CN113780444A - Tongue fur image classification model training method based on progressive learning - Google Patents
Tongue fur image classification model training method based on progressive learning Download PDFInfo
- Publication number
- CN113780444A CN113780444A CN202111086464.5A CN202111086464A CN113780444A CN 113780444 A CN113780444 A CN 113780444A CN 202111086464 A CN202111086464 A CN 202111086464A CN 113780444 A CN113780444 A CN 113780444A
- Authority
- CN
- China
- Prior art keywords
- target
- resolution
- classification model
- tongue
- image classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a tongue fur image classification model training method based on progressive learning, which comprises the following steps: acquiring an original training data set at least comprising a plurality of tongue fur images; determining a target resolution set according to a preset resolution amplification mode of progressive learning; determining a regularized strength value set according to a preset regularized strength amplification mode of progressive learning; executing preset resolution resetting operation on each tongue fur image in the original training data set to obtain a target training data set; and training the preset tongue fur image classification model for multiple times based on the target training data set and the regularization strength value set. Therefore, the method can be used for training the tongue fur image classification model with different resolutions by using different regularization strengths, so that the training speed of the tongue fur image classification model can be increased, and the classification accuracy of the trained tongue fur image classification model can be improved. The invention can be applied to digital medical systems.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for training a tongue fur image classification model based on progressive learning, computer equipment and a storage medium.
Background
With the rapid development of deep learning and artificial intelligence, the tongue fur image classification algorithm based on the convolutional neural network is used to assist the user in classifying tongue fur images. According to the technical characteristics of the artificial neural network, the classification accuracy of the tongue fur image classification model is influenced to a certain extent by the training process of the tongue fur image classification model. In the existing research, in order to improve the classification accuracy of the tongue fur image classification model, people try to improve the training effect of the tongue fur image classification model by increasing the resolution of the tongue fur image in the training data, so as to improve the classification accuracy of the tongue fur image classification model. However, it has been found in practice that, in this method, after the resolution of the tongue coating image is increased to a certain degree, the classification accuracy is rather likely to be lowered. Therefore, how to scientifically and effectively train the tongue fur image classification model to improve the classification accuracy of the tongue fur image classification model is a technical problem which needs to be solved urgently.
Disclosure of Invention
The invention aims to solve the technical problem that the classification accuracy of the tongue fur image classification model is lower in the conventional tongue fur image classification model training method.
In order to solve the technical problem, a first aspect of the present invention discloses a method for training a tongue fur image classification model based on progressive learning, the method comprising:
acquiring a target video to be processed;
performing dynamic target detection on the target video based on a preset dynamic target detection model to obtain a dynamic target area, a non-dynamic target area and depth information corresponding to the dynamic target area in the target video;
determining an image insertion area of the target video according to the dynamic target area and the non-dynamic target area;
determining target depth information corresponding to an image insertion area of the target video according to the depth information corresponding to the dynamic target area;
and inserting the predetermined advertisement image into a position corresponding to the target depth information in the image insertion area of the target video to complete the processing of the target video.
The invention discloses a device for training a tongue fur image classification model based on progressive learning in a second aspect, which comprises:
the acquisition module is used for acquiring a target video to be processed;
the detection module is used for carrying out dynamic target detection on the target video based on a preset dynamic target detection model to obtain a dynamic target area, a non-dynamic target area and depth information corresponding to the dynamic target area in the target video;
the determining module is used for determining an image inserting area of the target video according to the dynamic target area and the non-dynamic target area;
the determining module is further configured to determine, according to the depth information corresponding to the dynamic target area, target depth information corresponding to an image insertion area of the target video;
and the inserting module is used for inserting the predetermined advertisement image into the position corresponding to the target depth information in the image inserting area of the target video so as to finish the processing of the target video.
A third aspect of the present invention discloses a computer apparatus, comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program code stored in the memory to execute part or all of the steps of the training method of the tongue fur image classification model based on progressive learning disclosed by the first aspect of the invention.
In a fourth aspect, the present invention discloses a computer storage medium storing computer instructions for performing some or all of the steps of the method for training a tongue image classification model based on progressive learning disclosed in the first aspect of the present invention when the computer instructions are invoked.
