WO2024026990A1 - 识别模型的自动迭代训练方法、系统、设备和存储介质 - Google Patents

识别模型的自动迭代训练方法、系统、设备和存储介质 Download PDF

Info

Publication number
WO2024026990A1
WO2024026990A1 PCT/CN2022/119346 CN2022119346W WO2024026990A1 WO 2024026990 A1 WO2024026990 A1 WO 2024026990A1 CN 2022119346 W CN2022119346 W CN 2022119346W WO 2024026990 A1 WO2024026990 A1 WO 2024026990A1
Authority
WO
WIPO (PCT)
Prior art keywords
training
recognition model
recognition
automatic iterative
model
Prior art date
Application number
PCT/CN2022/119346
Other languages
English (en)
French (fr)
Inventor
应俊
潘天一
Original Assignee
上海扩博智能技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海扩博智能技术有限公司 filed Critical 上海扩博智能技术有限公司
Publication of WO2024026990A1 publication Critical patent/WO2024026990A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models

Definitions

  • the present disclosure relates to the technical field of model training. Specifically, an automatic iterative training method, system, equipment and storage medium for recognition models are disclosed.
  • the trained recognition model is usually used to identify the target object to be recognized to obtain the recognition result.
  • the continuous improvement of the demand for model recognition accuracy and the continuous updating and iteration of the types of recognition objects it is often necessary to retrain the obtained recognition models to meet the increasing changes in recognition requirements.
  • the present disclosure provides an automatic iterative training method, system, device and storage medium for a recognition model.
  • the first aspect of the present disclosure provides an automatic iterative training method for a recognition model, including the following steps:
  • a preset model iteration time is separated between two adjacent training rounds.
  • the recognition model is used to recognize an image to be recognized that contains a target object to obtain identification information of the target object;
  • the training data contains images to be recognized.
  • performing a training operation on the recognition model includes the following steps:
  • the pre-trained model is optimized so that the pre-trained model that meets the preset evaluation conditions is used as the recognition model to complete the current training round.
  • performing the first preset processing on the foreground area includes the following steps:
  • performing the second preset processing on the image to be recognized includes the following steps:
  • optimizing the pre-trained model includes the following steps:
  • the recognition results of the pre-trained model are post-processed using non-maximum value merging.
  • a second aspect of the present disclosure provides an automatic iterative training system for a recognition model, which is applied to the automatic iterative training method for a recognition model provided by the first aspect;
  • An automated iterative training system for recognition models includes:
  • the training unit is used to perform training operations on the recognition model based on the training data required for the current training round;
  • An inference unit used to perform inference operations on the recognition model that has completed the current training round to obtain the first recognition result containing pre-annotation information
  • a verification unit used to verify the first identification result to obtain the second identification result containing verification information
  • a generation unit configured to compare the first recognition result of the previous training round of the recognition model with the second recognition result of the current training round to generate training data required for the next training round;
  • Iterative unit is used to repeat the above steps to achieve automatic iterative training of the recognition model.
  • a third aspect of the present disclosure provides an automatic iterative training device for a recognition model, including:
  • Memory used to store computer programs
  • the processor is configured to implement the automatic iterative training method of the recognition model provided in the first aspect when executing the computer program.
  • a fourth aspect of the present disclosure provides a computer-readable storage medium, which is characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements automatic iteration of the recognition model provided in the first aspect. Training methods.
  • the training data required for the iteration of the recognition model can be automatically generated through the recognition results and verification results obtained between different training rounds, and these training data can be used to automatically update and iterate the recognition model to avoid
  • the recognition model is aging and cannot meet the recognition needs.
  • it saves the labor cost of operation and maintenance upgrade of the recognition model, which has scalable value.
  • Figure 1 shows a schematic flow chart of an automatic iterative training method for a recognition model according to an embodiment of the present disclosure
  • Figure 2 shows a schematic flowchart of performing a training operation on a recognition model according to an embodiment of the present disclosure
  • Figure 3 shows a schematic flowchart of performing first preset processing on the foreground area according to an embodiment of the present disclosure
  • Figure 4 shows a schematic flow chart of a second preset processing of an image to be recognized according to an embodiment of the present disclosure
  • Figure 5 shows a schematic structural diagram of an automatic iterative training system for recognition models according to an embodiment of the present disclosure
  • Figure 6 shows a schematic structural diagram of an electronic device according to an embodiment of the present disclosure
  • FIG. 7 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present disclosure.
  • the term “include” and its variations mean an open inclusion, ie, "including but not limited to.” Unless otherwise stated, the term “or” means “and/or”. The term “based on” means “at least regionally based on”. The terms “one example embodiment” and “an embodiment” mean “at least one example embodiment.” The term “another embodiment” means “at least one additional embodiment”. The terms “first,” “second,” etc. may refer to different or the same object. Other explicit and implicit definitions may be included below.
  • Figure 1 shows a flow chart that provides an automatic iterative training method for a recognition model.
  • the automatic iterative training method for a recognition model includes the following steps:
  • Step 101 Perform training operations on the recognition model based on the training data required for the current training round.
  • Step 102 Perform an inference operation on the recognition model that has completed the current training round to obtain the first recognition result containing pre-annotation information.
  • Step 103 Verify the first identification result to obtain the second identification result including verification information.
  • Step 104 Compare the first recognition result of the previous training round of the recognition model and the second recognition result of the current training round to generate training data required for the next training round.
  • Step 105 Repeat the above steps 101 to 104 to realize automatic iterative training of the recognition model. Among them, a preset model iteration time can be separated between two adjacent training rounds.
  • the technical solution provided by the present disclosure can be based on Pandas (a numerical computing extension tool based on the Python computer programming language, which incorporates a large number of libraries and some standard data models, providing efficient operation of large data sets
  • Pandas a numerical computing extension tool based on the Python computer programming language, which incorporates a large number of libraries and some standard data models, providing efficient operation of large data sets
  • the database implemented by the required tools uses its relevant features to quickly and flexibly create the required training data, thereby greatly reducing maintenance and use costs; the database can also save and label results and manual review results at the same time and record the differences between the two. difference.
  • the training performed by optimizing the training model each time a new training image is obtained is called a round of training.
