test starts an inference that includes the project ID and a flag whether to save the results of all layers.

Referring to FIG. 4 , the query-based deep learning inference system 100 according to an embodiment of the present invention is a query-based deep learning inference in the deep learning framework 120 interworking with the user terminal 130 and the database 110 . run the method

The deep learning framework 120 receives a learning query (Call Train) or an inference query (Call Test) from the user terminal (S410).

At this time, the deep learning framework 120 uses a model converter for compatibility with an external framework, imports a pre-trained model of an existing framework, or uses a model converter when exporting information or data from a database to the outside. It can be converted to ONNX model format through

Next, the deep learning framework 120 executes a network initialization (Init Network), a network configuration (Construct Network), and a network update (Update Network) according to a learning query or an inference query ( S420 ).

Next, the deep learning framework 120 executes training or inference when initialization of all layers is performed (S430).

In this case, the deep learning framework 120 may obtain batch data (Get Batch Data) and iterate until the end of learning and store the results and model (Store Result & Model).

Also, the deep learning framework 120 may execute a test, obtain test data (Get Test Data), feedforward, and store an inference result (Store Result).

Next, the deep learning framework 120 provides a learning result or an inference result to the user terminal 130 when learning or inference is terminated ( S440 ).

The above-described learning or reasoning process will be separately described below.

Referring to FIG. 5 , in the deep learning framework 120 according to an embodiment of the present invention, the following steps are executed for a user's learning request, and the database 110 calls QML 120 to print data. to return the result.

First, the deep learning framework 120, when a learning query is input from the user terminal 130 and learning is called (Call Train) (S50), network initialization (Init Network) (S51), network configuration (Construct Network) (S52), a network update (Update Network) (S53) is executed.

In addition, the deep learning framework 120 executes the initialization of the layer (Init Layer) (S55) until the initialization (Initialize all layers) for all layers is made (S54-No), and the initialized layer information (Initialized) Layer Info) is acquired, and a layer update (Update Layer) ( S56 ) is executed.

In addition, the deep learning framework 120, when initialization for all layers is made (S54-Yes), executes training (S57), and until the end of learning (S58-No) acquires batch data ( Get Batch Data) (S59), iteration is performed (S60), the result and model are stored (Store Result & Model) (S610), and the learning result is sent to the user terminal 130 at the end of learning (S58-Yes) provided (S62).

Referring to FIG. 6 , in the deep learning framework 120 according to an embodiment of the present invention, the following steps are executed for a user's inference request, and the database 110 calls QML 120 to print data. to return the result.

First, the deep learning framework 120, when an inference query is input from the user terminal 130 and inference is called (Call Test) (S63), network initialization (Init Network) (S64), network configuration (Construct Network) (S65), a network update (Update Network) (S66) is executed.

In addition, the deep learning framework 120, until initialization (Initialize all layers) for all layers is made (S67-No), layer initialization (Init Layer) (S68) and layer update (Update Layer) (S69) run

In addition, the deep learning framework 120, when initialization for all layers is made (S67-Yes), executes an inference test (Test) (S70), and obtains inference data (Get Test Data) (S71) Feed forward (S72), store the result (Store Result) (S73), and provide the inference result to the user terminal 130 (S74).

Referring to FIG. 7 , the network model stored in the database 110 according to an embodiment of the present invention requires a model converter for compatibility with external frameworks (tensorflow, pytorch, caffe, etc.). The ONNX (Open Neural Network Exchange) format is used when importing pre-trained models of existing frameworks or exporting them to the outside of the database.

Here, in addition to ONNX, Open Network Exchange (ONNX), Neural Network Exchange Format (NNEF), and a model weight file including training parameters and biases may be converted into a structured format.

The model converter converts the network structure and model data (weight, bias) defined in the structured format including the ONNX model into the network model table format of the database 110 (a). Conversely, the network model of the database 110 is converted into a structured format including the ONNX model (b).

The machine-learning model in the existing framework (Caffe, tensorflow, pytorch, etc.) can be uploaded to the database 110 through the Converter (Import) function after the user converts it to a saved format including the ONNX model.

The model learned in the QML 120 is stored in a structured format including the ONNX model in the database 110 or a CVS file through the Converter (Export) function.

The ONNX model and structured format stored in the database 110 can be converted into a target framework desired by the user and used.