In the embodiment of the invention, an original training data set comprising a plurality of tongue fur images is obtained, a target resolution set is determined according to a preset progressive learning resolution amplification mode, a regularization intensity value set corresponding to the target resolution set is determined according to a preset progressive learning regularization intensity amplification mode, each tongue fur image in the original training data set is subjected to preset resolution resetting operation to obtain a target training data set, and finally, a preset tongue fur image classification model is subjected to multiple times of training based on the target training data set and the regularization intensity value set to enable a target loss function of the tongue fur image classification model to be converged so as to finish training of the tongue fur image classification model. The method comprises the steps of determining a target resolution set and a regularization strength value set corresponding to the target resolution set in advance, resetting the resolutions of a plurality of tongue fur images in an original training data set to the target resolution in the target resolution set to form a target training data set comprising tongue fur images with various resolutions, and therefore, when a tongue fur image classification model is trained, training of the model can be carried out on tongue fur images with different resolutions by using different regularization strengths, the training speed of the tongue fur image classification model can be increased, and the classification accuracy of the trained tongue fur image classification model is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flowchart of a tongue fur image classification model training method based on progressive learning according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a training apparatus for a tongue coating image classification model based on progressive learning according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention discloses a method, a device, computer equipment and a storage medium for training a tongue fur image classification model based on progressive learning, wherein an original training data set comprising a plurality of tongue fur images is obtained, a target resolution set is determined according to a preset resolution amplification mode of progressive learning, a regularized intensity value set corresponding to the target resolution set is determined according to a preset regularized intensity amplification mode of progressive learning, preset resolution resetting operation is performed on each tongue fur image in the original training data set to obtain a target training data set, and finally, the preset tongue fur image classification model is trained for multiple times based on the target training data set and the regularized intensity value set, so that a target loss function of the tongue fur image classification model is converged to finish training the tongue fur image classification model. The method comprises the steps of determining a target resolution set and a regularization strength value set corresponding to the target resolution set in advance, resetting the resolutions of a plurality of tongue fur images in an original training data set to the target resolution in the target resolution set to form a target training data set comprising tongue fur images with various resolutions, and therefore, when a tongue fur image classification model is trained, training of the model can be carried out on tongue fur images with different resolutions by using different regularization strengths, the training speed of the tongue fur image classification model can be increased, and the classification accuracy of the trained tongue fur image classification model is improved. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a flowchart illustrating a tongue fur image classification model training method based on progressive learning according to an embodiment of the present invention. As shown in fig. 1, the method for training the tongue coating image classification model based on progressive learning may include the following operations:
101. an original training data set comprising at least a plurality of images of the tongue coating is acquired.
In the step 101, the original training data set may include a plurality of images (i.e., tongue coating images) of the human tongue coating, and each tongue coating image may have a corresponding label, where the label is used to classify the tongue coating image into four types, i.e., normal tongue coating, peeled tongue coating, little tongue coating, and no tongue coating. The label of each tongue fur image can be manually set. Alternatively, the tongue image in the original training data set may be acquired on a digital medical system of a hospital, and a tongue image library may be provided in the digital medical system for storing tongue images uploaded by respective image acquisition terminals in the digital medical system.
102. And determining a target resolution set according to a preset resolution amplification mode of progressive learning.
In step 102, the progressive learning strategy is a model training strategy for training the tongue image classification model by using tongue images with gradually increased resolutions. Specifically, the tongue image classification model is trained over and over again, and the resolution of the tongue image used in each training is gradually increased. For this reason, in each training of the tongue image classification model, it is an important question which resolution of tongue image is used for training. The resolution used for each training (i.e., the target resolution) may be pre-computed and then grouped into a set of target resolutions. The specific calculation manner of the target resolution is described later in detail.
103. And determining a regularized strength value set according to a preset regularized strength amplification mode of progressive learning, wherein regularized strength values in the regularized strength value set correspond to target resolutions in the target resolution set one by one, and the regularized strength values corresponding to the target resolutions increase along with the increase of the target resolutions.
In step 103, after each target resolution is calculated, the regularization intensity values increasing with the increase of each target resolution may be continuously calculated to form a regularization intensity value set. The calculation manner of the normalized intensity value is described in detail later.
104. And executing preset resolution resetting operation on each tongue coating image in the original training data set to obtain a target training data set, wherein the target training data sets in the target training data set correspond to the target resolutions in the target resolution set one by one, and the resolution of the tongue coating image in each group of target training data sets is the target resolution corresponding to the group of target training data sets.