  • the optimized recognition model can generate a new training set based on the difference between the current recognition results and the previous round of annotation results. update iteration.
  • the model iteration time can be set so that the model itself can automatically iterate and update.
  • the training process of the model can be further optimized: It is understandable that in the existing technology, the quality of the recognition model is closely related to the quality of the manually labeled training data.
  • manual annotation of training data has many problems such as high labor cost, heavy workload, and uneven annotation quality, which results in obvious differences in the effect of automatic iterative training of recognition models.
  • existing image recognition models are often only used in general technical fields such as pedestrian detection and face recognition, and cannot meet the needs of ultra-large resolution defect detection and model adaptive iterative upgrades in specific technical fields.
  • Figure 2 shows a schematic flowchart of performing a training operation on a recognition model. As shown in Figure 2, the specific steps may include:
  • Step 201 Divide the image to be recognized to obtain the foreground area. It can be understood that by dividing the foreground area and the background area, the consumption of computing resources can be reduced, and at the same time, the interference of the complex background area on the foreground can be reduced.
  • a foreground segmentation model can be used to implement the segmentation operation. Those skilled in the art can select an appropriate segmentation method according to actual needs, which is not limited here.
  • Step 202 Perform first preset processing on the foreground area to obtain the minimum circumscribed rectangular marked area containing the target object.
  • the specific implementation of the first preset processing will be explained in detail later.
  • Step 203 Perform second preset processing on the image to be recognized to obtain a preferred training set containing the minimum circumscribed rectangle marked area.
  • the specific implementation of the second preset processing will be explained in detail later.
  • Step 204 Train the preset recognition model through the optimized training set to generate a pre-trained model.
  • Step 205 Optimize the pre-trained model so that the pre-trained model that meets the preset evaluation conditions is used as the recognition model that completes the current training round.
  • the automatic iterative training method of the recognition model provided in the aforementioned steps 201 to 205 can, on the one hand, overcome the problems of high labor cost, heavy workload, and inconsistent annotation quality of manual annotation. On the other hand, it can be applied to various specific application scenarios.
  • the automatic iterative training method of the above recognition model can be applied to the inspection image recognition of wind turbine blades. It can be understood that in the process of using image recognition technology to inspect wind turbine blades, drones can be used to fly around the wind turbine blades and capture images of the surface of the wind turbine blades during the flight. Subsequently, the images can be captured by Image recognition is performed to obtain whether there are defects on the surface of wind turbine blades and the specific types of defects.
  • the image to be identified in the above embodiment may include an inspection photographed image containing the wind turbine blade, the foreground area may include the area occupied by the wind turbine blade in the inspection photographed image, and the target object may include the area present in the wind turbine blade. Defects on the blade surface.
  • the minimum circumscribed rectangular mark area cannot be obtained through the subsequent first preset processing. Therefore, it is necessary to determine in advance after completing the foreground division whether the edge lines of the foreground objects in the foreground area can be identified, and whether the edge lines of the foreground objects match the external features of the foreground objects. If any of the conditions are not met, the accurate minimum circumscribed rectangle marking area cannot be obtained. At this time, the marking frame containing the target object can be directly obtained from the original image to be recognized, and then the corresponding training data can be generated.
  • FIG. 3 shows a schematic flowchart of performing first preset processing on the foreground area. As shown in Figure 3, specific details may include:
  • Step 201 Obtain the edge line of the foreground object in the foreground area to obtain the angle of the foreground object in the image to be recognized.
  • the location of the blades can be intuitively obtained through the edge lines of the wind turbine blades, and then the location of the wind turbine blades in the image to be identified can be calculated by extracting the edge lines. Approximate angle.
  • Step 302 Rotate the foreground area according to the angle so that the foreground object is in the vertical direction or the horizontal direction.
  • Step 303 Obtain the circumscribed rectangular mark box containing the target object in the rotated foreground area as the minimum circumscribed rectangular mark area.
  • the mask information corresponding to the foreground area can be used to rotate the foreground area so that the wind turbine blades are in the vertical direction or the horizontal direction. At this time, these narrow and inclined defects are also rotated to the vertical direction or the horizontal direction.
  • the minimum enclosing rectangular marking area that can be obtained by marking the enclosing rectangular marking frame can further increase the proportion of defective foreground compared to directly marking the defect identification frame.
  • FIG. 4 shows a schematic flowchart of performing a second preset processing on an image to be recognized. As shown in Figure 4, specific details may include:
  • Step 401 Perform sliding window cropping on the image to be recognized according to the preset window size to obtain several cropped images that overlap with the minimum circumscribed rectangular mark area.
  • the resolution of the input image can be 1333*800 pixels.
  • the resolution of the captured pictures obtained during the inspection process exceeds 20 million pixels. Such huge captured pictures are obviously not suitable for direct input as images and need to be cropped through sliding windows. Perform preprocessing.
  • multiple fixed-size sliding windows can be set in the image to be recognized, and then the coincidence degree of each sliding window and the minimum circumscribed rectangle marked area is calculated one by one. If the coincidence degree is higher than the preset threshold, the The cropped image corresponding to the sliding window is used as qualified training data.
  • Step 402 Perform data enhancement processing on the cropped image to generate training data.
  • the data enhancement process can use the mosaic algorithm to enhance the data, which is equivalent to increasing the number of batch images by 4 times, effectively saving computing resources.
  • random left and right inversions are performed during the data enhancement process. Random color conversion, random size scaling, random affine transformation, random rotation and other operations can effectively improve the generalization ability of the model.
  • the four cropped images obtained after enhancement can finally be spliced to obtain the training data required for training.
  • the pre-built framework model may be secondary developed based on the open source framework mmdetection (a deep learning target detection toolbox implemented by an open source Python machine learning library).
  • the open source framework has basic versatility, but it is not perfectly suitable for all scenarios. Therefore, some local adjustments need to be made to the open source framework to meet the actual training needs and the rapid iteration and deployment requirements of possible subsequent needs.
  • Those skilled in the art can complete the construction of the model as required based on their own knowledge and meet the training requirements of relevant application scenarios, which is not limited here.
  • further optimizing the pre-trained model includes the following steps: post-processing the recognition results of the pre-trained model using non-maximum merging.
  • the post-processing method of Non-Maximum Suppression is usually used.