On the other hand, QML is a deep learning framework 120 being developed in C language. It is connected to the database 110 through a User Defined Function (UDF) and is executed by a call. The functions defined in the deep learning framework 120 are registered in the database 110 through the UDF, and the deep learning framework 120 is executed through the registered UDF call. The types of argument variables that can be used in UDF are defined as integer, real number, and string. In QML, they are used as follows. Integer is an integer value among the essential parameters constituting the network model, and the address value of the structure memory defined inside QML. Real number is a real value among essential parameters constituting the network model. String is a variable number of parameters and blob data (binary data).

The QML framework follows the channel-first data format, NCHW (N:batch, C: channel, H:height, W:width) format. The layer type supports the layers used in ONNX, and the parameters defined in each layer also follow the structured format including the ONNX format.

In the QML framework, a backpropagation algorithm is implemented so that the network model can be learned. A gradient calculation algorithm, which is an essential element of backpropagation, and an optimization algorithm for updating model parameters (weight, bias) are implemented. There are two ways to learn a network model: Train from scratch and fine tuning are supported. Train from scratch trains a network model from scratch. The weights of each layer are determined through a weight initialization algorithm. Fine tuning reads the weights of the pre-learned model (the weights stored in the database through the import function or obtained through previous learning attempts) to set the initial weights of the layers and perform learning.

Referring to FIG. 8 , in the deep learning framework 120 according to an embodiment of the present invention, QML_network_t(qml_network_t) is composed of a plurality of QML_layers_t(qml_network_t), and one QML_layer _t(qmll_network_t) is composed of a plurality of QML_tensor_t(qml_tensor_t).

Object qml_networks_t holds qml_network_t, N qml_network_t is included in qml_networks_t when learning a network model with multi GPU, and holds 1 qml_network_t when inferring a network model.

Object qml_network_t holds several qml_layer_t and network parameters.

Object qml_layer_t has input/output tensors (qml_tensor_t), Object qml_tensor_t is a 4D tensor composed of NCHW format, and contains dtype, qml_shape_t, data, name, etc.

Meanwhile, the query-based deep learning inference system 100 according to an embodiment of the present invention may manage clients, members, datasets, networks, learning, learning execution, and the like as follows.

[Client]

The query-based deep learning inference system 100 according to an embodiment of the present invention provides a function to manage the dataset and the machine learning process with the user terminal 130 and to check the results.

[Member Management]

In addition, the query-based deep learning inference system 100 grants the right to create and modify the data of the database 110 and the network model through member management and leave a change history.

[Dataset Management]

In addition, the query-based deep learning inference system 100 creates a new table to manage the dataset, and provides functions for querying, modifying, and uploading data. When creating a new dataset, a new table is automatically created and data is uploaded. Shows the results of querying data by accessing a table in the database or searching for data in the database through a user-written query. Modify data according to authority. Numerical data is input from the user or data is uploaded by reading one or more files. Provides a function for tagging training data.

[Network Management]

In addition, the query-based deep learning inference system 100 provides a function for managing the network model as follows. Add supported layers and adjust layer parameters to create new network models. Retrieves the list of previously created network models. A new network model is created by adding a new layer to the previously created network model. It provides a function to visualize and show the network model.

[Learning Management]

In addition, the query-based deep learning inference system 100 provides a function for managing learning as follows. Create or modify training by adjusting network models, datasets, and training parameters. The trained network model is output through the converter function. Check the resources of the server currently in use.

[Manage Learning Execution]

In addition, the query-based deep learning inference system 100 provides a function for performing learning and inference and confirming the result as follows. Check the server's resources. It informs the user whether learning and inference can be performed. Inquires the list of currently executed or pending learning plans. Create a learning plan by setting the registered network model, dataset, and learning parameters. You can check the learning parameters of the currently running or waiting learning plan. You can check the middle and results of the currently running learning plan. You can stop the currently running learning plan. You can start a pending study plan. Create an inference plan by setting the registered network model and dataset. You can check the result of the executed reasoning plan.

As described above, according to the present invention, the deep learning framework is connected to the information database in the form of a plug-in so that even users without professional knowledge on deep learning can provide necessary information to the user without difficulty, It is possible to realize a query-based deep learning inference system and a method for inferring data corresponding to a query by learning the data stored in the information database in a deep learning method.

Those skilled in the art to which the present invention pertains should understand that the present invention can be embodied in other specific forms without changing the technical spirit or essential characteristics thereof, so the embodiments described above are illustrative in all respects and not restrictive. only do The scope of the present invention is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. .

