Model processing method, device, storage medium and computer equipment

Abstract

The present invention discloses a model processing method, apparatus, storage medium, and computer equipment. The method comprises: processing a first image using an image processing model to obtain a second image corresponding to the first image; processing the second image using the image processing model to obtain a third image corresponding to the second image; and optimizing the image processing model based on the distance between the first and third images. This invention addresses the technical problem of low efficiency in improving the performance of image processing models in related technologies.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a model processing method, device, storage medium and computer equipment. Background Art

[0002] Deep learning refers to a collection of algorithms that apply various machine learning algorithms to multi-layer neural networks to solve various problems involving images, text, and other data. Image processing technology is a key application area for deep learning, with a wide range of applications. In related technologies, image processing models are typically trained using large numbers of image samples. However, achieving high accuracy requires a large number of pre-labeled samples, which is a complex and labor-intensive task. Consequently, these technologies often suffer from low efficiency in improving the performance of image processing models.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present invention provide a model processing method, apparatus, storage medium and computer equipment to at least solve the technical problem of low efficiency in improving the performance of image processing models in related technologies.

[0005] According to one aspect of an embodiment of the present invention, a model processing method is provided, including: using an image processing model to process a first image to obtain a second image corresponding to the first image; using the image processing model to process the second image to obtain a third image corresponding to the second image; and optimizing the image processing model based on the distance between the first image and the third image.

[0006] Optionally, based on the distance between the first image and the third image, optimizing the image processing model includes: constructing a loss function of the distance between the first image and the third image; and optimizing the image processing model by minimizing the loss function.

[0007] Optionally, the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in the target image, and the third image is an image of a second local area in the image to be processed.

[0008] Optionally, using the image processing model to process the first image to obtain a second image corresponding to the first image includes: obtaining the size of the target image; using the alignment module in the image processing model to perform an alignment operation on the first image to obtain a first image with the same size as the target image; using the feature extraction module in the image processing model to extract the first feature of the first image with the same size as the target image, and extracting the second feature of the target image; using the processing module in the image processing model to process the first feature and the second feature to obtain a second image corresponding to the first image.

[0009] Optionally, using the image processing model to process the second image to obtain a third image corresponding to the second image includes: obtaining the size of the image to be processed; using the alignment module in the image processing model to perform an alignment operation on the second image to obtain a second image with the same size as the image to be processed; using the feature extraction module in the image processing model to extract the third feature of the second image with the same size as the image to be processed, and extracting the fourth feature of the image to be processed; using the processing module in the image processing model to process the third feature and the fourth feature to obtain a third image corresponding to the second image.

[0010] Optionally, the method also includes: acquiring an image of a local area in the fourth image, and a fifth image; processing the image of the local area in the fourth image, and the fifth image using an optimized image processing model to obtain a corresponding area image in the fifth image corresponding to the local area in the fourth image.

[0011] Optionally, the image processing model includes an image recognition model for identifying at least one of the following predetermined local areas: a local area in a pedestrian image including a person, a local area in an object image including an object, and a local area in a scene image including a person and an object.

[0012] Optionally, the predetermined local area includes a local area of ​​an image frame captured from a surveillance image video.

[0013] According to another aspect of an embodiment of the present invention, a model processing method is also provided, including: receiving a model optimization instruction through an interactive interface; receiving a first image through the interactive interface based on the model optimization instruction; displaying a model optimization result on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization.

[0014] According to another aspect of an embodiment of the present invention, a model processing method is also provided, including: receiving a first area image through a front-end client, wherein the first area image is an image of a local area of ​​a first predetermined image; the front-end client sends the first area image to a back-end server, and receives a region processing result returned by the back-end server, wherein the region processing result is obtained by processing the optimized image processing model, and the region processing result includes an image of an area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization; the front-end client displays the region processing result.

[0015] According to one aspect of an embodiment of the present invention, a model processing device is also provided, including: a first processing module, used to process a first image using an image processing model to obtain a second image corresponding to the first image; a second processing module, used to process the second image using the image processing model to obtain a third image corresponding to the second image; and an optimization module, used to optimize the image processing model according to the distance between the first image and the third image.

[0016] According to another aspect of an embodiment of the present invention, a model processing device is also provided, including: a first receiving module for receiving a model optimization instruction through an interactive interface; a second receiving module for receiving a first image through the interactive interface based on the model optimization instruction; a first display module for displaying the model optimization result on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization.