  • the post-processing method of non-maximum value merging is adopted in order to meet the actual application requirements of wind turbine blade defect identification.
  • the defect identification of wind turbine blades it is required that the defect identification mark frame obtained after image recognition can all contain the area where the defect is located.
  • the usual non-maximum suppression post-processing method may select a smaller one among multiple qualified candidate frames.
  • the best option is used as the only choice to retain, thereby giving up other identification frames, which may result in the final selected identification frame still being unable to fully cover the single identification defect on the surface of the wind turbine blade; instead, multiple candidate frames are considered to jointly correspond to each other. Only under the condition of the largest external rectangle can the defect part to be identified be completely surrounded. Therefore, the use of non-maximum value merging to post-process the recognition results of the pre-trained model is a customized design for the above-mentioned specific application fields.
  • the preset evaluation condition includes that the recall rate of the preferred recognition model is greater than a preset threshold. It is understandable that in the process of evaluating image recognition models, the evaluation criteria often include two dimensions: recall and accuracy. Precision refers to the probability of identifying a target in an accurately recognized picture, while recall It refers to the ratio of the number of accurately identified targets to the number of targets in the training set.
  • the recall rate is required to reach 99% or higher.
  • the optimization process to achieve high recall rate includes:
  • FIG. 5 shows an automatic iterative training system for recognition models, which is applied to the automatic iterative training method for recognition models provided by the foregoing embodiments.
  • the automatic iterative training system of this recognition model can include:
  • the training unit 001 is used to perform training operations on the recognition model based on the training data required for the current training round.
  • the inference unit 002 is configured to perform an inference operation on the recognition model that has completed the current training round to obtain a first recognition result containing pre-annotation information.
  • the verification unit 003 is used to verify the first identification result to obtain the second identification result containing verification information.
  • the generation unit 004 is configured to compare the first recognition result of the previous training round of the recognition model and the second recognition result of the current training round to generate training data required for the next training round.
  • the iteration unit 005 is used to repeat the function implementation of the above-mentioned functional modules in order to realize automatic iterative training of the recognition model.
  • FIG. 6 shows a schematic structural diagram of an electronic device according to some embodiments of the present disclosure.
  • the electronic device is used to implement the automatic iteration method in the foregoing embodiments.
  • the electronic device 600 implemented according to the implementation method in this embodiment will be described in detail below with reference to FIG. 6 .
  • the electronic device 600 shown in FIG. 6 is only an example and should not impose any limitations on the functions and scope of use of any embodiment of the technical solution of the present disclosure.
  • electronic device 600 is embodied in the form of a general computing device.
  • the components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, and the like.
  • the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the implementation of each functional module in the automatic iterative training system of the recognition model in this embodiment.
  • the storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access unit (RAM) 6201 and/or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.
  • RAM random access unit
  • ROM read-only storage unit
  • Storage unit 620 may also include a program/utility 6204 having a set of (at least one) program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples, or some combination, may include the implementation of a network environment
  • Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures. .
  • the audio and video signal synchronization processing device 600 can also communicate with one or more external devices 700 (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that allow the user to interact with the electronic device 600, and /or communicate with any device (e.g., router, modem, etc.) that enables the electronic device to communicate with one or more other computing devices. This communication may occur through input/output (I/O) interface 650.
  • the electronic device 600 may also communicate with one or more networks (eg, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 660.
  • Network adapter 660 may communicate with other modules of electronic device 600 via bus 630.
  • a computer-readable storage medium is also provided.
  • a computer program is stored on the computer-readable storage medium. When executed by a processor, the computer program can realize various functions in the automatic iteration system disclosed above. module implementation.
  • various aspects described in the technical solution of the present disclosure can also be implemented in the form of a program product, which includes program code.
  • the program product When running on the terminal device, the program code is used to cause the terminal device to perform the steps described in the automatic iterative training method in the technical solution of the present disclosure according to the implementation methods in various embodiments of the technical solution of the present disclosure.
  • Figure 7 shows a schematic structural diagram of a computer-readable storage medium according to some embodiments of the present disclosure.
  • a program product 800 for implementing the above method in an embodiment according to the technical solution of the present disclosure is described. It can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be Run on terminal devices such as personal computers.
  • CD-ROM portable compact disk read-only memory
  • the program product generated according to this embodiment is not limited to this.
  • the readable storage medium can be any tangible medium that contains or stores a program.
  • the program can be used by or in conjunction with an instruction execution system, device or device. In conjunction with.
  • the Program Product may take the form of one or more readable media in any combination.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may include a data signal propagated in baseband or as a carrier wave having readable program code thereon. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.
  • Program code contained on a readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.
  • the program code for performing the operations of the technical solution of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also includes conventional procedural formulas. Programming language - such as C or similar programming language.
  • the program code may execute entirely on the user's computing device, partially on the user's computing device, as a stand-alone software package, execute entirely on the user's computing device, partially on a remote computing device, or entirely on the remote computing device or server execute on.
  • the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device, such as provided by an Internet service. (business comes via Internet connection).
  • LAN local area network
  • WAN wide area network
  • the training data required for the iteration of the recognition model can be automatically generated through the recognition results and verification results obtained between different training rounds, and these training data can be used to automatically upgrade the recognition model. Update iteration to avoid the situation where the recognition model ages and cannot meet the recognition needs. At the same time, it saves the labor cost of operation and maintenance upgrade of the recognition model, which has scalable value.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Remote Sensing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)