In step 104, after each target resolution is calculated, the resolutions of all tongue fur images in the original training data set may be reset according to each target resolution to obtain a target training data set corresponding to each target resolution, so as to form a target training data set. For example, the target resolutions include 256 × 256, 512 × 512, and 1024 × 1024, and after the resolution is reset, the target training data set with the tongue coating image resolution of 256 × 256, the target training data set with the tongue coating image resolution of 512 × 512, and the target training data set with the tongue coating image resolution of 1024 × 1024 are obtained, thereby forming the target training data set.
105. And training a preset tongue fur image classification model for multiple times based on the target training data set and the regularized strength value set, so that a target loss function of the tongue fur image classification model is converged, and the training of the tongue fur image classification model is completed.
In step 105, for example, the target resolutions of the target training data sets in the target training data set are 256 × 256, 512 × 512, and 1024 × 1024, and the corresponding normalized intensity values are 0.2, 0.3, and 0.4. At this time, the tongue fur image classification model may be trained for the first time by using the target training data set with the target resolution of 256 × 256 and the regularization intensity value of 0.2, the tongue fur image classification model may be trained for the second time by using the target training data set with the target resolution of 512 × 512 and the regularization intensity value of 0.3, and the tongue fur image classification model may be trained for the third time by using the target training data set with the target resolution of 1024 × 1024 and the regularization intensity value of 0.4, so that the target loss function of the tongue fur image classification model may be converged to complete the training of the tongue fur image classification model. Optionally, the tongue image classification model employs a network structure of EfficientNetV 2. In the past research, many scholars have tried to improve the classification accuracy of the trained tongue image classification model by increasing the resolution of the tongue image in the training data, but practice has found that after the resolution is improved to a certain degree, the increase in resolution rather easily leads to a reduction in classification accuracy. After the inventor conducts practice and analysis for many times, the reason for the occurrence of the situation is found as follows: for the same network structure, the higher the resolution of the input image is, the larger the required network capacity is, and the larger the required regularization strength is, and if the resolution of the input image is increased and the regularization strength is kept unchanged, the classification effect is liable to be reduced. Therefore, the embodiment of the invention provides a model training mode for tongue fur images with different resolutions by using different regularization strengths, and practices show that the model training mode can achieve the effects of accelerating the training speed of the tongue fur image classification model and improving the classification accuracy of the trained tongue fur image classification model.
Optionally, the target resolution, the regularization strength, the image resolution resetting operation and the tongue fur image classification model training can be completed by a central terminal with strong computing power in the digital medical system, and after the tongue fur image classification model training is completed, the trained tongue fur image classification model can be sent to each terminal in the digital medical system by the central terminal to perform the image classification task.
It can be seen that, in the implementation of the training method for the tongue fur image classification model based on progressive learning described in fig. 1, an original training data set including a plurality of tongue fur images is obtained, a target resolution set is determined according to a preset resolution amplification mode of progressive learning, a regularized intensity value set corresponding to the target resolution set is determined according to a preset regularized intensity amplification mode of progressive learning, a preset resolution resetting operation is performed on each tongue fur image in the original training data set to obtain a target training data set, and finally, the preset tongue fur image classification model is trained for multiple times based on the target training data set and the regularized intensity value set, so that a target loss function of the tongue fur image classification model is converged, and training of the tongue fur image classification model is completed. The method comprises the steps of determining a target resolution set and a regularization strength value set corresponding to the target resolution set in advance, resetting the resolutions of a plurality of tongue fur images in an original training data set to the target resolution in the target resolution set to form a target training data set comprising tongue fur images with various resolutions, and therefore, when a tongue fur image classification model is trained, training of the model can be carried out on tongue fur images with different resolutions by using different regularization strengths, the training speed of the tongue fur image classification model can be increased, and the classification accuracy of the trained tongue fur image classification model is improved.
In an optional embodiment, the determining the target resolution set according to a preset progressive learning resolution amplification manner includes:
determining the maximum resolution and the minimum resolution corresponding to the target resolution set;
and determining a plurality of target resolutions from the interval between the maximum resolution and the minimum resolution according to a preset target resolution determination mode to be used as a target resolution set.
In this alternative embodiment, when calculating the target resolutions of the target resolution sets, the maximum resolution and the minimum resolution may be determined, and then a plurality of target resolutions may be selected from among the maximum resolution and the minimum resolution to form the target resolution sets.
It can be seen that this alternative embodiment is implemented by determining the maximum resolution and the minimum resolution, and then selecting a plurality of target resolutions from between the maximum resolution and the minimum resolution to form a target resolution set, thereby enabling calculation of the target resolutions.