[0017] According to another aspect of an embodiment of the present invention, a model processing device is also provided, including: a third receiving module, used to receive a first area image through a front-end client, wherein the first area image is an image of a local area of ​​a first predetermined image; a fourth receiving module, used for the front-end client to send the first area image to a back-end server, and receive a region processing result returned by the back-end server, wherein the region processing result is obtained by processing the optimized image processing model, and the region processing result includes an image of an area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the distance between the first image and the third image, and the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization; a second display module, used for the front-end client to display the region processing result.

[0018] According to one aspect of an embodiment of the present invention, a storage medium is further provided, wherein the storage medium includes a stored program, wherein when the program is run, the device where the storage medium is located is controlled to execute any one of the above-mentioned model processing methods.

[0019] According to another aspect of an embodiment of the present invention, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program; and the processor is configured to execute the computer program stored in the memory, wherein when the computer program is executed, the processor executes any one of the above-described model processing methods.

[0020] In an embodiment of the present invention, an image processing model to be optimized is used to process a first image to obtain a second image corresponding to the first image, and the second image is processed to obtain a third image corresponding to the second image. By constraining the distance between the first image and the third image, the purpose of dual constraint on the processing result is achieved, thereby achieving the technical effect of efficiently optimizing the image processing model, and further solving the technical problem of low efficiency in improving the performance of the image processing model in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0022] Figure 1 A hardware structure block diagram of a computer terminal for implementing the model processing method is shown;

[0023] Figure 2 is a flow chart of a model processing method 1 according to embodiment 1 of the present invention;

[0024] Figure 3 is a flow chart of a second model processing method according to embodiment 1 of the present invention;

[0025] Figure 4 is a flow chart of a model processing method 3 according to embodiment 1 of the present invention;

[0026] Figure 5 is a schematic diagram of a complete pedestrian arbitrary local recognition structure according to an optional embodiment of the present invention;

[0027] Figure 6 is a schematic diagram of an optimization process of an optimization module according to an optional embodiment of the present invention;

[0028] Figure 7 is a structural block diagram of a model processing device 1 according to embodiment 2 of the present invention;

[0029] Figure 8 is a structural block diagram of a second model processing device according to embodiment 2 of the present invention;

[0030] Figure 9 is a structural block diagram of a model processing device 3 according to embodiment 2 of the present invention;

[0031] Figure 10 It is a structural block diagram of a computer terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0035] Deep Learning: Deep learning refers to a collection of machine learning algorithms applied to multi-layer neural networks to solve various problems involving images, text, and other data. Deep learning can generally be categorized as a neural network, but its specific implementation varies greatly. The core of deep learning is feature learning, which aims to obtain hierarchical feature information through layered networks, thereby solving important problems that previously required manual feature design.

[0036] Artificial Neural Networks (ANNs): ANNs have been a research hotspot in the field of artificial intelligence since the 1980s. They are a computational model that abstracts the neural networks in the human brain from an information processing perspective, forming different networks based on different connection methods.

[0037] Person Recognition: In the embodiments of the present invention, person recognition refers to taking a pedestrian image as input and outputting a pedestrian high-dimensional feature vector or pedestrian attribute discrimination result through methods such as machine learning.

[0038] Partial Person Recognition: In embodiments of the present invention, partial person recognition uses a partial pedestrian image of any region as input and outputs a high-dimensional feature vector of the pedestrian through machine learning and other methods. In applications such as image search, similarity comparisons are obtained by calculating the Euclidean or cosine distance between high-dimensional feature vectors. Generally, closer feature vectors correspond to people with higher semantic similarity, meaning they are more likely to be the same person.

[0039] Correspondence Learning: In this embodiment of the present invention, Correspondence Learning refers to the algorithm automatically finding semantically corresponding local regions in a target image based on a given local region, without manual annotation. For example, the algorithm can find the coordinates of the footsteps in another image of a pedestrian based on the input of the human foot region.

[0040] Example 1

[0041] According to an embodiment of the present invention, a method embodiment of a model processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] The method embodiment provided in Example 1 of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing the model processing method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (shown as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0043] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0044] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the model processing method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the vulnerability detection method of the above-mentioned application. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0045] The transmission device is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0046] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0047] Under the above operating environment, this application provides Figure 2 The model processing method shown. Figure 2 : is a flow chart of the model processing method 1 according to embodiment 1 of the present invention. Figure 2 As shown, the method includes the following steps:

[0048] Step S202: Processing the first image using an image processing model to obtain a second image corresponding to the first image;

[0049] Step S204: Process the second image using an image processing model to obtain a third image corresponding to the second image;

[0050] Step S206: Optimize the image processing model according to the distance between the first image and the third image.