Abstract

本公开提供了一种识别模型的自动迭代训练方法、系统、设备和计算机可读存储介质。通过本公开提出的技术方案，能够通过不同训练轮次间获得的识别结果与校验结果，自动生成识别模型迭代所需的训练数据，并利用这些训练数据进行识别模型的自动更新迭代，以避免识别模型出现老化、无法满足识别需求的情况，同时节省了对于识别模型进行运维升级人力成本，具有可推广价值。

Description

识别模型的自动迭代训练方法、系统、设备和存储介质 技术领域
本公开涉及模型训练技术领域，具体地，公开了一种识别模型的自动迭代训练方法、系统、设备和存储介质。
背景技术
在模型识别技术领域，通常使用训练后的识别模型，对待识别的目标物进行识别，以得到识别结果。随着对于模型识别准确度需求的不断提升，以及识别对象种类的不断更新迭代，往往需要对已获得的识别模型进行重新进行训练以满足日益增长的识别需求更迭。
发明内容
本公开提供了一种识别模型的自动迭代训练方法、系统、设备和存储介质。具体地，本公开的第一方面提供了一种识别模型的自动迭代训练方法，包括如下步骤：
根据当前训练轮次所需的训练数据，对识别模型执行训练操作；
对完成当前训练轮次的识别模型执行推理操作，以获取包含预标注信息的第一识别结果；
校验第一识别结果，以获取包含校验信息的第二识别结果；
比对识别模型的前一个训练轮次的第一识别结果和当前训练轮次的第二识别结果，以生成下一个训练轮次所需的训练数据；
重复上述步骤以实现识别模型的自动迭代训练。
在上述第一方面的一种可能的实现中，相邻的两个训练轮次之间间隔预设的模型迭代时间。
在上述第一方面的一种可能的实现中，识别模型用于对包含目标物的待识别图像进行识别以获取目标物的识别信息；
训练数据包含待识别图像。
在上述第一方面的一种可能的实现中，对识别模型执行训练操作包括如下步骤：
划分待识别图像，以获取对应的前景区域；
对前景区域进行第一预设处理，以获取包含目标物的最小外接矩形标记区域；
对待识别图像进行第二预设处理，以获取包含最小外接矩形标记区域的优选训练集；
通过优选训练集对识别模型进行训练，以生成预训练模型；
对预训练模型进行优化处理，以将满足预设评估条件的预训练模型作为完成当前训练轮次的识别模型。
在上述第一方面的一种可能的实现中，对前景区域进行第一预设处理包括如下步骤：
获取前景区域中前景物的边缘线，以获取前景物于待识别图像中的所处角度；
根据所处角度旋转前景区域，以使前景物相对于待识别图像处于垂直方向或水平方向；
于旋转后的前景区域中获取包含目标物的外接矩形标记框，以作为最小外接矩形标记区域。
在上述第一方面的一种可能的实现中，对待识别图像进行第二预设处理包括如下步骤：
对待识别图像根据预设窗口大小进行滑动窗口裁剪，以获取若干与最小外接矩形标记区域存在重叠区域的裁剪图像；
对裁剪图像进行数据增强处理，以生成优选训练集。
在上述第一方面的一种可能的实现中，对预训练模型进行优化处理包括如下步骤：
采用非极大值合并的方式对预训练模型的识别结果进行后处理。
本公开的第二方面提供了一种识别模型的自动迭代训练系统，应用于前述第一方面提供的识别模型的自动迭代训练方法中；
识别模型的自动迭代训练系统包括：
训练单元，用于根据当前训练轮次所需的训练数据，对识别模型执行训练操作；
推理单元，用于对完成当前训练轮次的识别模型执行推理操作，以获取包含预标注信息的第一识别结果；
校验单元，用于校验第一识别结果，以获取包含校验信息的第二识别结果；
生成单元，用于比对识别模型的前一个训练轮次的第一识别结果和当前训练轮次的第二识别结果，以生成下一个训练轮次所需的训练数据；
迭代单元，用于重复上述步骤以实现识别模型的自动迭代训练。
本公开的第三方面提供了一种识别模型的自动迭代训练设备，包括：
存储器，用于存储计算机程序；
处理器，用于执行计算机程序时实现前述第一方面提供的识别模型的自动迭代训练方法。
本公开的第四方面提供了一种计算机可读存储介质，其特征在于，计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时实现前述第一方面提供的识别模型的自动迭代训练方法。
与现有技术相比，本公开具有如下的有益效果：
通过本公开提出的技术方案，能够通过不同训练轮次间获得的识别结果与校验结果，自动生成识别模型迭代所需的训练数据，并利用这些训练数据进行识别模型的自动更新迭代，以避免识别模型出现老化、无法满足识别需求的情况，同时节省了对于识别模型进行运维升级人力成本，具有可推广价值。
附图说明
通过阅读参照以下附图对非限制性实施例所作的详细描述，本发明的其它特征、目的和优点将会变得更明显：
图1根据本公开实施例，示出了一种识别模型的自动迭代训练方法的流程示意图；
图2根据本公开实施例，示出了一种对识别模型执行训练操作的流程示意图；
图3根据本公开实施例，示出了一种对前景区域进行第一预设处理的流程示意图；
图4根据本公开实施例，示出了一种对待识别图像进行第二预设处理流程示意图；
图5根据本公开实施例，示出了一种识别模型的自动迭代训练系统的结构示意图；
图6根据本公开实施例，示出了一种电子设备的结构示意图；
图7根据本公开实施例，示出了一种计算机可读存储介质的结构示意图。
具体实施方法
下面结合具体实施例对本发明进行详细说明。以下实施例将有助于本领域的技术人员进一步理解本发明，但不以任何形式限制本发明。应当指出的是，对本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变化和改进。这些都属于本发明的保护范围。
在本文中使用的术语“包括”及其变形表示开放性包括，即“包括但不限于”。除非特别申明，术语“或”表示“和/或”。术语“基于”表示“至少区域地基于”。术语 “一个示例实施例”和“一个实施例”表示“至少一个示例实施例”。术语“另一实施例”表示“至少一个另外的实施例”。术语“第一”、“第二”等等可以指代不同的或相同的对象。下文还可能包括其他明确的和隐含的定义。
基于背景技术中的相关说明，可以理解的是，现有的识别模型训练方式容易导致在识别过程中出现识别模型老化的问题，往往需要多次重复训练以适应模型识别准确度需求的不断提升以及识别对象种类的不断更新迭代，这将耗费大量的人力成本和时间成本对模型老化进行持续监控和及时更新。为了克服上述技术问题，在本公开提供的一些实施例中，图1示出了提供了一种识别模型的自动迭代训练方法的流程示意图，该种识别模型的自动迭代训练方法包括如下步骤：
步骤101：根据当前训练轮次所需的训练数据，对识别模型执行训练操作。
步骤102：对完成当前训练轮次的识别模型执行推理操作，以获取包含预标注信息的第一识别结果。
步骤103：校验第一识别结果，以获取包含校验信息的第二识别结果。
步骤104：比对识别模型的前一个训练轮次的第一识别结果和当前训练轮次的第二识别结果，以生成下一个训练轮次所需的训练数据。
步骤105：重复上述步骤101至步骤104以实现识别模型的自动迭代训练。其中，相邻的两个训练轮次之间可以间隔预设的模型迭代时间。
可以理解的是，在每个训练轮次完成后，可以基于当前最优的模型进行推理，并由机器生成预标注结果(即为上述第一识别结果)，然后由复核人员基于标注结果进行人工复核和微调(复核和微调处理后的结果即为上述第二识别结果)。
于上述实施例中，本公开提供的技术方案可以使用基于Pandas(一种基于Python计算机编程语言的数值计算扩展工具，其中纳入了大量库和一些标准的数据模型，提供了高效地操作大型数据集所需的工具)实现的数据库，利用其相关特性，快速灵活创建所需训练数据，从而极大减少维护和使用成本；该数据库还可以同时保存与标注结果和人工复核结果并记录两者之间的差异。通过将每次获得新的训练图像时优化训练模型所进行的训练被称为一轮训练，那么优化识别模型可以根据当前识别结果与前一轮标注结果件的差异性生成新的训练集进行相应的更新迭代。在具体实现过程中，可以通过设定模型迭代时间以便模型自身实现自动迭代和更新。