In an optional embodiment, the determining, according to a preset target resolution determining manner, a plurality of target resolutions from an interval between the maximum resolution and the minimum resolution as a target resolution set includes:
determining a plurality of target resolutions from an interval between the maximum resolution and the minimum resolution as a set of target resolutions by:
wherein S isiIs the ith target resolution, S, in the set of target resolutions0Is the minimum resolution, SeIs the maximum resolution and N is the total number of target resolutions in the set of target resolutions.
In this alternative embodiment, N is the total number of target resolutions in the target resolution set, and is also the algebra for training the tongue fur image classification model. Each generation of training of the tongue coating image classification model requires the use of different target resolutions and regularization intensity values. The target resolution used by each generation of training of the tongue fur image classification model can be calculated through the formula. E.g. minimum resolution S0Set to 256 × 256, maximum resolution SeSet to 512 x 512, and the total number of target resolutions in the target resolution set (i.e. the algebra for training the tongue fur image classification model) N is set to 50, the calculated target resolution S is calculatedi256, 261.12, 261.12, 266.24, 266.24, 271.36, 271.36 … …
Therefore, by implementing the optional embodiment, a plurality of target resolutions can be selected from the preset maximum resolution and the preset minimum resolution at the same interval through the formula to form a target resolution set, so that the target resolutions used in the training can be uniformly distributed to the interval between the maximum resolution and the minimum resolution, and the training effect on the tongue fur image classification model is improved.
In an optional embodiment, the determining the regularized intensity value set according to a preset progressive learning regularized intensity augmentation mode includes:
determining a maximum regularization intensity value and a minimum regularization intensity value corresponding to the regularization intensity value set;
and determining a plurality of regularization intensity values from the interval between the maximum regularization intensity value and the minimum regularization intensity value according to a preset regularization intensity value determination mode to serve as a regularization intensity value set.
In this optional embodiment, when calculating the regularization strength value of the regularization strength value set, a maximum regularization strength value and a minimum regularization strength value may be determined, and then a plurality of regularization strength values may be selected from between the maximum regularization strength value and the minimum regularization strength value to form the regularization strength value set.
It can be seen that, by implementing the optional embodiment, the maximum regularization intensity value and the minimum regularization intensity value are determined, and then a plurality of regularization intensity values are selected from between the maximum regularization intensity value and the minimum regularization intensity value to form a regularization intensity value set, so that the regularization intensity value can be calculated.
In an optional embodiment, the determining, according to a preset regularization intensity value determining manner, a plurality of regularization intensity values from an interval between the maximum regularization intensity value and the minimum regularization intensity value as a regularization intensity value set includes:
determining a plurality of regularization intensity values from the interval between the maximum regularization intensity value and the minimum regularization intensity value as a set of regularization intensity values by the following formula:
wherein D isiIs the ith regularization intensity value in the set of regularization intensity values, which corresponds to the ith target resolution in the set of target resolutions, D0Is the minimum regularization intensity value, DeIs the maximum regularization intensity value, and N is the total number of regularization intensity values in the set of regularization intensity values.
In this alternative embodiment, N is the total number of regularization intensity values in the regularization intensity value set, and is also an algebraic number for training the tongue fur image classification model. Each generation of training of the tongue coating image classification model requires the use of different target resolutions and regularization intensity values. Tong (Chinese character of 'tong')The regularization intensity value used by each generation of training of the tongue fur image classification model can be calculated through the formula. For example, the minimum regularization intensity value D0Set to 0.1, maximum regularization intensity value DeSet to 0.6, and the total number of regularization intensity values (i.e., the algebra for training the tongue fur image classification model) N in the regularization intensity value set is set to 50, the computed regularization intensity value D is calculatedi0.1, 0.11, 0.12 and 0.13 … … in sequence
Therefore, by implementing the optional embodiment, a plurality of regularization intensity values can be selected from the preset maximum regularization intensity value and the preset minimum regularization intensity value according to the same interval through the formula to form a regularization intensity value set, so that the regularization intensity values used in training can be uniformly distributed to the interval between the maximum regularization intensity value and the minimum regularization intensity value, and the training effect on the tongue fur image classification model is improved.