[0051] Through the above steps, the image processing model to be optimized is used to process the first image to obtain a second image corresponding to the first image, and the second image is processed to obtain a third image corresponding to the second image. By constraining the distance between the first image and the third image, the purpose of dual constraint on the processing result is achieved, thereby achieving the technical effect of efficiently optimizing the image processing model, and further solving the technical problem of low efficiency in improving the performance of the image processing model in related technologies.

[0052] As an optional embodiment, the execution subject of the above method can be any computing device that can be used to perform calculations, for example, it can be an independent computer terminal, a computer cluster with strong computing capabilities, or a server deployed with computing tasks.

[0053] As an optional embodiment, when optimizing the image processing model according to the distance between the first image and the third image, a variety of methods can be used. For example, the following method can be used: constructing a loss function for the distance between the first image and the third image; and optimizing the image processing model by minimizing the loss function. It should be noted that the form of expressing the distance between the first image and the third image here can be diverse. For example, it can be the Euclidean distance that represents the coordinates between the first image and the third image, or it can be the cosine distance that represents the distance between the first image and the third image. It is not specifically limited here. In addition, the form of the loss function constructed here can also be diverse, as long as it can measure the distance between the first image and the third image. For example, it can be a triplet loss function, a cross entropy loss function, etc.

[0054] As an optional embodiment, when constructing a loss function for the distance between the first image and the third image; and optimizing the image processing model by minimizing the loss function, the constructed loss function can be a single type of loss function, for example, the triple loss function referred to above, or a cross-entropy loss function; or it can be a combination of multiple types of loss functions, for example, a total loss function obtained by weighted summation of the triple loss function and the cross-entropy loss function, wherein the weight of each loss function can be determined based on the optimization performance of the corresponding loss function. For example, if the historical optimization performance of the loss function is relatively high, the weight coefficient of the combination can be set to be larger; if the historical optimization performance of the loss function is relatively low, the weight coefficient of the combination can be set to be smaller.

[0055] As an optional embodiment, the image processing model can be used to process local areas in a complete image. That is, for a local area in a complete image, a corresponding area corresponding to the local area is processed from the target image. For example, the first image can be an image of the first local area in the image to be processed, the second image can be an image of the local area in the target image, and the third image can be an image of the second local area in the image to be processed. That is, the second image is an image of the corresponding area in the target image corresponding to the first local area in the image to be processed, and the third image is an image of the corresponding area in the image to be processed corresponding to the local area in the target image.

[0056] As an optional embodiment, the following method can be used to process a first image using an image processing model to obtain a second image corresponding to the first image: obtain the size of the target image; use the alignment module in the image processing model to perform an alignment operation on the first image to obtain a first image with the same size as the target image; use the feature extraction module in the image processing model to extract the first feature of the first image with the same size as the target image, and extract the second feature of the target image; use the processing module in the image processing model to process the first feature and the second feature to obtain a second image corresponding to the first image. It should be noted that the alignment module, feature extraction module, and processing module included in the above-mentioned image processing model can all have various structures, as long as they can respectively realize the above-mentioned alignment function, feature extraction function, and processing function.

[0057] As an optional embodiment, the second image is processed by an image processing model to obtain a third image corresponding to the second image. The above method for obtaining the second image corresponding to the first image can also be used to process the second image to obtain a third image corresponding to the second image. For example, the following method can be used: obtain the size of the image to be processed; use the alignment module in the image processing model to perform an alignment operation on the second image to obtain a second image with the same size as the image to be processed; use the feature extraction module in the image processing model to extract the third feature of the second image with the same size as the image to be processed, and extract the fourth feature of the image to be processed; use the processing module in the image processing model to process the third feature and the fourth feature to obtain a third image corresponding to the second image.

[0058] As an optional embodiment, after obtaining an optimized image processing model, the optimized image processing model can be used to process the image. For example, a corresponding local image corresponding to a predetermined local area image can be processed in a predetermined image. Using the optimized image processing model for processing effectively improves the accuracy of image processing. For example, using the optimized image processing model to process the image can be performed in the following manner: obtaining an image of a local area in a fourth image and a fifth image; processing the image of the local area in the fourth image and the fifth image using the optimized image processing model, and obtaining an image of a corresponding area in the fifth image corresponding to the local area in the fourth image.

[0059] As an optional embodiment, the above-mentioned image processing model may include an image recognition model for identifying local areas of various types of images. For example, it can be used to identify local areas in pedestrian images that include people; for another example, it can be used to identify local areas in scene images that include people and objects; for another example, it can be used to identify local areas in object images that include objects.

[0060] As an optional embodiment, the pedestrian images may include multiple types, for example, image frames captured from surveillance video. By identifying the captured image frames from the surveillance video, the local area of ​​the person included in the image frame can be efficiently identified, thereby improving the effectiveness of surveillance.

[0061] This application also provides Figure 3 The model processing method shown. Figure 3 Flowchart of the second model processing method according to embodiment 1 of the present invention. Figure 3 As shown, the method includes the following steps:

[0062] Step S302: receiving a model optimization instruction through an interactive interface;

[0063] Step S304: receiving a first image through an interactive interface based on the model optimization instruction;

[0064] Step S306, displaying the model optimization results on the interactive interface, wherein the model optimization results include the optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization.

[0065] Through the above steps, the model optimization instruction is received through the interactive interface, and the model optimization result is displayed on the interactive interface, wherein the image processing model to be optimized is used to process the first image to obtain the second image corresponding to the first image, and the second image is processed to obtain the third image corresponding to the second image. By constraining the distance between the first image and the third image, the purpose of the dual constraint on the processing result is achieved, thereby achieving the technical effect of efficiently optimizing the image processing model, and further solving the technical problem of low efficiency in improving the performance of the image processing model in the related technology.

[0066] This application also provides Figure 4 The model processing method shown. Figure 4 : is a flow chart of the model processing method 3 according to embodiment 1 of the present invention. Figure 4 As shown, the method includes the following steps:

[0067] Step S402: receiving a first region image through a front-end client, wherein the first region image is an image of a partial region of a first predetermined image;

[0068] In step S404, the front-end client sends the first region image to the back-end server, and receives a region processing result returned by the back-end server, wherein the region processing result is obtained by processing the optimized image processing model, and the region processing result includes an image of a region in the second predetermined image corresponding to the local region of the first predetermined image, wherein the optimized image processing model optimizes the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization;

[0069] Step S406: The front-end client displays the regional processing result.

[0070] Through the above steps, after the image of the local area is received by the front-end client, it is sent to the back-end server, and the back-end server returns the corresponding area processing result, wherein the area processing result is obtained by processing the optimized image processing model. In the process of optimizing the image processing model, the image processing model is used to process the first image to obtain the second image corresponding to the first image, and the second image is processed to obtain the third image corresponding to the second image. By constraining the distance between the first image and the third image, the purpose of dual constraint on the processing result is achieved, thereby achieving the technical effect of efficiently optimizing the image processing model, and then solving the technical problem of low efficiency in improving the performance of the image processing model in the related technology.

[0071] This application also provides an optional embodiment to make this optional embodiment clearer and more specific. In this optional embodiment, the image processing model is an image recognition model, the image to be recognized is a pedestrian image as an example, and the recognition basis is an image of a local area of ​​the pedestrian image. The recognition object is to identify a corresponding area in the target image corresponding to the local area of ​​the pedestrian image.

[0072] Pedestrian recognition technology is an important application direction of image recognition technology. However, most current pedestrian recognition technologies assume that the input is a complete pedestrian image, and incomplete input is rarely considered. Incomplete input will have a great negative impact on recognition performance.

[0073] There are generally two main technical aspects of arbitrary local pedestrian recognition. The first is to learn a multi-scale feature to adapt to arbitrary input sizes. The second is to find the area in the target image that is related to the given local input. This can be done by modeling the relationship between the given local region features and the target image features through functions such as least squares to obtain the weight coefficients between different regions of the target image features. When performing feature similarity comparison, the given local region features and the weighted target image features are used for calculation. However, methods that use functions such as least squares to model relationships are inefficient and complex because they use artificially set functions to model the semantic distance between regions, making them inflexible.

[0074] In view of this, in an embodiment of the present invention, a dual constraint technology based on local corresponding areas is proposed. This dual constraint technology utilizes the duality of the ability to find corresponding areas based on given input. That is, if the algorithm can find the corresponding local area y in the pedestrian image Y based on the local area x in the given pedestrian image X, then it can also output the opposite, that is, output the local area x in the pedestrian image X based on the found corresponding area y.

[0075] Figure 5is a schematic diagram of a complete pedestrian arbitrary local recognition structure according to an optional embodiment of the present invention, such as Figure 5 As shown, x p is any local area image input, y is the target image, x p After passing through the alignment module R based on the Spatial Transform Networks, an image of the same size as y is obtained. The corresponding features are obtained by the same feature extraction module F as y. The local dual constraint technology proposed in the optional embodiment of the present invention is used to optimize the module G. Its function is to output the target region position (dashed box in the right-leaning region) in the target image features that corresponds to the semantics of the input region based on the given local region features (solid box in the left-leaning region) and the target image features (right-leaning region).