进一步地，在实现对识别模型进行自动迭代训练的基础上，可以对模型的训练过程进行进一步的优化：可以理解的是，在现有技术中，识别模型的质量与人工标注训 练数据的质量密切相关，而人工标注训练数据又存在人工成本高、工作量大、标注质量不一等诸多问题，导致识别模型的自动迭代训练效果差异化明显。此外，现有的图像识别模型往往仅应用于行人检测、人脸识别等通用技术领域，无法满足特定技术领域中超大分辨率缺陷检测、模型自适应迭代升级等需求。
为了克服上述技术问题，在本申请的一些实施例中，图2示出了一种对识别模型执行训练操作的流程示意图。如图2所示，具体可以包括如下步骤：
通过优选训练集对识别模型进行训练，以生成预训练模型；
对预训练模型进行优化处理，以将满足预设评估条件的预训练模型作为完成当前训练轮次的识别模型
步骤201：划分待识别图像，以获取前景区域。可以理解的是，通过将前景区域与背景区域进行划分，能够减少计算资源的消耗，同时减少复杂背景区域对于前景的干扰。于上述步骤201中可以使用前景分割模型实现划分操作，本领域技术人员可以根据实际需要选择合适的划分手段，在此不做限定。
步骤202：对前景区域进行第一预设处理，以获取包含目标物的最小外接矩形标记区域。其中有关第一预设处理的具体实现将于后文中进行详细阐释和说明。
步骤203：对待识别图像进行第二预设处理，以获取包含最小外接矩形标记区域的优选训练集。其中有关第二预设处理的具体实现将于后文中进行详细阐释和说明。
步骤204：通过优选训练集对预设的识别模型进行训练，以生成预训练模型。
步骤205：对预训练模型进行优化处理，以将满足预设评估条件的预训练模型作为完成当前训练轮次的识别模型。
前述步骤201至步骤205所提供的识别模型的自动迭代训练方法一方面能够克服人工标注存在的人工成本高、工作量大、标注质量不一的问题，另一方面能够应用于各种特定应用场景中：在本公开的一种应用场景中，可以将上述识别模型的自动迭代训练方法应用至对风电叶片的巡检图像识别中。可以理解的是，在利用图像识别技术进行风电叶片巡检的过程中，可以使用无人机对围绕风电叶片进行飞行，并在飞行过程中对风电叶片表面进行图像拍摄，后续可以通过对拍摄图像进行图像识别以获取风电叶片表面是否具有缺陷以及缺陷对应的具体类型。
在风电叶片巡检过程中，上述实施例中的待识别图像可以包括包含风机叶片的巡检拍摄图像，前景区域可以包括风机叶片于巡检拍摄图像中的所占区域，目标物包括存在于风机叶片表面的缺陷。以下将统一以风电叶片缺陷识别中的应用为例对上述识 别模型的自动迭代训练方法的具体实现进行阐释和说明。
在本公开的一些实施例中，进一步的，在对前景区域进行第一预设处理前还可以包括如下步骤：
判断前景区域中前景物的边缘线是否能够识别且符合预设特征：若是，继续则进行第一预设处理；若否，则于待识别图像中直接获取包含目标物的标记框，以生成训练数据。
可以理解的是，风电叶片缺陷识别过程中，如果最原始的叶片前景分割模型在某张图上出现了判断失误，则无法通过后续的第一预设处理实现对最小外接矩形标记区域的获取，因此需要在完成前景划分后预先判断是否能够识别出前景区域中前景物的边缘线，以及前景物的边缘线是否与前景物的外部特征相匹配。若任一条件不符则无法获取准确的最小外接矩形标记区域，此时可以直接在原始的待识别图像中直接获取包含目标物的标记框，进而生成对应的训练数据。
在本公开的一些实施例中，进一步的，图3示出了一种对前景区域进行第一预设处理的流程示意图。如图3所示，具体可以包括：
步骤201：获取前景区域中前景物的边缘线，以获取前景物于待识别图像中的所处角度。以风电叶片缺陷识别为例，当正确进行前景区域划分后，可以通过风电叶片的边缘线直观地获取叶片所在的位置，进而可以通过提取边缘线的方式计算风电叶片在待识别图像中所处的大概角度。
步骤302：根据所处角度旋转前景区域，以使前景物处于垂直方向或水平方向。
步骤303：于旋转后的前景区域中获取包含目标物的外接矩形标记框，以作为最小外接矩形标记区域。
可以理解的是，由于风电叶片上出现的缺陷大多是跟随风电叶片方向所分布的，大多数是狭长、倾斜的状态；而当风电叶片在待识别图像处于倾斜状态时，在面对狭长、倾斜的缺陷时，标记框如果要完全包围叶片上的缺陷区域，就必须采用更大的矩形框才能实现。于上述步骤202中，可以利用前景区域对应的掩码信息来转动前景区域，使得风电叶片处于垂直方向或水平方向，此时也就将这些狭长、倾斜的缺陷旋转至垂直方向或水平方向，此时进行外接矩形标记框的标记所能够得到的最小外接矩形标记区域，相较于直接进行缺陷识别框的标记能够进一步增加缺陷前景的占比。
在本公开的一些实施例中，进一步的，图4示出了一种对待识别图像进行第二预设处理流程示意图。如图4所示，具体可以包括：
步骤401：对待识别图像根据预设窗口大小进行滑动窗口裁剪，以获取若干与最小外接矩形标记区域存在重叠区域的裁剪图像。可以理解的是，在通常的人工智能图像识别算法中，输入图像的分辨率可以为1333*800像素。而在风电叶片缺陷识别应用中，在巡检过程中获得的拍摄图片，其分辨率均超过了2000万像素，这样庞大的拍摄图片显然不适合直接作为图像直接输入，需要通过滑动窗口裁剪的方式进行预处理。
在执行滑动窗口裁剪的过程中，可以在待识别图像中设置多个固定大小的滑动窗口，进而逐一计算每个滑动窗口与最小外接矩形标记区域的重合度，若重合度高于预设阈值才将该滑动窗口对应的裁剪图像作为合格的训练数据。
步骤402：对裁剪图像进行数据增强处理，以生成训练数据。其中，数据增强处理可以采用采用mosaic算法来增强数据，相当于增大了4倍的批量图像数量大小，有效节约计算资源，同时基于mosaic算法的自身特性在数据增强过程中执行了随机左右颠倒、随机颜色转换，随机大小缩放，随机仿射变换，随机旋转等操作，有效提升模型的泛化能力。于上述实施例中，最终可以将增强后得到的四张裁剪图像之间进行拼接以获取训练所需的训练数据。
在本公开的一些实施例中，进一步的，在根据训练数据进行预训练模型的训练过程中采用的是本领域技术人员所熟知的方法：即对预先搭建好的框架模型输入训练数据，这里的训练数据是上述实施例中经数据增强后获得的拼接图像。于本实施例中，预先搭建的框架模型可以是基于开源框架mmdectection(一个开源的Python机器学习库所实现的深度学习目标检测工具箱)基础上进行二次开发的。开源框架具备基础的通用性，但并非能够完美适用所有场景，因此需要对开源框架做一些局部调整，以便适合实际训练需求以及后续可能需求的快速迭代和部署要求。本领域技术人员能够根据自身所掌握的知识能够所需完成模型的搭建，并符合相关应用场景的训练要求，在此不做限定。
在本公开的一些实施例中，进一步的，对预训练模型进行优化处理包括如下步骤：采用非极大值合并的方式对预训练模型的识别结果进行后处理。
可以理解的是，在一般的识别模型的自动迭代训练过程中，通常采用非极大值抑制(Non-Maximum Suppression，NMS)的后处理方法。而在本公开的上述实施例中，采用非极大值合并的后处理方式是为了与风电叶片缺陷识别的实际应用需求相契合的。在风电叶片缺陷识别中，要求经图像识别后获得的缺陷识别标记框能够全部包含缺陷所在区域，而通常的非极大值抑制后处理方法可能会在多个符合条件的候选框里选择 一个较优项作为保留的唯一选择，从而放弃其他识别框，而可能导致最终优选出来的识别框仍无法满足将风电叶片表面的单个识别缺陷完全覆盖的需求；反而在考虑多个候选框共同并集对应的最大外界矩形的情况下，才可以完全包围所需识别的缺陷部分，因此采用非极大值合并的方式对预训练模型的识别结果进行后处理是针对上述特定应用领域的定制化设计。