In an alternative embodiment, the original training data set further includes a label corresponding to each tongue image;
and training a preset tongue fur image classification model for multiple times based on the target training data set and the regularized strength value set to make a target loss function of the tongue fur image classification model converged so as to complete the training of the tongue fur image classification model, wherein the method further comprises the following steps:
classifying and predicting each tongue coating image in the original training data set based on the trained tongue coating image classification model to obtain a prediction label and a prediction probability value corresponding to each tongue coating image;
screening a noise tongue coating image from all tongue coating images according to the corresponding prediction label, the prediction probability value and the label of each tongue coating image, wherein the noise tongue coating image is a tongue coating image which is inconsistent with the corresponding prediction label and the label and has the prediction probability value lower than a preset prediction probability value threshold;
and deleting the noise tongue fur image and the label corresponding to the noise tongue fur image from the original training data set so as to clean the original training data set.
In this alternative embodiment, in practical applications, the corresponding label of each tongue image in the original training data set may be wrong, for example, the label of the tongue image of a normal tongue may be set to peel off. If the tongue fur image with the wrong labels is used for training the tongue fur image classification model, the classification effect of the tongue fur image classification model is influenced. To this end, the original training data set may be cleaned to remove these wrongly labeled tongue images from the original training data set. Specifically, the trained tongue fur image classification model can be used for predicting tongue fur images in the original training data set, if a predicted label of a certain tongue fur image is inconsistent with an original labeled label and the predicted probability value is lower than the predicted probability value threshold, it can be determined that the labeled label of the tongue fur image is wrong, the labeled label can be determined as a noise tongue fur image, and the noise tongue fur image is deleted from the original training data set, so that the original training data set is cleaned. These steps can be repeated continuously, washing the original training data set 3-7 times. The cleaned original training data set is used for training the model, so that the classification effect of the tongue fur image classification model can be further improved.
Therefore, by implementing the optional embodiment, after the training of the model is completed, the trained model is used for predicting the tongue fur image in the original training data set to obtain the predicted label and the predicted probability value of the tongue fur image, then the noise tongue fur image is screened out according to the predicted label, the predicted probability value and the original labeled label of the tongue fur image, and finally the noise tongue fur image is deleted from the original training data set to realize the cleaning of the original training data set, so that the classification effect of the tongue fur image classification model can be further improved.
In an alternative embodiment, the objective loss function of the tongue image classification model is:
wherein, yjIs the label, p, corresponding to the jth tongue coating imagejIs the predicted probability value corresponding to the jth tongue coating image, and M is the total number of tongue coating images in the original training data set.
In this alternative embodiment, in the training of the tongue fur image classification model, the model is trained by using the target loss function, which is beneficial to improving the convergence rate of the model and the final classification effect of the model.
Optionally, it is also possible: and uploading the training information of the tongue fur image classification model based on progressive learning training method to a block chain.
Specifically, the training information of the tongue image classification model based on the progressive learning is obtained by operating the training method of the tongue image classification model based on the progressive learning, and is used for recording the training condition of the tongue image classification model based on the progressive learning, such as an acquired original training data set, a target resolution set, a regularization intensity value set, a trained tongue image classification model, and the like. The training information of the tongue fur image classification model based on progressive learning is uploaded to the block chain, so that the safety and the fair transparency to the user can be guaranteed. The user can download the training information of the tongue fur image classification model based on progressive learning from the blockchain so as to verify whether the training information of the tongue fur image classification model based on progressive learning of the training method based on the tongue fur image classification model based on progressive learning is falsified. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a training device for a tongue fur image classification model based on progressive learning according to an embodiment of the present invention. As shown in fig. 2, the training device for tongue coating image classification model based on progressive learning may include:
an obtaining module 201, configured to obtain an original training data set at least including a plurality of tongue coating images;
a determining module 202, configured to determine a target resolution set according to a preset progressive learning resolution amplification manner;
the determining module 202 is further configured to determine a regularized strength value set according to a preset regularized strength amplification manner of progressive learning, where regularized strength values in the regularized strength value set correspond to target resolutions in the target resolution set one to one, and the regularized strength value corresponding to the target resolution increases with an increase in the target resolution;
a resolution resetting module 203, configured to perform a preset resolution resetting operation on each tongue coating image in the original training data set to obtain a target training data set, where target training data sets in the target training data set correspond to target resolutions in the target resolution set one by one, and a resolution of a tongue coating image in each group of target training data sets is a target resolution corresponding to the group of target training data sets;
the training module 204 is configured to train a preset tongue fur image classification model for multiple times based on the target training data set and the regularization strength value set, so that a target loss function of the tongue fur image classification model is converged, and thus the training of the tongue fur image classification model is completed.
For the specific description of the training apparatus for the tongue fur image classification model based on the progressive learning, reference may be made to the specific description of the training method for the tongue fur image classification model based on the progressive learning, and for avoiding repetition, the details are not repeated herein.