100: Query-based deep learning inference system

110: database

120: deep learning framework

130: user terminal

Claims

a database for storing data sets, training network models, training parameters, and training results;

a deep learning framework connected to the database in a plug-in manner, checking, correcting, and adding new data to information or data stored in the database; and

A user terminal that inputs a query through the deep learning framework and receives an inference result corresponding to the query from the database through the deep learning framework; includes,

The deep learning framework, upon receiving the query, generates a learning network model for checking, modifying, and new learning of the learning network model stored in the database, and according to the input query, information or data and a learning network Select a model and set learning parameters to execute machine learning, provide an intermediate learning result and a final result, select data and a pre-trained learning network model through the input query, and execute machine inference, and the inference A query-based deep learning inference system that provides results.
The method of claim 1,

The data set is a set of information or data having the same format, and the information or data is any kind of information or data used in machine learning, including numbers, text, images, images, and voices, based on query-based deep learning inference. system.
The method of claim 1,

The learning network model is a model used for machine learning, and is composed of input/output and parameters defining the inside of the model, and parameters necessary for machine learning and inference, and is stored in the database in a relational data format, and other deep learning through a converter A query-based deep learning inference system that can be converted into a framework.
The method of claim 1,

The database stores all input/output data used for machine learning and machine inference, stores models used for machine learning and machine inference, and provides a procedure corresponding to a user's query request, a query-based deep Learning inference system.
5. The method of claim 4,

The procedure is, Insert Network, Insert Layer, Make Project, Input Data Loader, Train, Save Model, and Test ), including a query-based deep learning inference system.
The method of claim 1,

The deep learning framework is

Used for compatibility with external frameworks, when importing a pre-trained model of an existing framework or exporting information or data from the database, a model weight file including ONNX, NNEF, and training parameter bias in a structured format model converter to use;

A query-based deep learning inference system that includes
7. The method of claim 6,

The model converter uses a model weight file including the ONNX, NNEF, and training parameter bias in a structured format, a network structure defined in a model format and model data, and a network model table of the database. A query-based deep learning inference system that converts to a format or, conversely, converts the network model of the database into the structured model format.
The method of claim 1,

The database, including a dataset table (Dataset Table), network table (Network Table), project table (Project Table), work table (Job Table), common table (Common Table), query-based deep learning inference system.
The method of claim 1,

The deep learning framework executes, when a learning query is input from the user terminal (Call Train), network initialization (Init Network), network configuration (Construct Network), and network update (Update Network), initialization for all layers When (Initialize all layers) is done, training is executed, and batch data is obtained until the end of training (Get Batch Data), and the result and model are stored by iteration (Store Result & Model), and training is completed when training is finished. A query-based deep learning inference system that provides a result to the user terminal.
The method of claim 1,

When an inference query is input from the user terminal (Call Test), the deep learning framework executes network initialization (Init Network), network configuration (Construct Network), and network update (Update Network), and initialization for all layers When (Initialize all layers) is done, the reasoning test is executed, the test data is obtained (Get Test Data), the feedforward is performed and the result is stored (Store Result), and the inference result is provided to the user terminal. Query-based deep learning inference system.
As a query-based deep learning inference method of a deep learning framework that works with user terminals and databases,

(a) receiving, by the deep learning framework, a learning query (Call Train) or an inference query (Call Test) from the user terminal;

(b) executing, by the deep learning framework, a network initialization (Init Network), a network configuration (Construct Network) and a network update (Update Network) according to the learning query or the inference query;

(c) executing training or inference (Test) when the deep learning framework is initialized for all layers; and

(d) providing, by the deep learning framework, a learning result or an inference result to the user terminal at the end of the learning or the inference;

A query-based deep learning inference method comprising
The method of claim 1,

In step (c), the deep learning framework acquires batch data until the end of the learning (Get Batch Data) and stores the result and model by iteration (Store Result & Model), query-based deep learning inference Way.
The method of claim 1,

In the step (c), the deep learning framework executes the inference test (Test), obtains test data (Get Test Data), feeds forward, and stores the inference result (Store Result), a query based deep learning inference method.
12. The method of claim 11,

When the deep learning framework in step (a) uses a model converter for compatibility with an external framework, imports a pre-trained model of an existing framework, or exports information or data from the database to the outside A query-based deep learning inference method for converting a model weight file including ONNX, NNEF, and training parameter bias into a structured format through the model converter.
15. The method of claim 14,

The model converter converts a network structure and model data defined in the structured format into a network model table format of the database, or vice versa, converts a network model of the database into the structured model format Transforming, query-based deep learning inference method.