在本公开的一些实施例中，进一步的，预设评估条件包括优选识别模型的召回率大于预设阈值。可以理解的是，在对图像识别模型进行评估的过程中，往往包括召回率和准确率两个维度的评估标准，其中准确率指的是准确识别的图片中识别出目标的概率，而召回率则指的是准确识别出的目标个数与训练集中目标个数的比值。
在风电叶片缺陷识别的应用场景中，对于召回率需求达到99％乃至更高的水平。于上述实施例中，实现高召回率的优化处理包括：
保证模型训练过程中在每一个希望识别出来的缺陷类型上都有足够的正样本量；以及
通过调整识别判断过程中对于阳性目标检测结果的判断阈值，或是判断敏感度。
其中，在保证足够正样本量的过程中，需要在一些较少见的稀少但严重度等级较高的缺陷样本上，执行更多的数据增强工作，使得这些原来样本量就比较少的缺陷类型在训练过程中不会被那些样本量特别多的缺陷类型给影响淹没；而在调整判断阈值的过程中，可以通过查看模型在预测标记框的缺陷类型的概率分布，进而适当降低对真阳预测结果的判断阈值。但值得注意的是，降低预测的阈值就会直接导致模型出现更多假阳预测的情况，进而导致准确率这一评估指标受到影响。在风电叶片缺陷识别的应用场景中，理想的召回率以及准确率的评估标准为召回率大于99％、准确率大于45％。
在本公开的一些实施例中，图5示出了一种识别模型的自动迭代训练系统，应用于前述实施例提供的识别模型的自动迭代训练方法中。具体的，如图5所示，该种识别模型的自动迭代训练系统可以包括：
训练单元001，用于根据当前训练轮次所需的训练数据，对识别模型执行训练操作。
推理单元002，用于对完成当前训练轮次的识别模型执行推理操作，以获取包含预标注信息的第一识别结果。
校验单元003，用于校验第一识别结果，以获取包含校验信息的第二识别结果。
生成单元004，用于比对识别模型的前一个训练轮次的第一识别结果和当前训练轮 次的第二识别结果，以生成下一个训练轮次所需的训练数据。
迭代单元005，用于按次序重复上述功能模块的功能实现以实现识别模型的自动迭代训练。
可以理解的是，上述功能模块中训练单元001至迭代单元005所实现的功能，与前述步骤101至步骤105所执行的操作一一对应，在此不做赘述。
可以理解的是，本公开技术方案的各个方面可以实现为系统、方法或程序产品。因此，本公开技术方案的各个方面可以具体实现为以下形式，即完全的硬件实施方法、完全的软件实施方法(包括固件、微代码等)，或硬件和软件方面结合的实施方法，这里可以统称为“电路”、“模块”或“平台”。
图6根据本公开的一些实施例，示出了一种电子设备的结构示意图，该种电子设备用于实现前述实施例中有关自动迭代方法的实现。下面参照图6来详细描述根据本实施例中的实施方法实施的电子设备600。图6显示的电子设备600仅仅是一个示例，不应对本公开技术方案任何实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600以通用计算设备的形式表现。电子设备600的组建可以包括但不限于：至少一个处理单元610、至少一个存储单元620、连接不同平台组件(包括存储单元620和处理单元610)的总线630、显示单元640等。
其中，存储单元存储有程序代码，程序代码可以被处理单元610执行，使得处理单元610执行本实施例中上述识别模型的自动迭代训练系统中各个功能模块的实现。
存储单元620可以包括易失性存储单元形式的可读介质，例如随机存取单元(RAM)6201和/或高速缓存存储单元6202，可以进一步包括只读存储单元(ROM)6203。
存储单元620还可以包括具有一组(至少一个)程序模块6205的程序/实用工具6204，这样的程序模块6205包括但不限于：操作系统、一个或多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现
总线630可以表示几类总线结构中的一种或多种，包括存储单元总线或者存储单元控制器、外围总线、图像加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。
音视频信号同步处理设备600也可以与一个或多个外部设备700(例如键盘、指向设备、蓝牙设备等)通信，还可以与一个或者多个使得用户与该电子设备600交互 的设备通信，和/或与使得该电子设备能与一个或多个其他计算设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口650进行。并且，电子设备600还可以通过网络适配器660与一个或者多个网络(例如局域网(LAN)、广域网(WAN)和/或公共网络，例如因特网)通信。网络适配器660可以通过总线630与电子设备600的其他模块通信。应当明白，尽管图6中未示出，可以结合电子设备600使用其他硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储平台等。
在本公开的一些实施例中，还提供了一种计算机可读存储介质，计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时能够实现上述公开中自动迭代系统中的各个功能模块的实现。
尽管本实施例未详尽地列举其他具体的实施方式，但在一些可能的实施方式中，本公开技术方案说明的各个方面还可以实现为一种程序产品的形式，其包括程序代码，当程序产品在终端设备上运行时，程序代码用于使终端设备执行本公开技术方案中自动迭代训练方法中描述的根据本公开技术方案各种实施例中实施方式的步骤。
图7根据本公开的一些实施例示出了一种计算机可读存储介质的结构示意图。如图7所示，其中描述了根据本公开技术方案的实施方式中用于实现上述方法的程序产品800，其可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码，并可以在终端设备，例如个人电脑上运行。当然，依据本实施例产生的程序产品不限于此，在本公开技术方案中，可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
计算机可读存储介质可以包括在基带中或者作为载波一区域传播的数据信号，其中承载了可读程序代码。这种传播的数据信号可以采用多种形式，包括但不限于 电磁信号、光信号或上述的任意合适的组合。可读存储介质还可以是可读存储介质以外的任何可读介质，该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、有线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言的任意组合来编写用于执行本公开技术方案操作的程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、C++等，还包括常规的过程式程序设计语言—诸如C语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、区域地在用户设备上执行、作为一个独立的软件包执行、区域在用户计算设备上区域在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中，远程计算设备可以通过任意种类的网络，包括局域网(LAN)或广域网(WAN)，连接到用户计算设备，或者，可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。
综上所述，通过本公开提出的技术方案，能够通过不同训练轮次间获得的识别结果与校验结果，自动生成识别模型迭代所需的训练数据，并利用这些训练数据进行识别模型的自动更新迭代，以避免识别模型出现老化、无法满足识别需求的情况，同时节省了对于识别模型进行运维升级人力成本，具有可推广价值。
上述描述仅是对本公开技术方案较佳实施例的描述，并非对本公开技术方案范围的任何限定，本公开技术方案领域的普通技术人员根据上述揭示内容做的任何变更、修饰，均属于权利要求书的保护范围。