EXAMPLE III
Referring to fig. 3, fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 3, the computer apparatus may include:
a memory 301 storing executable program code;
a processor 302 connected to the memory 301;
the processor 302 calls the executable program code stored in the memory 301 to execute the steps in the training method of the tongue fur image classification model based on progressive learning disclosed in the embodiment of the present invention.
Example four
Referring to fig. 4, an embodiment of the present invention discloses a computer storage medium 401, where the computer storage medium 401 stores computer instructions, and when the computer instructions are called, the computer instructions are used to execute the steps of the method for training a tongue fur image classification model based on progressive learning disclosed in an embodiment of the present invention.
The above-described embodiments of the apparatus are merely illustrative, and the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, where the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc-Read-Only Memory (CD-ROM), or other disk memories, CD-ROMs, or other magnetic disks, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
Finally, it should be noted that: the method, the apparatus, the computer device and the storage medium for training the tongue fur image classification model based on the progressive learning disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used for illustrating the technical solution of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for training a tongue fur image classification model based on progressive learning is characterized by comprising the following steps:
acquiring an original training data set at least comprising a plurality of tongue fur images;
determining a target resolution set according to a preset resolution amplification mode of progressive learning;
determining a regularized strength value set according to a preset regularized strength amplification mode of progressive learning, wherein regularized strength values in the regularized strength value set correspond to target resolutions in the target resolution set one by one, and the regularized strength values corresponding to the target resolutions increase along with the increase of the target resolutions;
executing preset resolution resetting operation on each tongue coating image in the original training data set to obtain a target training data set, wherein the target training data sets in the target training data set correspond to the target resolutions in the target resolution set one by one, and the resolution of the tongue coating image in each group of target training data sets is the target resolution corresponding to the group of target training data sets;
and training a preset tongue fur image classification model for multiple times based on the target training data set and the regularized strength value set, so that a target loss function of the tongue fur image classification model is converged, and the training of the tongue fur image classification model is completed.
2. The method for training a tongue fur image classification model based on progressive learning according to claim 1, wherein the determining a target resolution set according to a preset resolution augmentation mode of progressive learning comprises:
determining the maximum resolution and the minimum resolution corresponding to the target resolution set;
and determining a plurality of target resolutions from the interval between the maximum resolution and the minimum resolution according to a preset target resolution determination mode to be used as a target resolution set.
3. The method for training a tongue fur image classification model based on progressive learning according to claim 2, wherein the determining a plurality of target resolutions from the interval between the maximum resolution and the minimum resolution as a target resolution set according to a preset target resolution determination manner comprises:
determining a plurality of target resolutions from an interval between the maximum resolution and the minimum resolution as a set of target resolutions by:
wherein S isiIs the ith target resolution, S, in the set of target resolutions0Is the minimum resolution, SeIs the maximum resolution and N is the total number of target resolutions in the set of target resolutions.
4. The method for training a tongue fur image classification model based on progressive learning according to claim 3, wherein the determining a regularized intensity value set according to a preset regularized intensity amplification mode of progressive learning comprises:
determining a maximum regularization intensity value and a minimum regularization intensity value corresponding to the regularization intensity value set;
and determining a plurality of regularization intensity values from the interval between the maximum regularization intensity value and the minimum regularization intensity value according to a preset regularization intensity value determination mode to serve as a regularization intensity value set.
5. The method for training a tongue fur image classification model based on progressive learning according to claim 4, wherein the determining a plurality of regularization strength values from an interval between the maximum regularization strength value and the minimum regularization strength value as a regularization strength value set according to a preset regularization strength value determination manner comprises:
determining a plurality of regularization intensity values from the interval between the maximum regularization intensity value and the minimum regularization intensity value as a set of regularization intensity values by the following formula:
wherein D isiIs the ith regularization intensity value in the set of regularization intensity values, which corresponds to the ith target resolution in the set of target resolutions, D0Is the minimum regularization intensity value, DeIs the maximum regularization intensity value, and N is the total number of regularization intensity values in the set of regularization intensity values.