[0076] Figure 6 is a schematic diagram of the optimization process of the optimization module according to an optional embodiment of the present invention, such as Figure 6 As shown in , the pixel domain is used to represent the feature domain. Figure 6 In the example, based on the assumption that module G can predict the semantically corresponding area (the black solid box area on the left to the dotted text area on the right), it can also predict the semantically corresponding area (the dotted text area on the right to the white solid box area on the left). Therefore, this constraint is to minimize the distance between the result of the backward prediction and the input position, that is, to minimize Figure 6 The white double-headed arrow in the middle represents the distance. This minimization process is achieved by minimizing the loss function.

[0077] It should be noted that, in an optional embodiment of the present invention, the alignment module and the feature extraction module are not limited to a specific form, and are applicable to any feature extraction structure that can retain relevant position information. In an optional embodiment of the present invention, module G is usually a convolutional neural network structure, but is not limited to this structural form, and is applicable to any feature extraction structure. In an optional embodiment of the present invention, minimizing the distance can be achieved by minimizing the Euclidean distance of the coordinates of the two regions (blue block and pink block), but is not limited to this distance form, and any loss function that measures the distance between the two regions is applicable.

[0078] The method provided in the aforementioned optional embodiment effectively locates the corresponding region in the target image based on a given local region image without requiring additional manual annotation, thereby enhancing the performance of pedestrian recognition in any local region. Furthermore, the method provided in this optional embodiment requires only a single inference step during deployment, ensuring real-time efficiency and achieving higher recognition accuracy on public datasets than methods used in related technologies.

[0079] Through this optional implementation, a technology for arbitrary local pedestrian recognition based on corresponding region dual constraints is provided. This technology based on corresponding region dual constraints implements dual constraints between local regions, rather than instance-level dual constraints. This technology based on corresponding region dual constraints can utilize the duality of the ability to predict corresponding regions and achieve unsupervised learning capabilities by minimizing the forward and reverse prediction errors. This technology based on corresponding region dual constraints can effectively predict the corresponding local region in the target image based on a given local region, and on this basis improve the performance of arbitrary local pedestrian recognition.

[0080] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0081] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0082] Example 2

[0083] According to an embodiment of the present invention, a device for implementing the above-mentioned model processing method 1 is also provided. Figure 7 : is a structural block diagram of a model processing device according to embodiment 2 of the present invention. Figure 7 As shown, the device includes: a first processing module 72, a second processing module 74 and an optimization module 76. The device is described below.

[0084] The first processing module 72 is used to process the first image using the image processing model to obtain a second image corresponding to the first image; the second processing module 74 is connected to the above-mentioned first processing module 72, and is used to process the second image using the image processing model to obtain a third image corresponding to the second image; the optimization module 76 is connected to the above-mentioned second processing module 74, and is used to optimize the image processing model according to the distance between the first image and the third image.

[0085] It should be noted that the first processing module 72, the second processing module 74, and the optimization module 76 correspond to steps S202 to S206 in Example 1. The examples and application scenarios implemented by these modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in Example 1.

[0086] According to an embodiment of the present invention, a device for implementing the above-mentioned model processing method 2 is also provided. Figure 8 is a structural block diagram of a second model processing device according to embodiment 2 of the present invention, as shown in FIG. Figure 8 As shown, the device includes: a first receiving module 82, a second receiving module 84 and a first display module 86. The device is described below.

[0087] A first receiving module 82 is used to receive a model optimization instruction through an interactive interface; a second receiving module 84 is connected to the first receiving module 82 and is used to receive a first image through an interactive interface based on the model optimization instruction; a first display module 86 is connected to the second receiving module 84 and is used to display the model optimization result on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization.

[0088] It should be noted that the first receiving module 82, the second receiving module 84, and the first display module 86 correspond to steps S302 to S306 in Example 1. The examples and application scenarios implemented by these modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in Example 1.

[0089] According to an embodiment of the present invention, a device for implementing the above-mentioned model processing method 3 is also provided. Figure 9 : is a structural block diagram of a model processing device 3 according to embodiment 2 of the present invention, as shown in FIG. Figure 9 As shown, the device includes: a third receiving module 92, a fourth receiving module 94 and a second display module 96. The device is described below.

[0090] The third receiving module 92 is used to receive the first area image through the front-end client, wherein the first area image is an image of a local area of ​​the first predetermined image; the fourth receiving module 94 is connected to the above-mentioned third receiving module 92, and is used for the front-end client to send the first area image to the back-end server, and receive the area processing result returned by the back-end server, wherein the area processing result is obtained by processing the optimized image processing model, and the area processing result includes the image of the area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization; the second display module 96 is connected to the above-mentioned fourth receiving module 94, and is used for the front-end client to display the area processing result.

[0091] It should be noted that the third receiving module 92, the fourth receiving module 94, and the second display module 96 correspond to steps S402 to S406 in Example 1. The examples and application scenarios implemented by these modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in Example 1.

[0092] Example 3

[0093] The embodiment of the present invention can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal can also be replaced by a terminal device such as a mobile terminal.

[0094] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of a computer network.

[0095] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the model processing method of the application: using the image processing model to process the first image to obtain a second image corresponding to the first image; using the image processing model to process the second image to obtain a third image corresponding to the second image; optimizing the image processing model based on the distance between the first image and the third image.

[0096] Optionally, Figure 10 1 is a block diagram of a computer terminal according to an embodiment of the present invention. Figure 10 As shown, the computer terminal may include: one or more (only one is shown in the figure) processors 102, a memory 104, etc.

[0097] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the model processing method and device in the embodiments of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned model processing method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0098] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: use the image processing model to process the first image to obtain a second image corresponding to the first image; use the image processing model to process the second image to obtain a third image corresponding to the second image; optimize the image processing model based on the distance between the first image and the third image.

[0099] Optionally, the processor may also execute the program code of the following steps: optimizing the image processing model according to the distance between the first image and the third image, including: constructing a loss function of the distance between the first image and the third image; and optimizing the image processing model by minimizing the loss function.

[0100] Optionally, the processor may also execute program code of the following steps: the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in the target image, and the third image is an image of a second local area in the image to be processed.

[0101] Optionally, the processor may also execute the program code of the following steps: using an image processing model to process a first image to obtain a second image corresponding to the first image, including: obtaining the size of a target image; using an alignment module in the image processing model to perform an alignment operation on the first image to obtain a first image with the same size as the target image; using a feature extraction module in the image processing model to extract a first feature of the first image with the same size as the target image, and extracting a second feature of the target image; using a processing module in the image processing model to process the first feature and the second feature to obtain a second image corresponding to the first image.

[0102] Optionally, the processor may also execute the program code of the following steps: using an image processing model to process the second image to obtain a third image corresponding to the second image, including: obtaining the size of the image to be processed; using an alignment module in the image processing model to perform an alignment operation on the second image to obtain a second image with the same size as the image to be processed; using a feature extraction module in the image processing model to extract a third feature of the second image with the same size as the image to be processed, and extracting a fourth feature of the image to be processed; using a processing module in the image processing model to process the third feature and the fourth feature to obtain a third image corresponding to the second image.

[0103] Optionally, the above-mentioned processor can also execute the program code of the following steps: obtaining an image of the local area in the fourth image, and a fifth image; using the optimized image processing model to process the image of the local area in the fourth image, and the fifth image, to obtain a corresponding area image in the fifth image corresponding to the local area in the fourth image.

[0104] Optionally, the above-mentioned processor can also execute the program code of the following steps: the image processing model includes an image recognition model, which is used to identify at least one of the following predetermined local areas: a local area in a pedestrian image including a person, a local area in an object image including an object, and a local area in a scene image including a person and an object.

[0105] Optionally, the processor may further execute program code of the following steps: the predetermined local area includes a local area of ​​an image frame captured from the surveillance image video.

[0106] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receive a model optimization instruction through the interactive interface; based on the model optimization instruction, receive a first image through the interactive interface; display the model optimization result on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization.

[0107] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receiving a first area image through the front-end client, wherein the first area image is an image of a local area of ​​the first predetermined image; the front-end client sends the first area image to the back-end server, and receives the area processing result returned by the back-end server, wherein the area processing result is obtained by processing the optimized image processing model, and the area processing result includes an image of an area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization; the front-end client displays the area processing result.

[0108] According to an embodiment of the present invention, a first image is processed using an image processing model to be optimized to obtain a second image corresponding to the first image, and the second image is processed to obtain a third image corresponding to the second image. By constraining the distance between the first image and the third image, the purpose of dual constraint on the processing result is achieved, thereby achieving the technical effect of efficiently optimizing the image processing model, and further solving the technical problem of low efficiency in improving the performance of the image processing model in related technologies.

[0109] It can be understood by those skilled in the art that Figure 10 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 10 It does not limit the structure of the above electronic device. For example, the computer terminal 10 may also include Figure 10 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 10 Different configurations shown.

[0110] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0111] Example 4

[0112] The embodiment of the present invention further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the model processing method provided in the above embodiment 1.

[0113] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0114] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: processing the first image using an image processing model to obtain a second image corresponding to the first image; processing the second image using an image processing model to obtain a third image corresponding to the second image; and optimizing the image processing model based on the distance between the first image and the third image.

[0115] Optionally, in this embodiment, the storage medium is also configured to store program code for performing the following steps: optimizing the image processing model based on the distance between the first image and the third image includes: constructing a loss function of the distance between the first image and the third image; and optimizing the image processing model by minimizing the loss function.

[0116] Optionally, in this embodiment, the storage medium is also configured to store program code for executing the following steps: the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in the target image, and the third image is an image of a second local area in the image to be processed.

[0117] Optionally, in this embodiment, the storage medium is also configured to store program codes for executing the following steps: using an image processing model to process a first image to obtain a second image corresponding to the first image, including: obtaining the size of the target image; using an alignment module in the image processing model to perform an alignment operation on the first image to obtain a first image with the same size as the target image; using a feature extraction module in the image processing model to extract a first feature of the first image with the same size as the target image, and extracting a second feature of the target image; using a processing module in the image processing model to process the first feature and the second feature to obtain a second image corresponding to the first image.

[0118] Optionally, in this embodiment, the storage medium is also configured to store program codes for executing the following steps: using an image processing model to process the second image to obtain a third image corresponding to the second image, including: obtaining the size of the image to be processed; using an alignment module in the image processing model to perform an alignment operation on the second image to obtain a second image with the same size as the image to be processed; using a feature extraction module in the image processing model to extract a third feature of the second image with the same size as the image to be processed, and extracting a fourth feature of the image to be processed; using a processing module in the image processing model to process the third feature and the fourth feature to obtain a third image corresponding to the second image.

[0119] Optionally, in this embodiment, the storage medium is also configured to store program code for performing the following steps: obtaining an image of the local area in the fourth image, and a fifth image; processing the image of the local area in the fourth image, and the fifth image using an optimized image processing model to obtain a corresponding area image in the fifth image corresponding to the local area in the fourth image.

[0120] Optionally, in this embodiment, the storage medium is also configured to store program code for performing the following steps: the image processing model includes an image recognition model, which is used to identify at least one of the following predetermined local areas: a local area in a pedestrian image including a person, a local area in an object image including an object, and a local area in a scene image including a person and an object.

[0121] Optionally, in this embodiment, the storage medium is further configured to store program codes for executing the following steps: the predetermined local area includes a local area of ​​an image frame captured from the surveillance image video.

[0122] Optionally, in this embodiment, the storage medium is configured to store program code for executing the following steps: receiving a model optimization instruction through an interactive interface; receiving a first image through the interactive interface based on the model optimization instruction; displaying the model optimization result on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization.

[0123] Optionally, in this embodiment, the storage medium is also configured to store program codes for executing the following steps: receiving a first area image through a front-end client, wherein the first area image is an image of a local area of ​​a first predetermined image; the front-end client sends the first area image to a back-end server, and receives a region processing result returned by the back-end server, wherein the region processing result is obtained by processing the optimized image processing model, and the region processing result includes an image of an area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, and the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization; the front-end client displays the region processing result.

[0124] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0125] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0127] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0128] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0129] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0130] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A model processing method, characterized in that: include: Processing a first image using an image processing model to obtain a second image corresponding to the first image, wherein the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in a target image, the image to be processed and the target image are images that have not been manually annotated, and the second image is determined based on a first feature of the first image having the same size as the target image and a second feature of the target image; Processing the second image using the image processing model to obtain a third image corresponding to the second image, wherein the third image is an image of a second local area in the image to be processed; The image processing model is optimized according to a loss function of the distance between the first image and the third image.

2. The method according to claim 1, characterized in that Optimizing the image processing model according to a loss function of a distance between the first image and the third image includes: Constructing a loss function of the distance between the first image and the third image; The image processing model is optimized by minimizing the loss function.

3. The method according to claim 1, characterized in that Processing the first image using the image processing model to obtain a second image corresponding to the first image includes: Obtaining the size of the target image; Using an alignment module in the image processing model, perform an alignment operation on the first image to obtain a first image of the same size as the target image; Using a feature extraction module in the image processing model to extract a first feature of a first image having the same size as the target image, and extracting a second feature of the target image; The first feature and the second feature are processed using a processing module in the image processing model to obtain a second image corresponding to the first image.

4. The method according to claim 1, wherein Processing the second image using the image processing model to obtain a third image corresponding to the second image includes: Obtaining the size of the image to be processed; Using the alignment module in the image processing model, perform an alignment operation on the second image to obtain a second image with the same size as the image to be processed; Using a feature extraction module in the image processing model to extract a third feature of a second image having the same size as the image to be processed, and extracting a fourth feature of the image to be processed; The third feature and the fourth feature are processed using a processing module in the image processing model to obtain a third image corresponding to the second image.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: acquiring an image of the local area in the fourth image and a fifth image; The optimized image processing model is used to process the image of the local area in the fourth image and the fifth image to obtain a corresponding area image in the fifth image corresponding to the local area in the fourth image.

6. The method according to claim 5, characterized in that The image processing model includes an image recognition model for identifying at least one of the following predetermined local areas: a local area in a pedestrian image including a person, a local area in an object image including an object, and a local area in a scene image including a person and an object.

7. The method according to claim 6, characterized in that The predetermined local area includes a local area of ​​an image frame captured from a surveillance image video.

8. A model processing method, characterized in that: include: Receive model optimization instructions through the interactive interface; Based on the model optimization instruction, receiving a first image through the interactive interface; The model optimization result is displayed on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the loss function of the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization, the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in the target image, the image to be processed and the target image are images that have not been manually annotated, the second image is determined based on a first feature of the first image having the same size as the target image and a second feature of the target image, and the third image is an image of a second local area in the image to be processed.

9. A model processing method, characterized in that: include: Receiving a first area image through a front-end client, wherein the first area image is an image of a local area of ​​a first predetermined image; The front-end client sends the first area image to the back-end server, and receives the area processing result returned by the back-end server, wherein the area processing result is obtained by processing the optimized image processing model, and the area processing result includes an image of an area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the loss function of the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization, the first image is an image of the first local area in the image to be processed, the second image is an image of the local area in the target image, the image to be processed and the target image are images that have not been manually annotated, the second image is determined based on the first feature of the first image and the second feature of the target image that are the same size as the target image, and the third image is an image of the second local area in the image to be processed; The front-end client displays the regional processing result.

10. A model processing device, characterized in that: include: a first processing module, configured to process a first image using an image processing model to obtain a second image corresponding to the first image, wherein the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in the target image, the image to be processed and the target image are images that have not been manually annotated, and the second image is determined based on a first feature of the first image having the same size as the target image and a second feature of the target image; a second processing module, configured to process the second image using the image processing model to obtain a third image corresponding to the second image, wherein the third image is an image of a second local area in the image to be processed; An optimization module is used to optimize the image processing model according to a loss function of the distance between the first image and the third image.

11. A model processing device, characterized in that: include: A first receiving module, configured to receive a model optimization instruction through an interactive interface; A second receiving module, configured to receive a first image through the interactive interface based on the model optimization instruction; A first display module is used to display the model optimization result on the interactive interface, wherein the model optimization result includes an optimized image processing model, wherein the optimized image processing model is obtained by optimizing the image processing model according to the loss function of the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization, the first image is an image of a first local area in the image to be processed, the second image is an image of a local area in the target image, the image to be processed and the target image are images that have not been manually annotated, the second image is determined based on the first feature of the first image having the same size as the target image and the second feature of the target image, and the third image is an image of the second local area in the image to be processed.

12. A model processing device, characterized in that: include: A third receiving module is configured to receive a first area image through a front-end client, wherein the first area image is an image of a local area of ​​the first predetermined image; a fourth receiving module, configured for the front-end client to send the first area image to the back-end server, and to receive the area processing result returned by the back-end server, wherein the area processing result is obtained by processing the optimized image processing model, and the area processing result includes an image of an area corresponding to the local area of ​​the first predetermined image in the second predetermined image, wherein the optimized image processing model optimizes the image processing model according to the loss function of the distance between the first image and the third image, the third image is an image corresponding to the second image obtained by processing the second image using the image processing model before optimization, the second image is an image corresponding to the first image obtained by processing the first image using the image processing module before optimization, the first image is an image of the first local area in the image to be processed, the second image is an image of the local area in the target image, the image to be processed and the target image are images that have not been manually annotated, the second image is determined based on the first feature of the first image having the same size as the target image and the second feature of the target image, and the third image is an image of the second local area in the image to be processed; The second display module is used for the front-end client to display the regional processing result.

13. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the device where the storage medium is located is controlled to execute the model processing method according to any one of claims 1 to 9.

14. A computer device, characterized in that: include: memory and processor, The memory stores a computer program; The processor is configured to execute a computer program stored in the memory, and when the computer program is run, the processor is enabled to execute the model processing method according to any one of claims 1 to 9.

Images