Claims (10)

  1. 一种识别模型的自动迭代训练方法，其特征在于，包括如下步骤：
    根据当前训练轮次所需的训练数据，对所述识别模型执行训练操作；
    对完成所述当前训练轮次的所述识别模型执行推理操作，以获取包含预标注信息的第一识别结果；
    校验所述第一识别结果，以获取包含校验信息的第二识别结果；
    比对所述识别模型的前一个训练轮次的所述第一识别结果和当前训练轮次的所述第二识别结果，以生成下一个训练轮次所需的训练数据；
    重复上述步骤以实现所述识别模型的自动迭代训练。
  2. 如权利要求1所述的识别模型的自动迭代训练方法，其特征在于，相邻的两个所述训练轮次之间间隔预设的模型迭代时间。
  3. 如权利要求1所述的识别模型的自动迭代训练方法，其特征在于，所述识别模型用于对包含目标物的待识别图像进行识别以获取所述目标物的识别信息；
    所述训练数据包含所述待识别图像。
  4. 如权利要求3所述的识别模型的自动迭代训练方法，其特征在于，所述对识别模型执行训练操作包括如下步骤：
    划分所述待识别图像，以获取对应的前景区域；
    对所述前景区域进行第一预设处理，以获取包含所述目标物的最小外接矩形标记区域；
    对所述待识别图像进行第二预设处理，以获取包含所述最小外接矩形标记区域的优选训练集；
    通过所述优选训练集对所述识别模型进行训练，以生成预训练模型；
    对所述预训练模型进行优化处理，以将满足预设评估条件的所述预训练模型作为完成所述当前训练轮次的所述识别模型。
  5. 如权利要求1所述的识别模型的自动迭代训练方法，其特征在于，所述对前景区域进行第一预设处理包括如下步骤：
    获取所述前景区域中前景物的边缘线，以获取所述前景物于所述待识别图像中的 所处角度；
    根据所处角度旋转所述前景区域，以使所述前景物相对于所述待识别图像处于垂直方向或水平方向；
    于旋转后的所述前景区域中获取包含目标物的外接矩形标记框，以作为所述最小外接矩形标记区域。
  6. 如权利要求1所述的识别模型的自动迭代训练方法，其特征在于，所述对待识别图像进行第二预设处理包括如下步骤：
    对所述待识别图像根据预设窗口大小进行滑动窗口裁剪，以获取若干与所述最小外接矩形标记区域存在重叠区域的裁剪图像；
    对所述裁剪图像进行数据增强处理，以生成所述优选训练集。
  7. 如权利要求1所述的识别模型的自动迭代训练方法，其特征在于，所述对预训练模型进行优化处理包括如下步骤：
    采用非极大值合并的方式对所述预训练模型的识别结果进行后处理。
  8. 一种识别模型的自动迭代训练系统，其特征在于，应用于权利要求1至7中任意一项所述的识别模型的自动迭代训练方法中；
    所述识别模型的自动迭代训练系统包括：
    训练单元，用于根据当前训练轮次所需的训练数据，对所述识别模型执行训练操作；
    推理单元，用于对完成所述当前训练轮次的所述识别模型执行推理操作，以获取包含预标注信息的第一识别结果；
    校验单元，用于校验所述第一识别结果，以获取包含校验信息的第二识别结果；
    生成单元，用于比对所述识别模型的前一个训练轮次的所述第一识别结果和当前训练轮次的所述第二识别结果，以生成下一个训练轮次所需的训练数据；
    迭代单元，用于重复上述步骤以实现所述识别模型的自动迭代训练。
  9. 一种识别模型的自动迭代训练设备，其特征在于，包括：
    存储器，用于存储计算机程序；
    处理器，用于执行所述计算机程序时实现如权利要求1至7中任一项所述的识别模 型的自动迭代训练方法。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1至7中任意一项所述的识别模型的自动迭代训练方法。
PCT/CN2022/119346 2022-08-04 2022-09-16 识别模型的自动迭代训练方法、系统、设备和存储介质 WO2024026990A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210932112.5A CN115272896A (zh) 2022-08-04 2022-08-04 识别模型的自动迭代训练方法、系统、设备和存储介质
CN202210932112.5 2022-08-04