6. The method for training a tongue coating image classification model based on progressive learning according to any one of claims 1-5, wherein the original training data set further comprises a label corresponding to each tongue coating image;
and training a preset tongue fur image classification model for multiple times based on the target training data set and the regularized strength value set to make a target loss function of the tongue fur image classification model converged so as to complete the training of the tongue fur image classification model, wherein the method further comprises the following steps:
classifying and predicting each tongue coating image in the original training data set based on the trained tongue coating image classification model to obtain a prediction label and a prediction probability value corresponding to each tongue coating image;
screening a noise tongue coating image from all tongue coating images according to the corresponding prediction label, the prediction probability value and the label of each tongue coating image, wherein the noise tongue coating image is a tongue coating image which is inconsistent with the corresponding prediction label and the label and has the prediction probability value lower than a preset prediction probability value threshold;
and deleting the noise tongue fur image and the label corresponding to the noise tongue fur image from the original training data set so as to clean the original training data set.
7. The method for training a tongue coating image classification model based on progressive learning according to any one of claims 1-5, wherein the objective loss function of the tongue coating image classification model is as follows:
wherein, yjIs the label, p, corresponding to the jth tongue coating imagejIs the predicted probability value corresponding to the jth tongue coating image, and M is the total number of tongue coating images in the original training data set.
8. A training device of tongue fur image classification model based on progressive learning is characterized by comprising:
the system comprises an acquisition module, a comparison module and a processing module, wherein the acquisition module is used for acquiring an original training data set at least comprising a plurality of tongue fur images;
the determining module is used for determining a target resolution set according to a preset progressive learning resolution amplification mode;
the determining module is further configured to determine a regularization strength value set according to a preset regularization strength amplification mode of progressive learning, wherein regularization strength values in the regularization strength value set correspond to target resolutions in the target resolution set one to one, and the regularization strength values corresponding to the target resolutions increase with increase of the target resolutions;
a resolution resetting module, configured to perform a preset resolution resetting operation on each tongue coating image in the original training data set to obtain a target training data set, where target training data sets in the target training data set correspond to target resolutions in the target resolution set one by one, and a resolution of a tongue coating image in each group of target training data sets is a target resolution corresponding to the group of target training data sets;
and the training module is used for training a preset tongue fur image classification model for multiple times based on the target training data set and the regularization strength value set so as to enable a target loss function of the tongue fur image classification model to be converged, and thus the training of the tongue fur image classification model is completed.
9. A computer device, characterized in that the computer device comprises:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program code stored in the memory to execute the training method of the tongue fur image classification model based on the progressive learning according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements a method of training a tongue image classification model based on progressive learning according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111086464.5A CN113780444B (en) | 2021-09-16 | 2021-09-16 | Training method of tongue fur image classification model based on progressive learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111086464.5A CN113780444B (en) | 2021-09-16 | 2021-09-16 | Training method of tongue fur image classification model based on progressive learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113780444A true CN113780444A (en) | 2021-12-10 |
| CN113780444B CN113780444B (en) | 2023-07-25 |
Family
ID=78851364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111086464.5A Active CN113780444B (en) | 2021-09-16 | 2021-09-16 | Training method of tongue fur image classification model based on progressive learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113780444B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094966A (en) * | 2023-08-21 | 2023-11-21 | 青岛美迪康数字工程有限公司 | Tongue image identification method and device based on image amplification and computer equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345469A (en) * | 2018-09-07 | 2019-02-15 | 苏州大学 | It is a kind of that speckle denoising method in the OCT image of confrontation network is generated based on condition |
| CN109657722A (en) * | 2018-12-20 | 2019-04-19 | 山东农业大学 | Tongue fur image-recognizing method and system based on deep learning algorithm |
| CN110738235A (en) * | 2019-09-16 | 2020-01-31 | 平安科技（深圳）有限公司 | Pulmonary tuberculosis determination method, pulmonary tuberculosis determination device, computer device, and storage medium |