Publications (1)

Publication Number Publication Date
WO2024026990A1 true WO2024026990A1 (zh) 2024-02-08

Family

ID=83748912

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/119346 WO2024026990A1 (zh) 2022-08-04 2022-09-16 识别模型的自动迭代训练方法、系统、设备和存储介质

Country Status (2)

Country Link
CN (1) CN115272896A (zh)
WO (1) WO2024026990A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190385059A1 (en) * 2018-05-23 2019-12-19 Tusimple, Inc. Method and Apparatus for Training Neural Network and Computer Server
CN112287955A (zh) * 2019-07-24 2021-01-29 鲁班嫡系机器人（深圳）有限公司 基于图像的处理、训练、前景提取方法、装置及系统
CN113449773A (zh) * 2021-05-26 2021-09-28 北京有竹居网络技术有限公司 模型更新方法、装置、存储介质及电子设备
CN113920068A (zh) * 2021-09-23 2022-01-11 北京医准智能科技有限公司 一种基于人工智能的身体部位检测方法、装置及电子设备
CN114492787A (zh) * 2021-12-31 2022-05-13 中国科学院自动化研究所 自适应的神经网络训练方法、电子设备、介质和程序产品
US20220189147A1 (en) * 2020-02-13 2022-06-16 Tencent Technology (Shenzhen) Company Limited Object detection model training method and apparatus, object detection method and apparatus, computer device, and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190385059A1 (en) * 2018-05-23 2019-12-19 Tusimple, Inc. Method and Apparatus for Training Neural Network and Computer Server
CN112287955A (zh) * 2019-07-24 2021-01-29 鲁班嫡系机器人（深圳）有限公司 基于图像的处理、训练、前景提取方法、装置及系统
US20220189147A1 (en) * 2020-02-13 2022-06-16 Tencent Technology (Shenzhen) Company Limited Object detection model training method and apparatus, object detection method and apparatus, computer device, and storage medium
CN113449773A (zh) * 2021-05-26 2021-09-28 北京有竹居网络技术有限公司 模型更新方法、装置、存储介质及电子设备
CN113920068A (zh) * 2021-09-23 2022-01-11 北京医准智能科技有限公司 一种基于人工智能的身体部位检测方法、装置及电子设备
CN114492787A (zh) * 2021-12-31 2022-05-13 中国科学院自动化研究所 自适应的神经网络训练方法、电子设备、介质和程序产品

Also Published As

Publication number Publication date
CN115272896A (zh) 2022-11-01

Similar Documents

Publication Publication Date Title
US20210209410A1 (en) Method and apparatus for classification of wafer defect patterns as well as storage medium and electronic device
CN112668696A (zh) 一种基于嵌入式深度学习的无人机电网巡检方法和系统
CN110348522B (zh) 一种图像检测识别方法及系统、电子设备、图像分类网络优化方法及系统
CN111507958A (zh) 目标检测方法、检测模型的训练方法及电子设备
CN110021033A (zh) 一种基于金字塔孪生网络的目标跟踪方法
US11004204B2 (en) Segmentation-based damage detection
CN115393687A (zh) 一种基于双伪标签优化学习的rgb图像半监督目标检测方法
CN113436100B (zh) 用于修复视频的方法、装置、设备、介质和产品
US20220092407A1 (en) Transfer learning with machine learning systems
CN112967248B (zh) 生成缺陷图像样本的方法、装置、介质及程序产品
CN114092759A (zh) 图像识别模型的训练方法、装置、电子设备及存储介质
CN113947571A (zh) 车辆损伤检测模型的训练方法及车辆损伤识别方法
US20230222643A1 (en) Semantic deep learning and rule optimization for surface corrosion detection and evaluation
CN113361572A (zh) 图像处理模型的训练方法、装置、电子设备以及存储介质
CN111368878A (zh) 一种基于ssd目标检测的优化方法、计算机设备和介质
CN113377484A (zh) 弹窗处理方法及装置
CN114330588A (zh) 一种图片分类方法、图片分类模型训练方法及相关装置
US20230245429A1 (en) Method and apparatus for training lane line detection model, electronic device and storage medium
CN113936232A (zh) 一种碎屏识别方法、装置、设备和存储介质
WO2024026990A1 (zh) 识别模型的自动迭代训练方法、系统、设备和存储介质
CN110728229B (zh) 图像处理方法、装置、设备和存储介质
CN113223011A (zh) 基于引导网络和全连接条件随机场的小样本图像分割方法
KR20160128869A (ko) 사전 정보를 이용한 영상 물체 탐색 방법 및 이를 수행하는 장치
US20230008473A1 (en) Video repairing methods, apparatus, device, medium and products
CN111507396A (zh) 缓解神经网络对未知类样本产生错误分类的方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22953783

Country of ref document: EP

Kind code of ref document: A1