| WO2021016131A1 (en) * | 2019-07-19 | 2021-01-28 | The Jackson Laboratory | Convolutional neural networks for classification of cancer histological images |
| CN112766155A (en) * | 2021-01-19 | 2021-05-07 | 山东华宇航天空间技术有限公司 | Deep learning-based mariculture area extraction method |
| CN112884648A (en) * | 2021-01-25 | 2021-06-01 | 汉斯夫(杭州)医学科技有限公司 | Method and system for multi-class blurred image super-resolution reconstruction |
| CN112991183A (en) * | 2021-04-09 | 2021-06-18 | 华南理工大学 | Video super-resolution method based on multi-frame attention mechanism progressive fusion |
| CN113379602A (en) * | 2021-06-08 | 2021-09-10 | 中国科学技术大学 | Light field super-resolution enhancement method by using zero sample learning |
| CN113392845A (en) * | 2021-06-15 | 2021-09-14 | 广州观必达数据技术有限责任公司 | Deep learning remote sensing image semantic segmentation method and system based on U-NET |
-
2021
- 2021-09-16 CN CN202111086464.5A patent/CN113780444B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345469A (en) * | 2018-09-07 | 2019-02-15 | 苏州大学 | It is a kind of that speckle denoising method in the OCT image of confrontation network is generated based on condition |
| CN109657722A (en) * | 2018-12-20 | 2019-04-19 | 山东农业大学 | Tongue fur image-recognizing method and system based on deep learning algorithm |
| WO2021016131A1 (en) * | 2019-07-19 | 2021-01-28 | The Jackson Laboratory | Convolutional neural networks for classification of cancer histological images |
| CN110738235A (en) * | 2019-09-16 | 2020-01-31 | 平安科技（深圳）有限公司 | Pulmonary tuberculosis determination method, pulmonary tuberculosis determination device, computer device, and storage medium |
| CN112766155A (en) * | 2021-01-19 | 2021-05-07 | 山东华宇航天空间技术有限公司 | Deep learning-based mariculture area extraction method |
| CN112884648A (en) * | 2021-01-25 | 2021-06-01 | 汉斯夫(杭州)医学科技有限公司 | Method and system for multi-class blurred image super-resolution reconstruction |
| CN112991183A (en) * | 2021-04-09 | 2021-06-18 | 华南理工大学 | Video super-resolution method based on multi-frame attention mechanism progressive fusion |
| CN113379602A (en) * | 2021-06-08 | 2021-09-10 | 中国科学技术大学 | Light field super-resolution enhancement method by using zero sample learning |
| CN113392845A (en) * | 2021-06-15 | 2021-09-14 | 广州观必达数据技术有限责任公司 | Deep learning remote sensing image semantic segmentation method and system based on U-NET |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094966A (en) * | 2023-08-21 | 2023-11-21 | 青岛美迪康数字工程有限公司 | Tongue image identification method and device based on image amplification and computer equipment |
| CN117094966B (en) * | 2023-08-21 | 2024-04-05 | 青岛美迪康数字工程有限公司 | Tongue image identification method and device based on image amplification and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113780444B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111666857B (en) | Human behavior recognition method, device and storage medium based on environment semantic understanding | |
| CN110443222B (en) | Method and device for training face key point detection model | |
| CN110363220B (en) | Behavior class detection method and device, electronic equipment and computer readable medium | |
| CN111767707A (en) | Method, device, equipment and storage medium for detecting Rayleigh case | |
| WO2021179630A1 (en) | Complications risk prediction system, method, apparatus, and device, and medium | |
| CN112528764B (en) | Facial expression recognition method, system and device and readable storage medium | |
| CN111738351A (en) | Model training method and device, storage medium and electronic equipment | |
| CN110956615B (en) | Image quality evaluation model training method and device, electronic equipment and storage medium | |
| CN111414946A (en) | Artificial intelligence-based medical image noise data identification method and related device | |
| CN110288085B (en) | Data processing method, device and system and storage medium | |
| US20200160119A1 (en) | Sequential learning maintaining a learned concept | |
| CN111724370A (en) | Multi-task non-reference image quality evaluation method and system based on uncertainty and probability | |
| CN111368911A (en) | Image classification method and device and computer readable storage medium | |
| CN113705685A (en) | Disease feature recognition model training method, disease feature recognition device and disease feature recognition equipment | |
| CN110379491B (en) | Method, device, equipment and storage medium for identifying brain glioma | |
| CN113780444A (en) | Tongue fur image classification model training method based on progressive learning | |
| CN113705092B (en) | Disease prediction method and device based on machine learning | |
| CN111489803A (en) | Report coding model generation method, system and equipment based on autoregressive model | |
| CN113177554B (en) | Thyroid nodule identification and segmentation method, system, storage medium and equipment | |
| CN111275059B (en) | Image processing method and device and computer readable storage medium | |
| CN112818946A (en) | Training of age identification model, age identification method and device and electronic equipment | |
| CN115713669B (en) | Image classification method and device based on inter-class relationship, storage medium and terminal | |
| JP7238905B2 (en) | Recognizer training device, recognition device, data processing system, data processing method, and program | |
| CN112668710A (en) | Model training, tubular object extraction and data recognition method and equipment | |
| CN111476775B (en) | DR symptom identification device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |