Generating composite images for training defect detection systems and applications

Abstract

The invention relates to generating composite images for training defect detection systems and applications. The approaches presented herein provide for generating an image representing a physical object having one or more synthetic but realistic defects or other such changes or enhancements. The generative system may use the features of the defects and the environment to create a three-dimensional (3D) model of both the environment and the defects that may be used to generate one or more images of the defects or combinations of defects in various environments that may have different lighting conditions. The system may generate random changes, semi-random changes, or specific instruction changes of the synthetic environment and defects to simulate different visualizations of the defects under different environmental conditions. The potential system may also simulate different presentations of defects by adding or combining various defect types and simulating different levels of defect severity. By integrating these synthetic defects, the synthetic defect generation system may generate a wide variety of synthetic images, such as synthetic images that may be used to train a defect detection model.

Description

Background Technology

[0001] There are many different industries and operations, such as those related to the manufacture, finishing, and production of various physical objects, in which the ability to identify defects or other unacceptable or unexpected variations in objects is crucial. These defects may include various variations such as scratches, dents, unevenness, or tears on the surface or parts of an object. Traditionally, identifying such defects has relied heavily on manual labor, which is expensive, time-consuming, and prone to human error or variation between different human inspectors. The introduction of artificial intelligence (AI) systems offers a promising solution for reducing labor costs and inspection time, and improving accuracy and consistency, because AI systems can be trained to identify a wide range of defects. However, training AI-based models in a system to identify a near-infinite number of possible defects of different sizes, shapes, orientations, and degrees under varying environmental or lighting conditions requires a large number of annotated training images representing these possibilities. Capturing a sufficient number of images of physical objects with these defects under various lighting and environmental conditions can be extremely expensive and time-consuming. Training a model with an insufficient number and limited variety of images may negatively impact the accuracy of the defect detection model or cause the model to converge on specific types of defects or conditions with sufficient training data. Attached Figure Description

[0002] Various embodiments according to this disclosure will be described with reference to the accompanying drawings, in which:

[0003] Figures 1A to 1B The illustration shows a composite image of an object having one or more defects according to various embodiments;

[0004] Figure 2 The illustration shows an example system environment including a synthetic defect generation system according to various embodiments;

[0005] Figure 3 The illustration shows example block diagrams of modules in a synthetic defect generation system according to various embodiments;

[0006] Figure 4 The illustration shows example block diagrams illustrating modules in a defect simulation module according to various embodiments;

[0007] Figure 5 The illustration shows an example process of training a defect detection model using a generated synthetic image with defects, according to various embodiments.

[0008] Figure 6 The illustrations depict example processes for generating synthetic defects according to various embodiments;

[0009] Figure 7AThe inference and / or training logic according to at least one embodiment is illustrated;

[0010] Figure 7B The inference and / or training logic according to at least one embodiment is illustrated;

[0011] Figure 8 An example data center system according to at least one embodiment is shown;

[0012] Figure 9 A computer system according to at least one embodiment is shown;

[0013] Figure 10 A computer system according to at least one embodiment is shown;

[0014] Figure 11 At least a portion of a graphics processor according to one or more embodiments is shown;

[0015] Figure 12 At least a portion of a graphics processor according to one or more embodiments is shown;

[0016] Figure 13 This is an example data flow diagram of an advanced computing pipeline according to at least one embodiment;

[0017] Figure 14 This is a system diagram of an example system for training, adapting, instantiating, and deploying machine learning models in an advanced computing pipeline, according to at least one embodiment; and

[0018] Figure 15A and Figure 15B A data flow diagram of the process for training a machine learning model according to at least one embodiment is shown, as well as a client-server architecture for enhancing annotation tools using a pre-trained annotation model. Detailed Implementation

[0019] In the following description, various embodiments will be described. Specific configurations and details are set forth for illustrative purposes in order to provide a thorough understanding of the embodiments. However, it will also be apparent to those skilled in the art that the embodiments can be practiced without specific details. Furthermore, well-known features may be omitted or simplified so as not to obscure the described embodiments.

[0020] The systems and methods described herein can be used, but are not limited to, manufacturing and quality inspection systems, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more advanced driver assistance systems (ADAS)), manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, aircraft, boats, shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, aircraft, engineering vehicles, trains, underwater vehicles, remotely controlled vehicles such as drones, and / or other vehicle types. Furthermore, the systems and methods described herein can be used for a variety of purposes, such as, but not limited to, machine control, machine motion, machine driving, synthetic data generation, model training or updating, perception, augmented reality, virtual reality, mixed reality, robotics, security and supervision, simulation and digital twins, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, object or actor simulation and / or digital twins, data center processing, conversational AI, optical transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation for 3D assets, cloud computing, and / or any other suitable application.

[0021] The disclosed embodiments may be included in a variety of different systems, such as automotive systems (e.g., control systems for autonomous or semi-autonomous machines, perception systems for autonomous or semi-autonomous machines), systems implemented using robots, aviation systems, medical systems, manufacturing systems, boating systems, smart area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twin operations, systems implemented using edge devices, systems containing one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least partially in a data center, systems for performing conversational AI operations, systems for performing optical transmission simulations, systems for performing collaborative content creation for 3D assets, systems implemented using language models such as large language models (LLM) or visual language models (VLM), systems implemented at least partially using cloud computing resources, and / or other types of systems.

[0022] Various illustrative embodiments provide approaches to the synthetic generation of images including representations of objects, which may include one or more defects, variations, flaws, or other such enhancements. Objects can be represented using captured images of physical objects or synthetic image data simulating physical objects. Defects (or other enhancements) can be synthetically rendered to be more realistic during display or analysis. In at least one embodiment, a user (or control application, etc.) can specify one or more types of defects to be represented as present in the image to be generated, and can specify aspects such as the degree, size, shape, or other aspects of the defects. The synthetic defect generation system can train and deploy generative models to generate images of objects with realistic defects (or other enhancements), which can be used by defect detection models, such as those used to detect defects generated during manufacturing processes. Such synthetic images can also be advantageously used to train models for generating content in animations, games, or other such applications. In at least one embodiment, the synthetic defect generation system can use predefined features of defects and the environment to create 3D (three-dimensional) models of both the environment and the defects, which can be used to efficiently generate images of defects in various environments. Synthetic defect generation systems can additionally generate random, semi-random, or specific instruction variations of the synthetic environment and / or defects to simulate different visualizations of defects under diverse environmental conditions (such as different lighting or weather conditions, different object placements or orientations, etc.). The system can also simulate different defect presentations by adding or combining various defect types and simulating different defect severity levels. By integrating these synthetic defects, the system can generate diverse synthetic image arrays encompassing multiple defects under different imaging conditions. These diverse synthetic image arrays can be used to train defect detection models.

[0023] The synthetic defect generation system according to at least one embodiment offers several technical advantages and improvements. Traditionally, the development of AI models has relied heavily on the availability of real-world images of objects with defects intended for detection. However, conventional processes face numerous challenges and inefficiencies, which this disclosure addresses. For example, consider the need to train a defect detection model to distinguish between scratches and light reflections on a car, both represented as white lines in an image. To train the model to learn this distinction, it requires a wide variety of annotated images, each clearly illustrating a specific defect, including the annotation of a scratch or reflection. However, reconstructing these specific conditions in reality presents significant challenges. Leaving scratches on a real car is not only costly but can also lead to irreversible damage. Similarly, adjusting lighting to create specific reflective effects is demanding and subject to uncontrollable factors such as weather conditions. However, the synthetic defect generation system outlined in this disclosure allows users to customize environmental conditions and 3D models to generate desired synthetic defects. The synthetic defect generation system according to one or more embodiments of this disclosure is capable of simulating different environmental settings, such as lighting conditions, weather, and reflections, enabling users to create a series of images illustrating various defect scenarios. The generated synthetic images can be used as training data for training robust defect detection models.

[0024] Furthermore, in real-world scenarios, manually creating a wide range of defects on objects is extremely challenging, if not impractical, but nearly impossible. The diversity of defect types, coupled with the varied environmental conditions under which they may occur, makes physically reproducing these situations logically challenging. However, various disclosed embodiments overcome at least some of these and other such challenges by using features that allow the generation of various synthetic defects under diverse environmental conditions, including different lighting conditions, weather scenes, and reflections. A greater variety of images can be generated to enrich the training data used for defect detection models. More importantly, synthetic defect generation systems can recreate hybrid defect scenes where multiple defect types coexist on the same object. Using the disclosed synthetic defect generation systems, users can combine different types of defects in synthetic images under various scenarios. This feature provides a solution for creating complex defect scenes, thereby improving the effectiveness of AI training.

[0025] Based on the teachings and suggestions contained herein, it will be apparent to those skilled in the art that this functionality and other variations thereof may also be used within the scope of various embodiments.

[0026] Figures 1A to 1BThe illustration shows example images of objects including synthetic defects that can be generated according to various embodiments. In one embodiment, such images can be used as training data for a defect detection model. As an example, Figure 1A An image 100 depicts a vehicle 104 illuminated according to clear daytime lighting conditions 106. Image data for the vehicle can be provided using captured images of a physical vehicle or synthetic images generated to provide a realistic representation of the vehicle. In some embodiments, a generative model can be trained to take one type of object as input and generate a synthetic representation of the object independent of any input image data for the vehicle. One or more embodiments include a rendering engine that renders a scene depicting one or more objects with one or more defects based on input or stored information. This information may include a 3D representation or model of the object (e.g., a polygon mesh) and corresponding defects appearing in the rendering of the scene, texture and / or lighting (e.g., albedo, reflectance) assets corresponding to the object, and light transport effects in the scene simulated from the viewpoint of a virtual camera (e.g., via ray or path tracing). Figure 1A Vehicle 102 is illustrated as having a scratch 104 on one of the doors. This scratch 104 does not actually exist on the vehicle but is included in an image 100 of vehicle 104 generated by a trained generative model. In this example, the user may have specified the type of defect, here a scratch 104 in the paint, and the generative model generates an image 100 of vehicle 102 with a realistically appearing scratch. The user may also specify other aspects, such as the number of defects to include, the size or extent of each defect, the location of the defects, etc. In at least one embodiment, such generated image 100 should include defects that are realistic enough to appear to a human observer as actual defects in the represented object and / or be interpreted as real or physical defects (or other enhancements) in the object as determined by an analysis system, process, or operation.

[0027] As mentioned, such images can be used to train AI models (e.g., neural networks) to accurately identify these types of defects. To accurately identify these defects, images exhibiting defect characteristics (such as...) should be used. Figure 1AThe model is trained using a wide variety of training images (illustrated as defect features). Importantly, these images may also need to be annotated for at least some of the training processes. As a challenging scenario for such a model, distinguishing between scratches and light reflections requires training the model with a dataset containing images depicting scratches and light reflections that are visually similar to scratches (or other defects or variations). For example, cloud-like reflections in a vehicle's paint should not be interpreted as imperfections in the paint. The traditional approach to obtaining such images is to manually photograph cars with (and without) similar scratches under various specific lighting conditions to obtain images of the scratches and images illustrating the effects of various light reflections, which can be extremely challenging, expensive, and inefficient. The ability to rapidly synthesize and generate a large number of defect examples under various conditions provides an efficient and cost-effective solution for generating large numbers of training images at a significantly reduced cost.

[0028] For example, the same model can generate another image of a vehicle with different defects and / or under different lighting conditions. Figure 1B The illustration shows a synthetic image 110 with realistic defects generated by a synthetic defect generation system. This system can receive input information about a user-specified defect and one or more desired conditions (such as lighting conditions, environmental conditions, or contextual conditions). For example, Figure 1B Image 110 depicts the same vehicle 102 exhibiting numerous defects under partially cloudy lighting conditions 124. The defects shown in image 110 include scratches 112, 114, orange peeling 116, 120, and dents 122, 124. Figure 1B This also includes light reflection 118 that resembles a scratch under specific lighting conditions but should not be interpreted as a scratch. In some embodiments, the user may have specified any or all of these defects, including aspects of these defects, while in other embodiments, randomly or semi-randomly selected defects or blemishes may be generated, or the algorithm may specify to generate specific defects in which more training data is needed, and so on. In some embodiments, a realistic entire physical object may not exist, but defects may be synthesized to appear to exist in a painted metal panel, which may be unrelated to any type of object actually contained in the panel. This approach also allows the model to be trained on specific defects as well as combinations of similar or different types of defects.

[0029] The synthetic defect generation system in at least one embodiment can create a 3D (three-dimensional) model based on received instructions, the 3D (three-dimensional) model specifying environmental features and defect attributes, such as... Figure 1BThe diagram illustrates different types of defects. Synthetic defect generation systems can combine defects of various types and severity to create accurate representations of real-world scenes. Furthermore, the synthetic defect generation system can be instructed to modify environmental conditions, enabling the 3D model to produce images that depict the specific appearance of defects from different perspectives and under varying environmental conditions. These generated images are annotated and can be used during the training of AI models, significantly improving the efficiency and effectiveness of training AI systems to detect and differentiate various defect types and conditions.

[0030] Figure 2 The illustration depicts an example system environment including a synthetic defect generation system according to various embodiments. As an example, Figure 2 An example networking system 200 is illustrated that can be used to provide, generate, modify, encode, process, and / or transmit image data or other such content. The example networking system 200 may include client devices 202, other client devices 203, a network 214, third-party services 260, and a provider environment 216 including a synthetic defect generation system 230.

[0031] Client device 202 can use components of application 207 running on client device 202 and data stored locally on client device 202 to generate or receive data for a session. As an example, a user can leverage client device 202 to generate synthetic images using application 207 and / or use training data including these synthetic images to detect defects using application 207 (or different applications). Although only one client device 202 is illustrated in detail, system 200 may include one or more other client devices 203 that can communicate with provider environment 216 via network 214. Client device 202 can be any suitable computing device capable of enabling a user to generate synthetic images with defects as discussed herein, such as including desktop computers, laptop computers, computer workstations, game consoles, set-top boxes, streaming devices, smartphones, tablet computers, VR headsets, AR goggles, wearable computers, or smart TVs. In at least one embodiment, a user can generate synthetic defects using a user interface (UI) 206 running on client device 202, although at least some functionality may also operate on remote devices, networked devices, or via a cloud computing platform. In at least one embodiment, a user can provide input to UI 206, such as via a touch-sensitive display 204 or via a mouse cursor displayed on a mobile display screen. In one embodiment, a user can provide input to application 207 such as images, text, instructions, features of environmental conditions, features of defects, labels, annotations, training datasets, and supervised datasets. Application 207 may be provided by provider environment 216 for the user to download on client device 202. In at least one embodiment, the client device may include at least one processor 208 (e.g., CPU or GPU) and memory 210 to execute application 207 and / or perform tasks on behalf of application 207. In at least one embodiment, synthetic images generated by application 207 may be locally stored in local storage device 212.

[0032] In one embodiment, each client device 202 can submit requests across at least one wired or wireless network, such as the Internet, Ethernet, a local area network (LAN), or a cellular network, and other such options. In this example, these requests can be submitted to an address associated with a cloud provider that can operate or control one or more electronic resources within a cloud provider environment, such as a data center or server cluster. In at least one embodiment, the request can be received or processed by at least one edge server located at the network edge and outside at least one security layer associated with the cloud provider environment. This reduces latency by enabling client devices to interact with servers in closer proximity, while also improving the security of resources within the cloud provider environment.

[0033] Network 214 can represent a communication path between client device 202, provider environment 216, other client devices 203, and third-party service 260. Through network 214, client device 202 can send input information associated with the generation of synthetic defects. This information can be received by a remote computing system, such as being part of resource provider environment 216. In one embodiment, network 214 is the Internet. Network 214 can include any suitable network, including intranets, the Internet, cellular networks, local area networks (LANs), or any other such networks or combinations; and communication over the network can be achieved via wired and / or wireless connections. Network 214 can also utilize dedicated or private communication links that are not necessarily part of the Internet. In one embodiment, network 214 uses standard communication technologies and / or protocols. Therefore, network 214 can include links using technologies such as Ethernet, Wi-Fi, Integrated Services Digital Network (ISDN), Digital Subscriber Line (DSL), Asynchronous Transfer Mode (ATM), etc. Similarly, the networking protocols used on network 214 may include Multiprotocol Label Switching (MPLS), Transmission Control Protocol / Internet Protocol (TCP / IP), Hypertext Transfer Protocol (HTTP), Simple Mail Transfer Protocol (SMTP), File Transfer Protocol (FTP), etc. In one embodiment, at least some of the links use mobile network technologies such as Long Term Evolution (LTE). Data exchanged through network 214 can be represented using technologies or formats including Hypertext Markup Language (XML), Wireless Access Protocol (WAP), Short Message Service (SMS), etc. Additionally, all or some of the links can be encrypted using conventional encryption technologies such as Secure Sockets Layer (SSL), Secure HTTP, or Virtual Private Network (VPN). In another embodiment, client device 202 may use custom and / or dedicated data communication technologies to replace or supplement the technologies described above.

[0034] The provider environment 216 may include any appropriate components for receiving requests and responding to those requests by returning information or performing actions. Figure 2 In the illustrated embodiments, provider environment 216 may include interface 218 and server 220, which includes various components for performing tasks associated with generating synthetic images. In at least one embodiment, provider environment 216 may include a web server and / or application server for receiving and processing requests and then returning data or other content or information in response to those requests.

[0035] Interface 218 can receive communication with server 220. In at least one embodiment, interface layer 218 may include an application programming interface (API) or other exposed interfaces that enable users to submit requests to server 220. In at least one embodiment, interface 218 may also include other components, such as at least one web server, routing components, or load balancers. In at least one embodiment, components of interface layer 218 can determine the type of request or communication and can direct the request to an appropriate system or service, such as synthetic defect generation system 230.

[0036] Server 220 may include a transmission manager 222, a content application 224, an object storage device 234, and a user storage device 236. Server 220 may receive requests and data from client device 202, perform tasks associated with the requests, and send results or other data to client device 202. In at least one embodiment, the content application 224, running on server 220 (e.g., a cloud server or edge server), may initiate a session associated with client device 202, such as using a session manager and user data stored in user database 236, and may allow content manager 226 to select content, such as one or more object representations (e.g., images), from object repository 234 for processing. At least a portion of the generated content (such as synthetic images generated from synthetic defect generation system 230) may be transmitted to client device 202 using appropriate transmission manager 222 for transmission via download, streaming, or another such transmission channel. In some embodiments, defect detection system 230 or process may run on the same server 220 (or a different server) trained using synthetic defect images, and the results of defect detection may be sent to client device 202, among other such options. An encoder can be used to encode and / or compress at least some of this data before it is transmitted to client device 202. In at least one embodiment, client device 202 receiving such content can provide it to a corresponding application 207 for selection, provision, composition, modification, or use to render (or otherwise use) on or by client device 202. A decoder can also be used to decode data received via one or more networks 214 for rendering via client device 202, such as rendering image or video content via display 204. In at least one embodiment, at least some of the content may already be stored on, rendered on, or accessible to client device 202, such that at least that portion of the content does not need to be transmitted via network 214, for example, the content may have been previously downloaded or stored locally on a hard disk or optical disc. In at least one embodiment, a transmission mechanism such as data streaming can be used to transmit content from server 220 or user database 236 to client device 202. In at least one embodiment, at least a portion of the content may be obtained, enhanced, and / or streamed from another source (such as a third-party service 260 or other client device 203) that may also include a content application 262 for generating, enhancing, or providing content. In at least one embodiment, a portion of the function may be performed using multiple computing devices or multiple processors (such as a combination of CPU and GPU) within one or more computing devices.

[0037] In at least one embodiment, server 220 may include a processor such as a central processing unit (CPU). However, in at least one embodiment, resources in such an environment may utilize GPUs to process data for at least some types of requests. In at least one embodiment, GPUs with thousands of cores are designed to handle large amounts of parallel workloads and have therefore become popular in deep learning for training neural networks and generating predictions. In at least one embodiment, while offline building using GPUs allows for faster training of larger and more complex models, offline prediction generation means either that input features cannot be used at request time or that predictions must be generated for all permutations of features and stored in a lookup table to serve real-time requests. In at least one embodiment, if the deep learning framework supports CPU mode and the model is small and concise enough that feedforward can be performed on the CPU with a reasonable latency, a service on a CPU instance can host the model. In at least one embodiment, training can be done offline on the GPU, and inference can be done in real time on the CPU. In at least one embodiment, if the CPU approach is not a viable option, the service can run on a GPU instance. However, in at least one embodiment, because GPUs have different performance and cost characteristics than CPUs, running a service that offloads runtime algorithms to the GPU may require designing it differently from a CPU-based service.

[0038] Server 220 may include content application 224, which includes content manager 226, defect detection system 230, and / or synthetic defect generation system 232. As previously discussed, content manager 226 may send objects (such as images and instructions) from object repository 234, along with requests and other data from client device 202, to synthetic defect generation system 230 for generating synthetic images. Synthetic defect generation system 230 may generate synthetic images with defects and provide the results to transmission manager 222 for transmission back to client device 202. Synthetic defect generation system 230 may also use local datasets or datasets provided by third-party service 260 to train a machine learning model capable of generating synthetic images and store the trained model in a model library. Figure 3 The functions associated with the synthetic defect generation system 230 will be discussed in more detail.

[0039] Figure 3Example block diagrams depicting various modules of a synthetic defect generation system 230 according to at least one embodiment are illustrated. The synthetic defect generation system 230 may include a defect modeling module 304 defining the characteristics of defects, an environment modeling module 302 defining the characteristics of the environment, an image generation module 306 simulating defects under various environmental conditions in a 3D model, and a user interface 308 for accepting input from a user (or other such source). In some embodiments, the system may further include a training manager 308 managing the training process of defect generation and / or detection models, a training data repository 324 storing training data, and a model repository 326 storing saved models.

[0040] The synthetic defect generation system 230 can operate by receiving requests to generate synthetic variations for input images. Users can utilize the synthetic defect generation system 230 to construct a 3D model, thereby manipulating environmental conditions within the model to generate an array of images visually representing the desired defect from a selected viewpoint. The synthetically generated images can then be used as training data for a defect detection model. In one embodiment, the synthetic generation system 230 can use images showing defects present in a specific environment as input to extract characteristics of the environment and the defects. In another embodiment, the synthetic generation system 230 can receive a script or other document detailing the characteristics of the defects and the environmental attributes used to discover them. Using these specifications, the synthetic generation system 230 can then create a 3D model of the object including the defect and temporarily store it in the outlined environment. The synthetic images generated by the synthetic generation system 230 can be passed to a training manager 308, which uses the synthetically generated training data (such as images generated from the 3D model) to train defect detection on how to identify various defects. Each module in the synthetic defect generation system 230 is discussed in more detail in the following sections.

[0041] The defect modeling module 304 can utilize a realistic renderer (e.g., a rendering engine) to create a three-dimensional (3D) model to model the defect. In at least one embodiment, the defect modeling module 304 can utilize one or more defect model libraries to construct the defect. The defect modeling module 304 can also receive specific instructions, such as a script outlining the characteristics of the defect for recreating a 3D model of the defect. The defect modeling module 304 can also construct a 3D model based on an input image. The defect modeling module 304 can reconstruct a wide range of defects, such as manufacturing defects. Manufacturing defects may include geometric defects, assembly defects, and material (or texture) defects. Geometric defects correspond to unexpected variations in the geometry of an object that deviate from expected manufacturing parameters. These defects may include dents, physical warpage or deformation, burrs, holes, or debris. An example might be a part manufactured outside of expected tolerance levels, resulting in unexpected geometric deviations. Assembly defects relate to anomalies when assembling multiple parts or 3D geometries. Assembly defects may involve missing parts, misaligned parts, or parts assembled in incorrect orientation. Material or texture defects correspond to anomalies found on the surface of an object, such as scratches, minor dents, wear marks, or paint runs. The defect modeling module 304 can be instructed to create 3D models of the defects using a realistic renderer. After these 3D models are created, the image generation module 306 can use these models to randomize the defects and generate a variety of variant arrays of these defects for enhancement using the environment model generated by the environment modeling module 302, which will be discussed further below.

[0042] In at least one embodiment, the environment modeling module 302 can construct realistic 3D models of various environments. These environments can be rendered using a highly realistic renderer that effectively replicates the real-world environment for temporary storage of defective objects. The environment modeling module 302 can have the flexibility to render environments based on various inputs, such as images, sensor data, or scripts detailing specific characteristics of the environment. Sensor data inputs can appear in various forms, including sensor data inputs from LiDAR sensors, radar, or thermal imagers. Each sensor can provide unique data points that contribute to an accurate 3D representation of the environment. For example, a LiDAR sensor uses pulsed laser light to measure distances, thus providing detailed spatial information that is useful when creating accurate 3D models. The environment modeling module 302 can also receive and process a wide range of environmental characteristics, from lighting and weather conditions to the texture of the environment. For example, the environment modeling module 302 can be instructed to replicate the luminous intensity of sunlight or dusk to simulate different weather conditions (such as sunny or cloudy), or to replicate environmental textures such as rough terrain or smooth surfaces. An example of complex textures might be simulating a room filled with mirrors. The environment modeling module 302 can accurately render reflection, diffraction, and refraction. As another example, the environment modeling module 302 can model a snowy environment, where the whiteness of snow causes a lot of reflected light, creating an environment filled with bright reflective surfaces. The environment modeling module 302 can simulate various scenes and provide various training data for training AI to identify defects in environments where AI defect recognition is challenging. Once these environment models are rendered, they can be used by the image generation module 306 to temporarily store objects with defects. The image generation module 306 can utilize the models generated by the defect modeling module 304 and the environment modeling module 302 to generate a wide range of images, which can be used, for example, to train a defect detection model. Figure 4 The image generation module 306 will be discussed in more detail.

[0043] like Figure 4As illustrated, the image generation module 306 may include an environment simulation module 410, a defect simulation module 420, and an enhancement module 430. The environment simulation module 410 can simulate a range of environments. These simulated environments may be slightly enhanced or completely fictional virtual replicas of the real world. For example, a user can use a LiDAR scan of a real-world location, such as a manufacturing facility, as a starting point and then modify it to meet their needs. This might involve changing lighting conditions 411, changing weather conditions 412, adding or removing elements from the environment, or creating entirely new environments 413 (such as environments that are more challenging for defect detection models). In one embodiment, the environment simulation module 410 employs a generative model to introduce random variations into the simulated environment. The generative model is trained to generate multiple instances of objects or environments with subtle or significant variations in specific characteristics within a 3D modeling and simulation framework. For example, suppose the synthetic training environment involves a warehouse with several light sources. The environment simulation module 410 can use the generative model to create multiple versions of the warehouse, each with a different lighting scene. In one instance, some light bulbs might be simulated as burnt out, creating a darker environment. In another instance, all the lights might function perfectly, resulting in a bright lighting scene. In another instance, different bulbs might burn out due to different lighting scenarios. The environment simulation module 410 can use a generative model to randomize these lighting conditions across various iterations of the warehouse environment, thus providing a range of lighting scenarios for AI training. The ability to broaden and vary environmental conditions through randomization is a significant advantage of the environment simulation module 410. In real-world settings, conditions are limited to the specific circumstances at the time of data capture. For example, if all images were captured on a sunny day, the AI ​​model might perform poorly under cloudy conditions because it has overfitted to the specific sunny conditions. However, the environment simulation module 410 can introduce variations such as cloudy and sunny, dim and bright lighting, thereby providing a wider range of training data through randomization to create a more robust AI model. Therefore, the environment simulation module 410 enables the creation of highly diverse and challenging training environments, making the defect detection model more robust and adaptable to a wide range of real-world scenarios.

[0044] According to at least one embodiment, the defect simulation module 420 can generate and randomize a wide variety of defects on a simulation model. In one embodiment, the defect simulation module 420 can generate variations of manufacturing defects, such as geometric defects, assembly defects, and texture defects. To randomize assembly defects (missing parts, misaligned parts, or incorrectly placed parts), the defect simulation module 420 manipulates the display and arrangement of parts within the model. For example, the defect simulation module 420 can hide specific parts, thereby changing their position or altering their orientation. To randomize geometric defects, the defect simulation module 420 can generate changes to the actual shape, size, or alignment of the parts. The defect simulation module 420 can achieve this by adjusting parameters associated with the defect, such as the severity 421 of the defect (e.g., the depth or width of a dent, the angle or shape deformation of a bent part). For example, in a model of an automotive panel, the defect simulation module 420 can modify parameters to simulate various types of geometric defects, such as deep dents caused by severe impacts, slight bends due to improper handling, or shape warping due to manufacturing process defects. To randomize texture defects 422 (such as paint runs, orange peel, or wear marks) appearing on the surface of an object, the defect simulation module 420 can use a texture processing system such as Adobe Substance. The defect simulation module 420 can also apply scratch-like textures (e.g., as stickers) to a 3D model of a smartphone screen or create an uneven paint appearance on the surface of a model car. The defect simulation module 420 can also randomize defect combinations by simulating compound defects 423, which are combinations of multiple defects and multiple types of defects appearing simultaneously on the same object. For example, the defect simulation module 420 can model a car panel carrying misaligned parts (assembly defects) and paint runs (texture defects).

[0045] According to at least one embodiment, the enhancement module 430 can enhance the simulated environment model and defect model to generate a comprehensive synthetic image. Once the environment and defect have been simulated, the enhancement module 430 temporarily stores the defective object in the environment. The enhancement module 430 can also be instructed to dynamically adjust the scene application. For example, the enhancement module 430 can be instructed to change the positioning or orientation of the defective object in the environment to simulate different perspectives. The enhancement module 430 can capture images of the defective product from multiple angles, or even simulate camera movement passing over the object, to provide a more comprehensive view of the defect. By simulating these different perspectives, the enhancement module 430 helps create diverse datasets that can enhance the robustness of the AI ​​model. The synthetic image generated by the enhancement module 430 is then used by the training manager 308 to train the defect detection model.

[0046] Training manager 308 can train a defect detection model using synthetic images generated from image generation module 306 as training data. The defect detection model can take the synthetic images as input data and generate an output that identifies defects on objects. In one embodiment, training manager 308 can train a convolutional neural network (CNN) to process pixel data and learn features such as edges, corners, and textures from raw image pixels, gradually building an understanding of more complex structures. The output of the CNN model includes bounding boxes using predicted classification labels. In one embodiment, the output can be a segmentation map for a segmentation task, where each pixel of the image is classified using a label. Training manager 308 can also train models such as U-Net or variants of transformer models suitable for visual recognition tasks, such as the Visual Transformer (ViT). Training manager 308 can train a model with an encoder-decoder structure, where the encoder gradually reduces the spatial dimension while increasing the depth (feature map), and the decoder does the opposite, thus capturing spatial details while preserving contextual information. The input to the defect detection model can be an image, and the output is a classification or segmentation map. Training manager 308 can train the model using synthetic images and their corresponding defect labels or annotations. Defect detection models can learn to map input images to their correct labels by minimizing a loss function. The trained model can then be used to detect and quantify defects in new and unseen images.

[0047] In one embodiment, training manager 308 trains a defect detection model to identify anomalies exceeding a predetermined threshold as defects. The threshold can be based on several factors, such as the size, depth, or location of the defect. Training manager 308 can train the model to focus on significant defects that may have a substantial impact on the quality of an object. For example, to identify and measure scratches on an object, training manager 308 can use synthetic images labeled with bounding boxes or segmentation masks to guide the training process, where each bounding box or pixel in the image is classified as belonging to a certain category (in this case, e.g., “scratched” or “no scratch”). In one embodiment, training manager 308 can quantify the severity of a scratch by measuring certain properties of the annotated scratch, such as length, width, or depth. Based on these measurements, a severity score can be assigned to each scratch, which can then be visualized using color coding. For example, a severe scratch of 10 mm might be depicted in red, a moderately severe scratch of 1.5 mm in yellow, and a minor scratch of 0.5 mm in green. By training the model in this way, training manager 308 allows the model to not only identify defects but also measure their severity.

[0048] Figure 5An example process 500 is illustrated that can be used to generate synthetic images with defects (such as those used to train a defect detection model to identify and classify defects). This example process 500 begins by identifying one or more defects 510 to be represented in synthetic data. In one embodiment, defect 510 can be a manufacturing or process defect. Defects may originate from images, models, point clouds, text descriptions, or any other form of data containing information related to defect characteristics. This information can be used to construct an environmental and / or defect 3D model. Using the identified defects 510, the synthetic defect generation system 230 can extract, select, or determine relevant environmental characteristics 520 and defect characteristics 530 to be used to create relevant 3D models. The environment simulation module 410 can generate a realistic 3D environment model 540 designed to simulate various real-world conditions. Parameters such as lighting and weather conditions can be changed to introduce variability, thereby improving the robustness of the trained model. The defect simulation module 420 can generate one or more 3D models 550 of the identified defects 510. In one embodiment, the defect 3D model incorporates variations in defect characteristics such as width, depth, shape, texture, and severity, thus representing a wide range of possible defects. Following the generation of the environment and defect model, the enhancement module 430 synthesizes 560 or generates or replicates defects in various environments to improve the variability of the synthetic data. The enhancement module 430 can generate different perspectives of the same defect and / or different combinations of defects to further expand the dataset. The training manager 308 then uses the generated synthetic images and their respective annotations to train the defect detection model 570.

[0049] In at least one embodiment, a validation process that tests the model on a separate validation dataset can be used to validate the defect detection model. The validation process is crucial for determining the model's performance and its ability to generalize to unseen data. For incorrect predictions, feedback can be sent back to the initial step in the form of more example images or improved ground truth annotations for the defects. Iteration continues until the model achieves the desired performance on the validation dataset. Once the defect detection model achieves satisfactory results on the validation dataset, it is ready to be deployed in real-world scenarios for detecting and classifying defects. The process from defect identification to model deployment provides an iterative and robust approach to creating effective defect detection models. The extensive use of synthetic data ensures that the model is trained on comprehensive and diverse datasets, thereby improving the model's performance and generalization ability in real-world scenarios.

[0050] Figure 6An example process for generating synthetic images for defect detection is illustrated. It should be understood that, unless otherwise specifically stated, additional, fewer, or alternative steps may exist within the scope of various embodiments, performed in a similar or alternative sequence or at least partially in parallel, for this and other processes presented herein. Furthermore, although this process is described with respect to defects and model training, it should be understood that various other types of enhancements can be synthesized using this process, and the synthesized images or image data can also be used for other purposes. In this example, process 600 begins by providing 302 inputs to a generative model, which consists of image data for an object and an indication of at least one defect type. The generative model may be a machine learning model trained by a synthetic defect generation system 230 to generate variations of images with this defect type. In one or more embodiments, the generative model may be implemented as one or more autoregressive models, Gaussian-based generative models, fractional generative models, or probabilistic generative models (such as diffusion models, variational autoencoders (VAEs), or generative adversarial networks (GANs)). Image data for an object may include captured image data of a physical object, synthetic image data of a virtual object, or an indication of the object type to be synthesized, and other such options. In this example process 600, input indicating one or more aspects of a defect (such as possibly related to size, depth, or degree) or the lighting, environment, or context to be represented in the generated image may also be optionally provided at 604. Operations or modules such as image generation module 306 may use a generative model to generate 606 one or more synthetic images including representations of objects having at least one instance of at least one defect type, wherein the object and defect are optionally represented according to one or more optional aspects, such as representation under one or more environmental conditions. One or more images may then be provided at 608 or stored for one or more purposes, such as for use as training data to train a defect detection model. Within the scope of various embodiments, numerous different images representing different types and degrees of defects (or other variations or enhancements) with respect to various objects or object types under various conditions can be generated. In other embodiments, labeled (and / or latent space encoded) synthetically generated images of objects with enhancements (e.g., defects) can be provided to train, fine-tune, or update parameters (e.g., one or more weights, one or more biases, etc.) of a visual language model (VLM). In one or more deployment embodiments, images of one or more objects (e.g., from an assembly line) can be provided to such a VLM, prompting it to query whether any defects in the images displayed in the VLM are evident. In other embodiments, labeled and / or latent space encoded synthetically generated images can be provided along with the prompted query during the enhancement generation process.

[0051] Reasoning and training logic

[0052] Figure 7A Inference and / or training logic 715 is shown for performing inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Provide details about reasoning and / or training logic 715.

[0053] In at least one embodiment, inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701 for storing forward and / or output weights and / or input / output data, and / or other parameters configuring neurons or layers of a neural network trained for and / or used for inference in one or more embodiments. In at least one embodiment, training logic 715 may include or be coupled to code and / or data storage 701 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, code and / or data storage 701 stores weight parameters and / or input / output data of each layer of a neural network trained or used in one or more embodiments during forward propagation of input / output data and / or weight parameters during training and / or inference using one or more embodiments. In at least one embodiment, any portion of the code and / or data storage 701 may be included within other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0054] In at least one embodiment, any portion of the code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 701 may be a cache memory, dynamic random access memory (“DRAM”), static random access memory (“SRAM”), non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether the code and / or data storage 701 is internal or external to the processor, for example, or composed of DRAM, SRAM, flash memory, or some other storage type, may depend on the available on-chip or off-chip storage space, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in the inference and / or training of the neural network, or some combination of these factors.

[0055] In at least one embodiment, inference and / or training logic 715 may include, but is not limited to, code and / or data storage 705 for storing backpropagation and / or output weights and / or input / output data corresponding to neurons or layers of a neural network trained and / or used for inference in one or more embodiments. In at least one embodiment, during training and / or inference using one or more embodiments, code and / or data storage 705 stores weight parameters and / or input / output data for each layer of a neural network trained or used in one or more embodiments during backpropagation of input / output data and / or weight parameters. In at least one embodiment, training logic 715 may include or be coupled to code and / or data storage 705 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic including integer and / or floating-point units (collectively, an arithmetic logic unit (ALU)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of the code and / or data storage 705 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. In at least one embodiment, any portion of the code and / or data storage 705 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 705 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice between the code and / or data storage 705 being internal or external to the processor, for example, whether it consists of DRAM, SRAM, flash memory, or some other type of storage, depends on whether the available storage is on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the data batch size used in the inference and / or training of the neural network, or some combination of these factors.

[0056] In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be separate storage structures. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be the same storage structure. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be partially identical and partially separate storage structures. In at least one embodiment, any portion of code and / or data storage 701 and code and / or data storage 705 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0057] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, one or more arithmetic logic units (“ALUs”) 710 (including integer and / or floating-point units) for performing logical and / or mathematical operations at least in part based on or instructed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from layers or neurons within a neural network) stored in activation storage 720, which are functions of input / output and / or weight parameter data stored in code and / or data storage 701 and / or code and / or data storage 705. In at least one embodiment, activation is activated in response to execution instructions or other code, and linear algebraic and / or matrix-based mathematical generation performed by ALU 710 is stored in activation storage 720, wherein weight values ​​stored in code and / or data storage 705 and / or code and / or data storage 701 are used as operands with other values, such as bias values, gradient information, momentum values, or other parameters or hyperparameters, and any or all of these can be stored in code and / or data storage 705 or code and / or data storage 701 or other on-chip or off-chip storage.

[0058] In at least one embodiment, one or more ALUs 710 are included in one or more processors or other hardware logic devices or circuits, while in another embodiment, one or more ALUs 710 may be located outside the processor or other hardware logic device or the circuitry that uses them (e.g., a coprocessor). In at least one embodiment, ALUs 710 may be included within an execution unit of a processor, or otherwise included in a group of ALUs accessible by the execution unit of the processor, which may be within the same processor or distributed among different processors of different types (e.g., a central processing unit, a graphics processing unit, a fixed-function unit, etc.). In at least one embodiment, code and / or data storage 701, code and / or data storage 705, and activation storage 720 may be on the same processor or other hardware logic device or circuitry, while in another embodiment, they may be in different processors or other hardware logic devices or circuitries, or in some combination of the same and different processors or other hardware logic devices or circuitries. In at least one embodiment, any portion of activation storage 720 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Furthermore, inference and / or training code may be stored together with other code accessible to the processor or other hardware logic or circuitry, and may be retrieved and / or processed using the processor’s fetch, decode, schedule, execute, exit, and / or other logic circuitry.

[0059] In at least one embodiment, the active memory 720 may be a cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other memory. In at least one embodiment, the active memory 720 may be wholly or partially located inside or outside one or more processors or other logic circuits. In at least one embodiment, the choice of whether the active memory 720 is internal to or external to the processor may depend on the available on-chip or off-chip storage, the latency requirements for training and / or inference functions, the batch size of data used in inference and / or training the neural network, or some combination of these factors. For example, it may include DRAM, SRAM, flash memory, or other memory types. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (“ASIC”), such as those from Google. Processing unit, from Graphcore TM Inference processing unit (IPU) or from Intel Corp. (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as field programmable gate array (“FPGA”)

[0060] Figure 7B Inference and / or training logic 715 according to at least one or more embodiments is illustrated. In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, hardware logic, wherein computational resources are dedicated or otherwise uniquely used in conjunction with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (ASIC), such as those from Google. Processing unit, from Graphcore TM Inference processing unit (IPU) or from Intel Corp. (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7BThe inference and / or training logic 715 shown can be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware (e.g., field-programmable gate array (FPGA)). In at least one embodiment, the inference and / or training logic 715 includes, but is not limited to, code and / or data storage 701 and code and / or data storage 705, which can be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, momentum values, and / or other parameter or hyperparameter information. Figure 7B In at least one embodiment shown, each of code and / or data storage 701 and code and / or data storage 705 is associated with dedicated computing resources (e.g., computing hardware 702 and computing hardware 706), respectively. In at least one embodiment, each of computing hardware 702 and computing hardware 706 includes one or more ALUs that perform mathematical functions (e.g., linear algebraic functions) only on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of the function execution are stored in activation storage 720.

[0061] In at least one embodiment, each of the code and / or data storage 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activation obtained from one “store / computation pair 701 / 702” of the code and / or data storage 701 and computing hardware 702 provides input as input to the next “store / computation pair 705 / 706” of the code and / or data storage 705 and computing hardware 706, in order to reflect the conceptual organization of the neural network. In at least one embodiment, each store / computation pair 701 / 702 and 705 / 706 may correspond to more than one neural network layer. In at least one embodiment, additional store / computation pairs (not shown) may be included in the inference and / or training logic 715 after or in parallel with the store / computation pairs 701 / 702 and 705 / 706.

[0062] Data Center

[0063] Figure 8 An example data center 800 that can be used with at least one embodiment is shown. In at least one embodiment, the data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0064] In at least one embodiment, such as Figure 8As shown, the data center infrastructure layer 810 may include a resource coordinator 812, grouped computing resources 814, and node computing resources (“nodes CR”) 816(1)-816(N), where “N” represents any positive integer. In at least one embodiment, nodes CR 816(1)-816(N) may include, but are not limited to, any number of central processing units (“CPUs”) or other processors (including accelerators, field-programmable gate arrays (FPGAs), graphics processors, etc.), memory devices (e.g., dynamic read-only memory), storage devices (e.g., solid-state drives or disk drives), network input / output (“NWI / O”) devices, network switches, virtual machines (“VMs”), power modules, and cooling modules, etc. In at least one embodiment, one or more nodes CR 816(1)-816(N) may be servers having one or more of the aforementioned computing resources.

[0065] In at least one embodiment, the grouped computing resources 814 may include individual groups (not shown) of node CRs housed in one or more racks, or a plurality of racks (also not shown) housed in data centers in various geographic locations. Individual groups of node CRs within the grouped computing resources 814 may include computing, networking, memory, or storage resources that can be configured or allocated to support groups of one or more workloads. In at least one embodiment, several node CRs, including CPUs or processors, may be grouped within one or more racks to provide computing resources to support one or more workloads. In at least one embodiment, the one or more racks may also include any number of power modules, cooling modules, and network switches, in any combination.

[0066] In at least one embodiment, resource coordinator 812 may configure or otherwise control one or more nodes CR816(1)-816(N) and / or grouped computing resources 814. In at least one embodiment, resource coordinator 812 may include a software design infrastructure (“SDI”) management entity for data center 800. In at least one embodiment, resource coordinator may include hardware, software, or some combination thereof.

[0067] In at least one embodiment, such as Figure 8As shown, framework layer 820 includes a job scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, framework layer 820 may include a framework of software 832 supporting software layer 830 and / or one or more applications 842 supporting application layer 840. In at least one embodiment, software 832 or application 842 may respectively include web-based service software or applications, such as services or applications provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, framework layer 820 may be, but is not limited to, a free and open-source software web application framework, such as Apache Spark™ (hereinafter referred to as "Spark") which can leverage distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, job scheduler 832 may include Spark drivers to facilitate the scheduling of workloads supported by the various layers of data center 800. In at least one embodiment, configuration manager 824 may be able to configure different layers, such as software layer 830 and framework layer 820 including Spark and distributed file system 828 for supporting large-scale data processing. In at least one embodiment, resource manager 826 is capable of managing cluster or group computing resources mapped to or allocated to support distributed file system 828 and job scheduler 822. In at least one embodiment, cluster or group computing resources may include group computing resources 814 on data center infrastructure layer 810. In at least one embodiment, resource manager 826 may coordinate with resource coordinator 812 to manage these mapped or allocated computing resources.

[0068] In at least one embodiment, the software 832 included in the software layer 830 may include software used by at least a portion of the nodes CR816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of software may include, but are not limited to, Internet web page search software, email virus scanning software, database software, and streaming video content software.

[0069] In at least one embodiment, the application layer 840 may include one or more applications 842 that can be used by at least a portion of nodes CR816(1)-816(N), grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The one or more types of applications may include, but are not limited to, any number of genomics applications, cognitive computing and machine learning applications, including training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in conjunction with one or more embodiments.

[0070] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can perform any number and type of self-modification actions based on any amount and type of data acquired in any technically feasible manner. In at least one embodiment, self-modification actions can mitigate potentially poor configuration decisions by data center operators of data center 800 and can prevent underutilization and / or poor performance of the data center.

[0071] In at least one embodiment, data center 800 may include tools, services, software, or other resources to train one or more machine learning models or to use one or more machine learning models to predict or infer information according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model can be trained by calculating weight parameters based on a neural network architecture using the software and computing resources described above with respect to data center 800. In at least one embodiment, information can be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to data center 800 by using weight parameters calculated through one or more training techniques described herein.

[0072] In at least one embodiment, the data center may use a CPU, application-specific integrated circuit (ASIC), GPU, FPGA, or other hardware to utilize the aforementioned resources to perform training and / or inference. Furthermore, one or more of the aforementioned software and / or hardware resources may be configured as a service to allow a user to train or perform information inference, such as image recognition, speech recognition, or other artificial intelligence services.

[0073] Inference and / or training logic 815 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, inference and / or training logic 715 can... Figure 8Used in systems for reasoning or predicting operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0074] Such components can be used to generate images of objects with synthetic but realistic defects or other variations or enhancements, which may help train defect detection systems.

[0075] Computer System

[0076] Figure 9 This is a block diagram illustrating an exemplary computer system according to at least one embodiment. The exemplary computer system may be a system of interconnected devices and components, a system-on-a-chip (SoC), or some combination thereof formed with a processor, which may include an execution unit to execute instructions. In at least one embodiment, according to this disclosure, such as the embodiments described herein, computer system 900 may include, but is not limited to, components such as processor 902, whose execution unit includes logic to execute algorithms for process data. In at least one embodiment, computer system 900 may include a processor, such as those available from Intel Corporation of Santa Clara, California. Processor family, Xeon™ XScale™ and / or StrongARM™ Core TM or Nervana TM A microprocessor may be used, although other systems (including PCs, engineering workstations, set-top boxes, etc.) with other microprocessors may also be used. In at least one embodiment, computer system 900 may execute a version of the Windows operating system available from Microsoft Corporation of Redmond, Washington, although other operating systems (such as UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0077] The embodiments can be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol (IP) devices, digital cameras, personal digital assistants (“PDAs”), and handheld PCs. In at least one embodiment, the embedded application may include a microcontroller, a digital signal processor (“DSP”), a system-on-a-chip (SoC), a network computer (“NetPC”), a set-top box, a network hub, a wide area network (“WAN”) switch, or any other system that can execute one or more instructions according to at least one embodiment.

[0078] In at least one embodiment, the computer system 900 may include, but is not limited to, a processor 902, which may include, but is not limited to, one or more execution units 908, to perform machine learning model training and / or inference according to the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, but in another embodiment, the computer system 900 may be a multiprocessor system. In at least one embodiment, the processor 902 may include, but is not limited to, a Complex Instruction Set Computer (“CISC”) microprocessor, a Reduced Instruction Set Computing (“RISC”) microprocessor, a Very Long Instruction Word (“VLIW”) microprocessor, a processor implementing instruction set combination, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which can transmit data signals between the processor 902 and other components in the computer system 900.

[0079] In at least one embodiment, processor 902 may include, but is not limited to, a Level 1 (“L1”) internal cache memory (“cache”) 904. In at least one embodiment, processor 902 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory may reside external to processor 902. Depending on specific implementation and requirements, other embodiments may also include a combination of internal and external caches. In at least one embodiment, register file 906 may store different types of data in various registers, including but not limited to integer registers, floating-point registers, status registers, and instruction pointer registers.

[0080] In at least one embodiment, a logic execution unit 908, including but not limited to performing integer and floating-point operations, is also located within the processor 902. In at least one embodiment, the processor 902 may further include a microcode (“ucode”) read-only memory (“ROM”) for storing microcode of certain macro instructions. In at least one embodiment, the execution unit 908 may include logic for processing a packaged instruction set 909. In at least one embodiment, by including the packaged instruction set 909 in the instruction set of a general-purpose processor, along with the associated circuitry for executing the instructions, the packaged data in the processor 902 can be used to perform operations used by numerous multimedia applications. In one or more embodiments, the execution of numerous multimedia applications can be accelerated and performed more efficiently by using the full width of the processor’s data bus to perform operations on the packaged data, which may eliminate the need to transfer smaller data units on the processor’s data bus to perform one or more operations on one data element at a time.

[0081] In at least one embodiment, the execution unit 908 may also be used in a microcontroller, embedded processor, graphics device, DSP, and other types of logic circuitry. In at least one embodiment, the computer system 900 may include, but is not limited to, memory 920. In at least one embodiment, memory 920 may be implemented as a dynamic random access memory (“DRAM”) device, a static random access memory (“SRAM”) device, a flash memory device, or other storage device. In at least one embodiment, memory 920 may store instructions 919 and / or data 921 represented by data signals that can be executed by processor 902.

[0082] In at least one embodiment, the system logic chip may be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip may include, but is not limited to, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage, as well as for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 may initiate data signals between the processor 902, the memory 920, and other components in the computer system 900, and bridge data signals between the processor bus 910, the memory 920, and the system I / O 922. In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 may be coupled to the memory 920 via the high-bandwidth memory path 918, and the graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port (“AGP”) interconnect 914.

[0083] In at least one embodiment, computer system 900 may use system I / O 922, which is a proprietary hub interface bus, to couple MCH 916 to I / O controller hub (“ICH”) 930. In at least one embodiment, ICH 930 may provide direct connectivity to certain I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, but is not limited to, a high-speed I / O bus for connecting peripheral devices to memory 920, chipset, and processor 902. Examples may include, but are not limited to, audio controller 929, firmware hub (“FlashBIOS”) 928, wireless transceiver 926, data storage 924, a conventional I / O controller 923 including user input and keyboard interfaces, serial expansion port 927 (e.g., a Universal Serial Bus (USB) port), and network controller 934. Data storage 924 may include hard disk drives, floppy disk drives, CD-ROM devices, flash memory devices, or other mass storage devices.

[0084] In at least one embodiment, Figure 9 A system including interconnected hardware devices or "chips" is shown, while in other embodiments, Figure 9An exemplary system-on-a-chip (SoC) may be illustrated. In at least one embodiment, the device may be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of the computer system 900 are interconnected using a compute fast link (CXL) interconnect.

[0085] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, inference and / or training logic 715 may be... Figure 9 Used in systems for reasoning or predicting operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0086] Such components can be used to generate images of objects with synthetic but realistic defects or other variations or enhancements, which may help train defect detection systems.

[0087] Figure 10 This is a block diagram illustrating an electronic device 1000 using a processor 1010 according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example, but not limited to, a laptop computer, tower server, rack server, blade server, laptop computer, desktop computer, tablet computer, mobile device, telephone, embedded computer, or any other suitable electronic device.

[0088] In at least one embodiment, system 1000 may include, but is not limited to, processor 1010 communicatively coupled to any suitable number or type of components, peripherals, modules, or devices. In at least one embodiment, processor 1010 uses a bus or interface coupling, such as an I2C bus, system management bus (“SMBus”), low pin count (LPC) bus, serial peripheral interface (“SPI”), high-definition audio (“HDA”) bus, serial advanced technology accessory (“SATA”) bus, universal serial bus (“USB”) (versions 1, 2, and 3), or universal asynchronous receiver / transmitter (“UART”) bus. In at least one embodiment, Figure 10 The system shown includes interconnected hardware devices or "chips," while in other embodiments, Figure 10 An exemplary system-on-a-chip (SoC) can be illustrated. In at least one embodiment, Figure 10 The device shown can be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, Figure 10 One or more components are interconnected using Computational Fast Link (CXL) interconnects.

[0089] In at least one embodiment, Figure 10 It may include a display 1024, a touch screen 1025, a touchpad 1030, a near field communication unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, a fast chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash (“BIOS, FWFlash”) 1022, a DSP 1060, a drive 1020 (e.g., a solid-state drive (“SSD”) or a hard disk drive (“HDD”)), a wireless local area network unit (“WLAN”) 1050, a Bluetooth unit 1052, a wireless wide area network unit (“WWAN”) 1056, a global positioning system (GPS) 1055, a camera (“USB 3.0 camera”) 1054 (e.g., a USB 3.0 camera) and / or a low-power double data rate (“LPDDR”) memory unit (“LPDDR3”) 1015 implemented in, for example, the LPDDR3 standard. These components can each be implemented in any suitable way.

[0090] In at least one embodiment, other components may be communicatively coupled to processor 1010 via the components described above. In at least one embodiment, accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to sensor hub 1040. In at least one embodiment, thermal sensor 1039, fan 1037, keyboard 1046, and touchpad 1030 may be communicatively coupled to EC 1035. In at least one embodiment, speaker 1063, earphone 1064, and microphone (“mic”) 1065 may be communicatively coupled to audio unit (“audio codec and Class D amplifier”) 1062, which in turn may be communicatively coupled to DSP 1060. In at least one embodiment, audio unit 1064 may include, for example, but not limited to, audio encoder / decoder (“codec”) and Class D amplifier. In at least one embodiment, SIM card (“SIM”) 1057 may be communicatively coupled to WWAN unit 1056. In at least one embodiment, components such as WLAN unit 1050, Bluetooth unit 1052, and WWAN unit 1056 can be implemented as next-generation form factor (NGFF).

[0091] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, inference and / or training logic 715 may be... Figure 10 The system is used to infer or predict operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0092] Such components can be used to generate images of objects with synthetic but realistic defects or other variations or enhancements, which may help train defect detection systems.

[0093] Figure 11 This is a block diagram of a processing system according to at least one embodiment. In at least one embodiment, system 1100 includes one or more processors 1102 and one or more graphics processors 1108, and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a large number of processors 1102 or processor cores 1107. In at least one embodiment, system 1100 is a processing platform incorporated within a system-on-a-chip (SoC) integrated circuit for use in mobile, handheld, or embedded devices.

[0094] In at least one embodiment, system 1100 may include or be integrated into a server-based gaming platform, including a game console, mobile game console, handheld game console, or online game console, which are game and media consoles. In at least one embodiment, system 1100 is a mobile phone, smartphone, tablet computing device, or mobile internet device. In at least one embodiment, processing system 1100 may also include components coupled to or integrated into a wearable device, such as a smartwatch, smart glasses, augmented reality, or virtual reality device. In at least one embodiment, processing system 1100 is a television or set-top box device having one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0095] In at least one embodiment, one or more processors 1102 each include one or more processor cores 1107 for processing instructions that, when executed, perform operations against the system and user software. In at least one embodiment, each of the one or more processor cores 1107 is configured to process a specific instruction set 1109. In at least one embodiment, the instruction set 1109 may facilitate Complex Instruction Set Computing (CISC), Reduced Instruction Set Computing (RISC), or computation via Very Long Instruction Word (VLIW). In at least one embodiment, the processor cores 1107 may each process different instruction sets 1109, which may include instructions that facilitate the emulation of other instruction sets. In at least one embodiment, the processor cores 1107 may also include other processing devices, such as digital signal processors (DSPs).

[0096] In at least one embodiment, processor 1102 includes cache memory 1104. In at least one embodiment, processor 1102 may have a single internal cache or multiple levels of internal caches. In at least one embodiment, the cache memory is shared among various components of processor 1102. In at least one embodiment, processor 1102 also uses an external cache (e.g., a Level 3 (L3) cache or a last-level cache (LLC)) (not shown), which can be shared among processor cores 1107 using known cache coherence techniques. In at least one embodiment, processor 1102 further includes a register file 1106, which may include different types of registers for storing different types of data (e.g., integer registers, floating-point registers, status registers, and instruction pointer registers). In at least one embodiment, register file 1106 may include general-purpose registers or other registers.

[0097] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 to transmit communication signals, such as address, data, or control signals, between the processors 1102 and other components in the system 1100. In at least one embodiment, the interface bus 1110 may be a processor bus, such as a version of the Direct Media Interface (DMI) bus. In at least one embodiment, the interface 1110 is not limited to the DMI bus and may include one or more peripheral component interconnect buses (e.g., PCI, PCI Express), memory buses, or other types of interface buses. In at least one embodiment, the processor 1102 includes an integrated memory controller 1116 and a platform controller hub 1130. In at least one embodiment, the memory controller 1116 facilitates communication between memory devices and other components of the processing system 1100, while the platform controller hub (PCH) 1130 provides connectivity to I / O devices via a local I / O bus.

[0098] In at least one embodiment, memory device 1120 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase-change memory device, or a device with suitable performance for use as processor memory. In at least one embodiment, memory device 1120 may be used as system memory of processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process. In at least one embodiment, memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 of processor 1102 to perform graphics and media operations. In at least one embodiment, display device 1111 may be connected to processor 1102. In at least one embodiment, display device 1111 may include one or more internal display devices, such as in mobile electronic devices or laptop devices, or external display devices connected via a display interface (e.g., DisplayPort). In at least one embodiment, the display device 1111 may include a head-mounted display (HMD), such as a stereoscopic display device for virtual reality (VR) or augmented reality (AR) applications.

[0099] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to connect to the storage device 1120 and the processor 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripheral devices include, but are not limited to, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, a touch sensor 1125, and a data storage device 1124 (e.g., a hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 may be connected via a storage interface (e.g., SATA) or via a peripheral bus, such as a peripheral component interconnect bus (e.g., PCI, PCIe). In at least one embodiment, the touch sensor 1125 may include a touchscreen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 may be a Wi-Fi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or LTE transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and may be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, network controller 1134 may enable network connectivity to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to interface bus 1110. In at least one embodiment, audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, processing system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to system 1100. In at least one embodiment, platform controller hub 1130 may also be connected to one or more Universal Serial Bus (USB) controllers 1142 that connect input devices, such as a keyboard and mouse combination 1143, a camera 1144, or other USB input devices.

[0100] In at least one embodiment, instances of the memory controller 1116 and platform controller hub 1130 may be integrated into a discrete external graphics processor, such as external graphics processor 1112. In at least one embodiment, the platform controller hub 1130 and / or the memory controller 1116 may be external to one or more processors 1102. For example, in at least one embodiment, system 1100 may include external memory controller 1116 and platform controller hub 1130, which may be configured as a memory controller hub and peripheral controller hub in a system chipset communicating with processor 1102.

[0101] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the graphics processor 1100. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs embodied in the graphics processor. Furthermore, in at least one embodiment, the inference and / or training operations described herein may use, in addition to Figure 7A or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0102] Such components can be used to generate images of objects with synthetic but realistic defects or other variations or enhancements, which may help train defect detection systems.

[0103] Figure 12 This is a block diagram of a processor 1200 having one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208 according to at least one embodiment. In at least one embodiment, the processor 1200 may include additional cores, up to and including additional cores 1202N indicated by dashed boxes. In at least one embodiment, each processor core 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core may also access one or more shared cache units 1206.

[0104] In at least one embodiment, internal cache units 1204A-1204N and shared cache unit 1206 represent a cache memory hierarchy within processor 1200. In at least one embodiment, cache memory units 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of cache in a shared intermediate cache, such as Level 2 (L2), Level 3 (L3), Level 4 (L4), or other levels of cache, wherein the highest level of cache preceding external memory is classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0105] In at least one embodiment, the processor 1200 may further include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCIe buses. In at least one embodiment, the system agent core 1210 provides management functions for various processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 to manage access to various external memory devices (not shown).

[0106] In at least one embodiment, one or more processor cores 1202A-1202N include support for multi-threaded concurrent processing. In at least one embodiment, system agent core 1210 includes components for coordinating and operating cores 1202A-1202N during multi-threaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) including logic and components for regulating one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0107] In at least one embodiment, processor 1200 further includes a graphics processor 1208 for performing graph processing operations. In at least one embodiment, graphics processor 1208 is coupled to a shared cache unit 1206 and a system proxy core 1210 including one or more integrated memory controllers 1214. In at least one embodiment, system proxy core 1210 further includes a display controller 1211 for driving graphics processor outputs to one or more coupled displays. In at least one embodiment, display controller 1211 may also be a separate module coupled to graphics processor 1208 via at least one interconnect, or it may be integrated within graphics processor 1208.

[0108] In at least one embodiment, ring-based interconnect unit 1212 is used to couple internal components of processor 1200. In at least one embodiment, alternative interconnect units, such as point-to-point interconnects, switched interconnects, or other technologies, may be used. In at least one embodiment, graphics processor 1208 is coupled to ring interconnect 1212 via I / O link 1213.

[0109] In at least one embodiment, I / O link 1213 represents at least one of a variety of I / O interconnects, including packaged I / O interconnects that facilitate communication between various processor components and high-performance embedded memory module 1218 (e.g., eDRAM module). In at least one embodiment, each of processor cores 1202A-1202N and graphics processor 1208 uses embedded memory module 1218 as a shared last-level cache.

[0110] In at least one embodiment, processor cores 1202A-1202N are homogeneous cores executing a common instruction set architecture. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), with one or more processor cores 1202A-1202N executing a common instruction set, while one or more other processor cores 1202A-1202N execute a subset of the common instruction set or a different instruction set. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, with one or more cores having relatively high power consumption coupled to one or more power cores having lower power consumption. In at least one embodiment, processor 1200 may be implemented on one or more chips or implemented as a SoC integrated circuit.

[0111] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into processor 1200. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs embodied in Figure 12 The graphics processor 1212, graphics core 1202A-1202N, or other components are used. Furthermore, in at least one embodiment, the inference and / or training operations described herein can use, except... Figure 7A or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor 1200 to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0112] Such components can be used to generate images of objects with synthetic but realistic defects or other variations or enhancements, which may help train defect detection systems.

[0113] Virtualization computing platform

[0114] Figure 13This is an example data flow diagram of process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, process 1300 may be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. Process 1300 may be executed within training system 1304 and / or deployment system 1306. In at least one embodiment, training system 1304 may be used to train, deploy, and implement machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use in deployment system 1306. In at least one embodiment, deployment system 1306 may be configured to offload processing and computing resources in a distributed computing environment to reduce the infrastructure requirements of facility 1302. In at least one embodiment, one or more applications in the pipeline may use or invoke services of deployment system 1306 (e.g., inference, visualization, computation, AI, etc.) during application execution.

[0115] In at least one embodiment, some applications used in the advanced processing and inference pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, a machine learning model may be trained at facility 1302 using data 1308 (e.g., imaging data) generated at facility 1302 (and stored on one or more Picture Archiving and Communication System (PACS) servers at facility 1302), imaging or sequencing data 1308 from another or more facilities, or a combination thereof. In at least one embodiment, training system 1304 may be used to provide applications, services, and / or other resources to generate a deployable machine learning model for the work of deploying system 1306.

[0116] In at least one embodiment, the model registry 1324 may be supported by an object storage system that supports version control and object metadata. In at least one embodiment, it may be available from within a cloud platform via, for example, cloud storage (e.g., Figure 14 The system uses a cloud-compatible application programming interface (API) to access object storage. In at least one embodiment, machine learning models within the model registry 1324 can be uploaded, listed, modified, or deleted by the developer or partner of the system interacting with the API. In at least one embodiment, the API can provide access to methods that allow users with appropriate credentials to associate models with applications, enabling the models to be executed as part of the containerized instantiation of the application.

[0117] In at least one embodiment, training pipeline 1404 ( Figure 14This can include situations where facility 1302 is training its own machine learning model or has an existing machine learning model that needs optimization or updating. In at least one embodiment, imaging data 1308 generated by imaging devices, sequencing devices, and / or other types of devices can be received. In at least one embodiment, once the imaging data 1308 is received, AI-assisted annotation 1310 can be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for the machine learning model. In at least one embodiment, AI-assisted annotation 1310 can include one or more machine learning models (e.g., convolutional neural networks (CNNs)) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, AI-assisted annotation 1310 can then be used directly or adjusted or fine-tuned using annotation tools to generate ground-based data. In at least one embodiment, AI-assisted annotation 1310, labeled clinical data 1312, or a combination thereof can be used as ground-based data for training the machine learning model. In at least one embodiment, the trained machine learning model may be referred to as output model 1316 and may be used by deployment system 1306 as described herein.

[0118] In at least one embodiment, the training pipeline may include a scenario where facility 1302 requires a machine learning model to perform one or more processing tasks for deploying one or more applications in system 1306, but facility 1302 may not currently have such a machine learning model (or may not have a model optimized, efficient, or effective for this purpose). In at least one embodiment, an existing machine learning model may be selected from model registry 1324. In at least one embodiment, model registry 1324 may include machine learning models trained to perform various inference tasks on imaging data. In at least one embodiment, the machine learning model in model registry 1324 may be trained on imaging data from a different facility (e.g., a remote facility) instead of facility 1302. In at least one embodiment, the machine learning model may have already been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training on imaging data from a specific location, training may be performed at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts the off-site transfer of the imaging data. In at least one embodiment, once a model has been trained or partially trained at one location, a machine learning model can be added to model registry 1324. In at least one embodiment, the machine learning model can then be retrained or updated at any number of other facilities, and the retrained or updated model can be used in model registry 1324. In at least one embodiment, a machine learning model (referred to as output model 1316) can then be selected from model registry 1324, and can be used in deployment system 1306 to perform one or more processing tasks for one or more applications of the deployment system.

[0119] In at least one embodiment, the scenario may include facility 1302, which requires a machine learning model to perform one or more processing tasks for deploying one or more applications in system 1306, but facility 1302 may not currently have such a machine learning model (or may not have an optimized, efficient, or effective model). In at least one embodiment, the machine learning model selected from model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at facility 1302 due to population variability, robustness, anomalous diversity of training data, and / or other problems with the training data used to train the machine learning model. In at least one embodiment, AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for training or updating the machine learning model. In at least one embodiment, labeled data 1312 may be used as ground-based data for training the machine learning model. In at least one embodiment, retraining or updating the machine learning model may be referred to as model training 1314. In at least one embodiment, model training 1314 (e.g., AI-assisted annotation 1310, labeled clinical data 1312, or a combination thereof) can be used as ground-based data to retrain or update the machine learning model. In at least one embodiment, the trained machine learning model can be referred to as output model 1316 and can be used by deployment system 1306, as described herein.

[0120] In at least one embodiment, deployment system 1306 may include software 1318, service 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, deployment system 1306 may include a software "stack" such that software 1318 can be built on top of service 1320 and can be used to perform some or all of the processing tasks, and service 1320 and software 1318 can be built on top of hardware 1322 and use hardware 1322 to perform the deployment system's processing, storage, and / or other computational tasks. In at least one embodiment, software 1318 may include any number of different containers, each of which can perform an instantiation of an application. In at least one embodiment, each application can perform one or more processing tasks (e.g., inference, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in a high-level processing and inference pipeline. In at least one embodiment, in addition to receiving and configuring imaging data for use by each container and / or by facility 1302 after processing through the pipeline, advanced processing and inference pipelines (e.g., to convert output back to available data types) can be defined based on the selection of different containers desired or required for processing imaging data 1308. In at least one embodiment, a combination of containers within software 1318 (e.g., constituting a pipeline) may be referred to as a virtual instrument (as described in more detail herein), and the virtual instrument may utilize service 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated within the container.

[0121] In at least one embodiment, the data processing pipeline may receive input data (e.g., imaging data 1308) in a specific format in response to an inference request (e.g., a request from a user of deployment system 1306). In at least one embodiment, the input data may represent one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data may be preprocessed as part of the data processing pipeline to prepare it for processing by one or more applications. In at least one embodiment, post-processing may be performed on the output of one or more inference tasks or other processing tasks of the pipeline to prepare output data for the next application and / or to prepare output data for user transmission and / or use (e.g., as a response to an inference request). In at least one embodiment, the inference task may be performed by one or more machine learning models, such as trained or deployed neural networks, which may include the output model 1316 of training system 1304.

[0122] In at least one embodiment, the tasks of the data processing pipeline can be encapsulated in containers, each container representing a discrete, fully functional instantiation of an application and a virtualized computing environment capable of referencing a machine learning model. In at least one embodiment, containers or applications can be published to a private (e.g., limited access) area of ​​a container registry (described in more detail herein), and trained or deployed models can be stored in a model registry 1324 and associated with one or more applications. In at least one embodiment, an image of an application (e.g., a container image) can be used in the container registry, and once a user selects an image from the container registry for deployment in the pipeline, that image can be used to generate containers for instantiation of the application for use by the user's system.

[0123] In at least one embodiment, a developer (e.g., a software developer, clinician, physician, etc.) can develop, publish, and store an application (e.g., as a container) for performing image processing and / or inference on provided data. In at least one embodiment, a software development kit (SDK) associated with the system can be used to perform development, publication, and / or storage (e.g., to ensure that the developed application and / or container conforms to or is compatible with the system). In at least one embodiment, the developed application can be tested locally using the SDK (e.g., at a first facility, testing data from a first facility), the SDK serving as a system (e.g., Figure 11 System 1100 may support at least some services 1320. In at least one embodiment, since DICOM objects may contain one to hundreds of images or other data types, and due to variations in the data, the developer may be responsible for managing (e.g., setting up constructs for preprocessing built into the application, etc.) the extraction and preparation of incoming data. In at least one embodiment, once verified by system 1300 (e.g., for accuracy), the application becomes available in the container registry for user selection and / or implementation to perform one or more processing tasks on data at the user's facility (e.g., a second facility).

[0124] In at least one embodiment, the developer can then share the application or container over a network for the system (e.g., Figure 13The system 1300 allows for user access and use. In at least one embodiment, completed and validated applications or containers may be stored in a container registry, and associated machine learning models may be stored in a model registry 1324. In at least one embodiment, a requesting entity (which provides an inference or image processing request) may browse the container registry and / or model registry 1324 to obtain applications, containers, datasets, machine learning models, etc., select desired combinations of elements to include in the data processing pipeline, and submit an image processing request. In at least one embodiment, the request may include input data necessary to execute the request (and, in some examples, patient-related data), and / or may include selections of applications and / or machine learning models to be executed when processing the request. In at least one embodiment, the request may then be passed to one or more components of the deployment system 1306 (e.g., the cloud) to perform processing in the data processing pipeline. In at least one embodiment, processing performed by the deployment system 1306 may include referencing elements (e.g., applications, containers, models, etc.) selected from the container registry and / or model registry 1324. In at least one embodiment, once the results are generated through the pipeline, the results can be returned to the user for reference (e.g., for viewing in a suite of viewing applications executed locally, on a local workstation, or on a terminal).

[0125] In at least one embodiment, service 1320 may be utilized to assist in processing or executing applications or containers in the pipeline. In at least one embodiment, service 1320 may include computing services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, service 1320 may provide functionality common to one or more applications in software 1318, thus abstracting functionality into services that can be invoked or utilized by applications. In at least one embodiment, the functionality provided by service 1320 can operate dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using...). Figure 11The parallel computing platform 1130 in the system can be scaled well. In at least one embodiment, it is not required that each application providing the same functionality as the shared service 1320 must have a corresponding instance of service 1320, but rather that service 1320 can be shared between and among various applications. In at least one embodiment, as a non-limiting example, the service may include an inference server or engine that can be used to perform detection or segmentation tasks. In at least one embodiment, a model training service may be included, which can provide the ability to train and / or retrain machine learning models. In at least one embodiment, a data augmentation service may be further included, which can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, conforming to REST, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used, which can add image rendering effects (e.g., ray tracing, rasterization, denoising, sharpening, etc.) to add realism to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, a virtual instrument service may be included, which provides beamforming, segmentation, inference, imaging, and / or support for other applications within the virtual instrument pipeline.

[0126] In at least one embodiment, where service 1320 includes an AI service (e.g., an inference service), as part of application execution, one or more machine learning models can be executed by invoking (e.g., as an API call) the inference service (e.g., an inference server) to execute one or more machine learning models or their processing. In at least one embodiment, where another application includes one or more machine learning models for a segmentation task, the application can invoke the inference service to execute the machine learning models for performing one or more processing operations associated with the segmentation task. In at least one embodiment, software 1318 implementing advanced processing and inference pipelines, including a segmentation application and an anomaly detection application, can be pipelined because each application can invoke the same inference service to execute one or more inference tasks.

[0127] In at least one embodiment, hardware 1322 may include a GPU, CPU, graphics card, AI / deep learning system (e.g., an AI supercomputer, such as NVIDIA's DGX), cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, specially built support for software 1318 and services 1320 in deployment system 1306. In at least one embodiment, GPU processing may be used to perform local processing (e.g., at facility 1302) within the AI / deep learning system, in the cloud system, and / or other processing components of deployment system 1306 to improve the efficiency, accuracy, and performance of image processing and generation. In at least one embodiment, as a non-limiting example, software 1318 and / or services 1320 may be optimized for GPU processing in relation to deep learning, machine learning, and / or high-performance computing. In at least one embodiment, at least some of the computing environment of deployment system 1306 and / or training system 1304 may be executed in a data center, one or more supercomputers, or high-performance computing systems with GPU-optimized software (e.g., a hardware and software combination of an NVIDIA DGX system). In at least one embodiment, as described herein, hardware 1322 may include any number of GPUs that can be invoked to perform data processing in parallel. In at least one embodiment, the cloud platform may also include GPU-optimized execution for deep learning tasks, GPU processing for machine learning tasks, or other computational tasks. In at least one embodiment, an AI / deep learning supercomputer and / or GPU-optimized software (e.g., as provided on NVIDIA's DGX systems) may be used as a hardware abstraction and scaling platform to execute the cloud platform (e.g., NVIDIA's NGC). In at least one embodiment, the cloud platform may integrate application container cluster systems or coordination systems (e.g., Kubernetes) across multiple GPUs to achieve seamless scaling and load balancing.

[0128] Figure 14 This is a system diagram of an example system 1400 for generating and deploying an imaging deployment pipeline according to at least one embodiment. In at least one embodiment, system 1400 can be used to implement Figure 13 The process 1300 and / or other processes include advanced processing and inference pipelines. In at least one embodiment, system 1400 may include training system 1304 and deployment system 1306. In at least one embodiment, training system 1304 and deployment system 1306 may be implemented using software 1318, service 1320 and / or hardware 1322, as described herein.

[0129] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) may be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 may be implemented locally (in relation to a healthcare facility) or as a combination of cloud computing resources and local computing resources. In at least one embodiment, access to the API in cloud 1426 may be restricted to authorized users by establishing security measures or protocols. In at least one embodiment, the security protocol may include a network token, which may be signed by an authentication service (e.g., AuthN, AuthZ, Gluecon, etc.) and may carry appropriate authorization. In at least one embodiment, the API of the virtual instrument (described herein) or other instances of system 1400 may be restricted to a set of public IPs that have been audited or authorized for interaction.

[0130] In at least one embodiment, the various components of system 1400 may communicate with each other using any of a variety of different network types, including but not limited to local area networks (LANs) and / or wide area networks (WANs) via wired and / or wireless communication protocols. In at least one embodiment, communication between facilities and components of system 1400 (e.g., for sending inference requests, for receiving the results of inference requests, etc.) may be transmitted via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet), etc.

[0131] In at least one embodiment, similar to the description herein. Figure 13 As described, training system 1304 can execute training pipeline 1404. In at least one embodiment, where deployment system 1306 uses one or more machine learning models in deployment pipeline 1410, training pipeline 1404 can be used to train or retrain one or more (e.g., pre-trained) models, and / or implement one or more pre-trained models 1406 (e.g., without retraining or updating). In at least one embodiment, as a result of training pipeline 1404, output model 1316 can be generated. In at least one embodiment, training pipeline 1404 can include any number of processing steps, such as, but not limited to, transformation or adaptation of imaging data (or other input data). In at least one embodiment, different training pipelines 1404 can be used for different machine learning models used by deployment system 1306. In at least one embodiment, similar to the description of... Figure 13 The training pipeline 1404 described in the first example can be used for the first machine learning model, similar to the one described above. Figure 13 The training pipeline 1404 described in the second example can be used for a second machine learning model, similar to the one described above. Figure 13The training pipeline 1404 of the third example described can be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 can be used according to the requirements of each corresponding machine learning model. In at least one embodiment, one or more machine learning models may have already been trained and are ready for deployment, so the training system 1304 may not perform any processing on the machine learning models, and one or more machine learning models may be implemented by the deployment system 1306.

[0132] In at least one embodiment, depending on the implementation or embodiment, the output model 1316 and / or the pre-trained model 1406 may include any type of machine learning model. In at least one embodiment, and not limited thereto, the machine learning model used by system 1400 may include models using linear regression, logistic regression, decision trees, support vector machines (SVM), Naive Bayes, k-nearest neighbors (Knn), k-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutions, recursion, perceptrons, long / short-term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machines, etc.), and / or other types of machine learning models.

[0133] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotations, as described herein regarding at least Figure 11More specifically, in at least one embodiment, labeled clinical data 1312 can be generated using any number of techniques (e.g., conventional annotation). In at least one embodiment, in some examples, labels or other annotations can be generated by drawing programs (e.g., annotation programs), computer-aided design (CAD) programs, tagging programs, another type of application suitable for generating annotations or labels for ground reality, and / or can be hand-drawn. In at least one embodiment, ground reality data can be synthetically generated (e.g., generated from computer models or renderings), realistically generated (e.g., designed and generated from real-world data), machine-generated (e.g., extracting features from data using feature analysis and learning, and then generating labels), human-annotated (e.g., taggers or annotation experts, defining the placement of labels), and / or combinations thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by machine learning models), there may be corresponding ground reality data generated by training system 1304. In at least one embodiment, AI-assisted annotation can be performed as part of deployment pipeline 1410; supplementing or replacing AI-assisted annotation included in training pipeline 1404. In at least one embodiment, system 1400 may include a multi-layer platform, which may include a software layer (e.g., software 1318) of a diagnostic application (or other application type) capable of performing one or more medical imaging and diagnostic functions. In at least one embodiment, system 1400 may be communicatively coupled (e.g., via an encrypted link) to a network of PACS servers in one or more facilities. In at least one embodiment, system 1400 may be configured to access and reference data from PACS servers to perform operations such as training machine learning models, deploying machine learning models, image processing, inference, and / or other operations.

[0134] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or certified API that can invoke (e.g., call) an application or container from an external environment (e.g., facility 1302). In at least one embodiment, the application may then invoke or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with their respective applications, and the software 1318 and / or service 1320 may utilize the hardware 1322 to perform processing tasks efficiently and effectively.

[0135] In at least one embodiment, deployment system 1306 may execute deployment pipeline 1410. In at least one embodiment, deployment pipeline 1410 may include any number of applications, which may be sequential, non-sequential, or otherwise applied to imaging data (and / or other data types) – including AI-assisted annotation, the imaging data being generated by imaging devices, sequencing devices, genomics devices, etc., as described above. In at least one embodiment, as described herein, deployment pipeline 1410 for an individual device may be referred to as a virtual instrument for the device (e.g., a virtual ultrasound instrument, a virtual CT scanner, a virtual sequencing instrument, etc.). In at least one embodiment, for a single device, more than one deployment pipeline 1410 may exist, depending on the desired information from the data generated from the device. In at least one embodiment, a first deployment pipeline 1410 may exist if it is desired to detect an anomaly from an MRI machine, and a second deployment pipeline 1410 may exist if it is desired to perform image enhancement from the output of the MRI machine.

[0136] In at least one embodiment, the image generation application may include processing tasks that utilize machine learning models. In at least one embodiment, a user may wish to use their own machine learning model or select a machine learning model from the model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to be included in the application performing the processing tasks. In at least one embodiment, the application may be optional and customizable, and by defining the application's construction, the deployment and implementation of the application for a specific user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of system 1400 (e.g., service 1320 and hardware 1322), the deployment pipeline 1410 can be more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0137] In at least one embodiment, deployment system 1306 may include a user interface (UI) 1414 (e.g., a graphical user interface, a web interface, etc.) that can be used to select applications to be included in deployment pipeline 1410, deploy applications, modify or change applications or their parameters or configurations, use and interact with deployment pipeline 1410 during setup and / or deployment, and / or otherwise interact with deployment system 1306. In at least one embodiment, although not shown with respect to training system 1304, user interface 1414 (or different user interfaces) can be used to select models to be used in deployment system 1306, to select models to be trained or retrained in training system 1304, and / or to otherwise interact with training system 1304.

[0138] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may be used to manage interactions between applications or containers deployed through the pipeline 1410 and services 1320 and / or hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate interactions from application to application, from application to service 1320, and / or from application or service to hardware 1322. In at least one embodiment, although shown as included in software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in service 1320. In at least one embodiment, the application coordination system 1428 (e.g., Kubernetes, DOCKER, etc.) may include a container coordination system that can group applications into containers as logical units for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from the deployment pipeline 1410 (e.g., rebuilding applications, splitting applications, etc.) with individual containers, each application can execute in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0139] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed independently (e.g., a first user or developer can develop, modify, and deploy a first application, and a second user or developer can develop, modify, and deploy a second application separate from the first user or developer). This allows focus on the tasks of a single application and / or container without being hindered by the tasks of another application or container. In at least one embodiment, the pipeline manager 1412 and the application coordination system 1428 can facilitate communication and collaboration between different containers or applications. In at least one embodiment, the application coordination system 1428 and / or the pipeline manager 1412 can facilitate communication and resource sharing between and within each application or container, provided that the expected inputs and / or outputs of each container or application are known to the system (e.g., based on the construction of the application or container). In at least one embodiment, since one or more applications or containers in the deployment pipeline 1410 can share the same services and resources, the application coordination system 1428 can coordinate, load balance, and determine the sharing of services or resources between and within the various applications or containers. In at least one embodiment, the scheduler can be used to track the resource requirements of applications or containers, the current or planned use of these resources, and resource availability. Therefore, in at least one embodiment, the scheduler can allocate resources to different applications and distribute resources between and among applications, taking into account the system's needs and availability. In some examples, the scheduler (and / or other components of the application coordination system 1428) can determine resource availability and distribution based on constraints imposed on the system (e.g., user constraints), such as Quality of Service (QoS), the urgency of data output (e.g., to determine whether to perform real-time processing or delayed processing), etc.

[0140] In at least one embodiment, service 1320, utilized and shared by applications or containers in deployment system 1306, may include computing service 1416, AI service 1418, visualization service 1420, and / or other service types. In at least one embodiment, an application may invoke (e.g., execute) one or more services 1320 to perform processing operations for the application. In at least one embodiment, an application may utilize computing service 1416 to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, one or more computing services 1416 may be utilized to perform parallel processing (e.g., using parallel computing platform 1430) to process data substantially simultaneously through one or more applications and / or one or more tasks of a single application. In at least one embodiment, parallel computing platform 1430 (e.g., NVIDIA's CUDA) may implement general-purpose computing on a GPU (GPGPU) (e.g., GPU / graphics 1422). In at least one embodiment, the software layer of parallel computing platform 1430 may provide access to the GPU's virtual instruction set and parallel computing elements to execute computing kernels. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, memory may be shared between and within multiple containers, and / or between and within different processing tasks within a single container. In at least one embodiment, inter-process communication (IPC) calls may be generated for multiple containers and / or multiple processes within containers to enable the use of the same data (e.g., multiple different stages of one or more applications processing the same information) from a shared memory segment of the parallel computing platform 1430. In at least one embodiment, instead of copying data and moving it to different locations in memory (e.g., read / write operations), the same data in the same memory location can be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, this information about the new location of the data can be stored and shared between applications because the resulting data from processing is used to generate new data. In at least one embodiment, the location of the data, and the location of the updated or modified data, may be part of the definition of how the payload in the container is understood.

[0141] In at least one embodiment, AI service 1418 may be used to perform an inference service for executing a machine learning model associated with the application (e.g., a task to perform one or more processing tasks of the application). In at least one embodiment, AI service 1418 may utilize AI system 1424 to execute a machine learning model (e.g., a neural network such as a CNN) for segmentation, reconstruction, object detection, feature detection, classification, and / or other inference tasks. In at least one embodiment, the application deploying pipeline 1410 may use one or more output models 1316 of self-training system 1304 and / or other models of the application to perform inference on imaging data. In at least one embodiment, two or more examples of inference using application coordination system 1428 (e.g., a scheduler) may be available. In at least one embodiment, a first category may include a high-priority / low-latency path that can implement a higher service level protocol, such as for performing inference on urgent requests in emergency situations or for radiologists during diagnostic procedures. In at least one embodiment, a second category may include a standard priority path that can be used for requests that may not be urgent or for situations where analysis can be performed at a later time. In at least one embodiment, the application coordination system 1428 may allocate resources (e.g., services 1320 and / or hardware 1322) based on priority paths for different inference tasks of the AI ​​service 1418.

[0142] In at least one embodiment, shared memory may be installed into AI service 1418 in system 1400. In at least one embodiment, shared memory may operate as a cache (or other storage device type) and may be used to process inference requests from applications. In at least one embodiment, when an inference request is submitted, a set of API instances of deployment system 1306 may receive the request and may select one or more instances (e.g., for best fit, for load balancing, etc.) to process the request. In at least one embodiment, to process the request, the request may be fed into a database, and if not already in the cache, a machine learning model may be located from model registry 1324. A verification step may ensure that an appropriate machine learning model is loaded into the cache (e.g., shared memory), and / or a copy of the model may be saved to the cache. In at least one embodiment, if the application is not already running or there are not enough instances of the application, a scheduler (e.g., the scheduler of pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if an inference server has not yet been started to execute the model, an inference server may be started. Any number of inference servers may be started for each model. In at least one embodiment, in a pull model that clusters inference servers, the model can be cached whenever load balancing is favorable. In at least one embodiment, the inference servers can be statically loaded into the corresponding distributed servers.

[0143] In at least one embodiment, an inference server running in a container can be used to perform inference. In at least one embodiment, an instance of the inference server can be associated with a model (and optionally multiple versions of the model). In at least one embodiment, if an instance of the inference server does not exist when a request to perform inference on the model is received, a new instance can be loaded. In at least one embodiment, when the inference server is started, a model can be passed to the inference server, allowing the same container to be used to serve different models, as long as the inference server runs as different instances.

[0144] In at least one embodiment, during application execution, an inference request for a given application can be received, and a container (e.g., an instance of a hosted inference server) can be loaded (if not already loaded), and a launcher can be invoked. In at least one embodiment, preprocessing logic within the container can (e.g., using a CPU and / or GPU) load, decode, and / or perform any additional preprocessing on the incoming data. In at least one embodiment, once the data is ready for inference, the container can infer the data as needed. In at least one embodiment, this can include a single inference call for an image (e.g., a hand X-ray) or can request inference for hundreds of images (e.g., a chest CT scan). In at least one embodiment, the application can summarize the results before completion, which may include, but is not limited to, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating visualizations, or generating text to summarize the results. In at least one embodiment, different priorities can be assigned to different models or applications. For example, some models may have a real-time (TAT less than 1 minute) priority, while other models may have a lower priority (e.g., TAT less than 10 minutes). In at least one embodiment, model execution time can be measured from the requesting agency or entity, and may include cooperative network traversal time and inference service execution time.

[0145] In at least one embodiment, the transfer of requests between service 1320 and the inference application can be hidden behind a software development kit (SDK) and robust transfer can be provided via queues. In at least one embodiment, requests are placed in queues via an API for individual application / tenant ID combinations, and the SDK pulls requests from the queues and provides them to the application. In at least one embodiment, the name of the queue can be provided in the environment where the SDK picks up the queue. In at least one embodiment, asynchronous communication via queues may be useful because it allows any instance of the application to pick up work when it becomes available. Results can be sent back via queues to ensure no data loss. In at least one embodiment, queues can also provide the ability to partition work, as the highest priority work can go into a queue connected to a majority of instances of the application, while the lowest priority work can go into a queue connected to a single instance that processes tasks in the order they are received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in cloud 1426, and the inference service can perform inference on the GPU.

[0146] In at least one embodiment, visualization service 1420 can be used to generate visualizations for viewing the output of application and / or deployment pipeline 1410. In at least one embodiment, visualization service 1420 can utilize GPU / graphics 1422 to generate visualizations. In at least one embodiment, visualization service 1420 can implement rendering effects such as ray tracing to generate higher quality visualizations. In at least one embodiment, visualizations can include, but are not limited to, 2D image rendering, 3D volume rendering, 3D volume reconstruction, 2D tomographic slicing, virtual reality display, augmented reality display, etc. In at least one embodiment, a virtualized environment can be used to generate virtual interactive displays or environments (e.g., virtual environments) for system users (e.g., doctors, nurses, radiologists, etc.) to interact with. In at least one embodiment, visualization service 1420 can include an internal visualizer, cinematic and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0147] In at least one embodiment, hardware 1322 may include GPU / graphics 1422, AI system 1424, cloud 1426, and / or any other hardware for performing training system 1304 and / or deployment system 1306. In at least one embodiment, GPU / graphics 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs that can be used to perform processing tasks for any feature or function of computing service 1416, AI service 1418, visualization service 1420, other services, and / or software 1318. For example, for AI service 1418, GPU / graphics 1422 may be used to perform preprocessing on imaging data (or other data types used by machine learning models), postprocessing on the output of machine learning models, and / or inference (e.g., to execute machine learning models). In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may use GPU / graphics 1422. In at least one embodiment, cloud 1426 may include a GPU-optimized platform for deep learning tasks. In at least one embodiment, AI system 1424 may use a GPU, and one or more AI systems 1424 may be used to perform cloud 1426 (or at least part of a task for deep learning or inference). Similarly, although hardware 1322 is shown as a discrete component, this is not intended to be limiting, and any component of hardware 1322 may be combined with or utilized by any other component of hardware 1322.

[0148] In at least one embodiment, AI system 1424 may include a specially built computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, in addition to CPU, RAM, memory, and / or other components, features, or functions, AI system 1424 (e.g., NVIDIA's DGX) may also include software (e.g., a software stack) that can be used to perform GPU-optimized tasks using multiple GPUs / graphics 1422. In at least one embodiment, one or more AI systems 1424 may be implemented in a cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of system 1400.

[0149] In at least one embodiment, cloud 1426 may include GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that can provide a GPU-optimized platform for performing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include AI system 1424 for performing one or more AI-based tasks of system 1400 (e.g., as a hardware abstraction and scaling platform). In at least one embodiment, cloud 1426 may be integrated with application coordination system 1428 utilizing multiple GPUs to achieve seamless scaling and load balancing between and within applications and services 1320. In at least one embodiment, as described herein, cloud 1426 may be responsible for performing at least some of the services 1320 of system 1400, including computing service 1416, AI service 1418, and / or visualization service 1420. In at least one embodiment, cloud 1426 may perform large and small batch inference (e.g., perform NVIDIA's TENSORRT), provide accelerated parallel computing APIs and platform 1430 (e.g., NVIDIA's CUDA), perform application coordination system 1428 (e.g., KUBERNETES), provide graphics rendering APIs and platform (e.g., for ray tracing, 2D graphics, 3D graphics and / or other rendering techniques to produce higher quality cinematic effects), and / or provide other functionalities for system 1400.

[0150] Figure 15A A data flow diagram of a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment is shown. In at least one embodiment, a non-limiting example can be used. Figure 15A The system 1500 executes the process 1500. In at least one embodiment, the process 1500 may utilize services and / or hardware, as described herein. In at least one embodiment, the refined model 1512 generated by the process 1500 may be executed by a deployment system for one or more containerized applications in the deployment pipeline.

[0151] In at least one embodiment, model training 1514 may include retraining or updating the initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data, such as customer dataset 1506, and / or new ground reality data associated with the input data). In at least one embodiment, to retrain or update the initial model 1504, the output or loss layer of the initial model 1504 may be reset or deleted, and / or replaced with an updated or new output or loss layer. In at least one embodiment, the initial model 1504 may have previously fine-tuned parameters (e.g., weights and / or biases) retained from previous training, so training or retraining 1514 may not require as much time or processing as training the model from scratch. In at least one embodiment, during model training 1514, when generating predictions on the new customer dataset 1506 by resetting or replacing the output or loss layer of the initial model 1504, the parameters of the new dataset may be updated and readjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0152] In at least one embodiment, the pre-trained model 1506 may be stored in a data store or registry. In at least one embodiment, the pre-trained model 1506 may have been trained at least partially at one or more facilities other than the facility executing process 1500. In at least one embodiment, to protect the privacy and rights of patients, subjects, or customers at different facilities, the pre-trained model 1506 may have been trained locally using locally generated customer or patient data. In at least one embodiment, the pre-trained model 1506 may be trained using cloud and / or other hardware, but confidential, privacy-protected patient data may not be transferred to, used by, or accessed by any component of the cloud (or other non-local hardware). In at least one embodiment, if the pre-trained model 1506 is trained using patient data from more than one facility, the pre-trained model 1506 may have been trained separately for each facility before training on patient or customer data from another facility. In at least one embodiment, such as when customer or patient data has been published for privacy reasons (e.g., by abandonment, for experimental purposes, etc.), or where customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train a pre-trained model 1506 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0153] In at least one embodiment, when selecting an application for use in the deployment pipeline, the user may also select a machine learning model for a specific application. In at least one embodiment, the user may not have a model available, so the user may select a pre-trained model to use with the application. In at least one embodiment, the pre-trained model may not be optimized to generate accurate results on the user facility's customer dataset 1506 (e.g., based on patient diversity, demographics, type of medical imaging equipment used, etc.). In at least one embodiment, the pre-trained model may be updated, retrained, and / or fine-tuned for use at various facilities before being deployed into the deployment pipeline for use with one or more applications.

[0154] In at least one embodiment, a user may select a pre-trained model to update, retrain, and / or fine-tune, and this pre-trained model may be referred to as the initial model 1504 of the training system in process 1500. In at least one embodiment, a client dataset 1506 (e.g., imaging data, genomic data, sequencing data, or other data types generated by equipment at the facility) may be used to perform model training (which may include, but is not limited to, transfer learning) on ​​the initial model 1504 to generate a refined model 1512. In at least one embodiment, ground-based data corresponding to the client dataset 1506 may be generated by the training system 1304. In at least one embodiment, the ground-based data may be generated at the facility, at least in part, by clinicians, scientists, physicians, or practitioners.

[0155] In at least one embodiment, AI-assisted annotation may be used to generate ground-based data in some examples. In at least one embodiment, AI-assisted annotation (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted ground-based data for a customer dataset. In at least one embodiment, a user may use the annotation tool within a user interface (graphical user interface (GUI)) on a computing device.

[0156] In at least one embodiment, user 1510 can interact with the GUI via computing device 1508 to edit or fine-tune annotations or automatic annotations. In at least one embodiment, polygon editing features can be used to move the vertices of a polygon to more precise or fine-tuned positions.

[0157] In at least one embodiment, once the customer dataset 1506 has associated ground-based data, the ground-based data (e.g., from AI-assisted annotations, manual labeling, etc.) can be used to generate a refined model 1512 during model training. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 an arbitrary number of times, and the ground-based data can be used to update the parameters of the initial model 1504 until an acceptable level of accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 is generated, it can be deployed in one or more deployment pipelines at the facility to perform one or more processing tasks related to medical imaging data.

[0158] In at least one embodiment, the refined model 1512 can be uploaded to a pre-trained model registry for selection by another facility. In at least one embodiment, this process can be performed at any number of facilities, allowing the refined model 1512 to be further refined an arbitrary number of times on a new dataset to generate a more general model.

[0159] Figure 15B This is an example illustration of a client-server architecture 1532 for enhancing an annotation tool using a pre-trained annotation model, according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 may be instantiated based on the client-server architecture 1532. In at least one embodiment, the annotation tool 1536 in an imaging application can assist ray surgeons, for example, in identifying organs and abnormalities. In at least one embodiment, the imaging application may include software tools, as a non-limiting example, that help user 1510 identify several extreme points on a specific organ of interest in a raw image 1534 (e.g., in a 3D MRI or CT scan) and receive automatic annotation results for all 2D slices of that specific organ. In at least one embodiment, the results may be stored in a data store as training data 1538 and used as (e.g., but not limited to) ground-based data for training. In at least one embodiment, when computing device 1508 sends extreme points for AI-assisted annotation, for example, a deep learning model may receive this data as input and return inference results for segmenting organs or abnormalities. In at least one embodiment, a pre-instantiated annotation tool (e.g., Figure 15BThe AI-assisted annotation tool 1536B can be enhanced by making API calls (e.g., API call 1544) to a server (such as annotation assistant server 1540), which may include a set of pre-trained models 1542 stored, for example, in an annotation model registry. In at least one embodiment, the annotation model registry may store the pre-trained models 1542 (e.g., machine learning models, such as deep learning models) pre-trained to perform AI-assisted annotation on specific organs or anomalies. In at least one embodiment, these models can be further updated using a training pipeline. In at least one embodiment, the pre-installed annotation tool can be improved over time as new labeled data is added.

[0160] Other variations are within the spirit of this disclosure. Therefore, although the disclosed technology is readily adaptable to various modifications and alternative constructions, certain embodiments thereof are illustrated in the accompanying drawings and have been described in detail above. However, it should be understood that the disclosure is not intended to be limited to one or more specific forms disclosed, but rather, it is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of this disclosure as defined in the appended claims.

[0161] Unless otherwise stated or obviously contradicted by the context, the terms “a,” “an,” and “the,” and similar references, used in the context of describing the disclosed embodiments (particularly in the context of the appended claims), should be interpreted as encompassing both singular and plural forms, rather than as definitions of the terms. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” should be interpreted as open-ended terms (meaning “including, but not limited to”). The term “connection” (referring to a physical connection where not modified) should be interpreted as partially or wholly contained, attached to, or joined together, even with some intervention. Unless otherwise indicated herein, references to numerical ranges herein are intended only as a way of abbreviating each individual value falling within that range, and each individual value is incorporated into the specification as if it were separately described herein. Unless otherwise indicated or contradicted by the context, the use of the terms “set” (e.g., “item set”) or “subset” should be interpreted as a non-empty set comprising one or more members. Furthermore, unless otherwise indicated or contradicted by the context, the term "subset" of a corresponding set does not necessarily refer to an appropriate subset of the corresponding set, but rather the subset and the corresponding set can be equal.

[0162] Unless otherwise explicitly stated or clearly contradicted by the context, connective phrases such as “at least one of A, B, and C” or “at least one of A, B, and C” are understood in the context to generally refer to items, terms, etc., which can be A or B or C, or any non-empty subset of the set A, B, and C. For example, in an illustrative example of a set with three members, the connective phrases “at least one of A, B, and C” and “at least one of A, B, and C” refer to any of the following sets: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Therefore, such connective language is generally not intended to imply that some embodiments require the presence of at least one of A, at least one of B, and at least one of C. Additionally, unless otherwise stated or contradicted by the context, the term “multiple” indicates a plural state (e.g., “multiple items” means multiple items). The number of items in a multiple item is at least two, but may be more if explicitly indicated or indicated by the context. Furthermore, unless otherwise stated or clearly understood from the context, the phrase “based on” means “at least partially based on” rather than “based on only”.

[0163] Unless otherwise indicated herein or clearly contradicted by the context, the operations of the processes described herein may be performed in any suitable order. In at least one embodiment, processes such as those described herein (or variations thereof and / or combinations thereof) are executed under the control of one or more computer systems configured with executable instructions and are implemented as code (e.g., executable instructions, one or more computer programs, or one or more application programs) that is executed jointly on one or more processors via hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors. In at least one embodiment, the computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagating transient electrical or electromagnetic transmissions) but includes non-transitory data storage circuitry (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on one or more non-transitory computer-readable storage media (or other memory for storing executable instructions) on which executable instructions are stored, which, when executed by one or more processors of a computer system (i.e., as a result of execution), cause the computer system to perform the operations described herein. In at least one embodiment, the set of non-transitory computer-readable storage media comprises multiple non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media lack all the code, but the multiple non-transitory computer-readable storage media collectively store all the code. In at least one embodiment, the executable instructions are executed such that different instructions are executed by different processors; for example, the non-transitory computer-readable storage media store the instructions, and the main central processing unit (“CPU”) executes some instructions while the graphics processing unit (“GPU”) executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and the different processors execute different subsets of the instructions.

[0164] Therefore, in at least one embodiment, the computer system is configured to implement one or more services that perform the operations of the processes described herein, either individually or collectively, and such a computer system is configured with suitable hardware and / or software to enable the implementation of the operations. Furthermore, the computer system implementing at least one embodiment of this disclosure is a single device, and in another embodiment it is a distributed computer system comprising multiple devices operating in different ways, such that the distributed computer system performs the operations described herein, and that a single device does not perform all the operations.

[0165] The use of any and all examples or exemplary language (e.g., “such as”) provided herein is intended only to better illustrate embodiments of this disclosure and does not constitute a limitation on the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any unclaimed element is essential to the practice of the disclosure.

[0166] All references cited in this article, including publications, patent applications and patents, are incorporated herein by reference as if each reference were individually and specifically indicated to be incorporated herein by reference and the entire contents of which are described herein.

[0167] The terms “coupled” and “connected”, and their derivatives, may be used in the specification and claims. It should be understood that these terms may not be intended to be synonyms with each other. Rather, in certain examples, “connected” or “coupled” may be used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. “Coupled” may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0168] Unless otherwise expressly stated, it will be understood that throughout this specification, terms such as “processing,” “computing,” “determining,” etc., refer to the actions and / or processes of a computer or computing system or similar electronic computing device that process and / or convert data represented as physical quantities (e.g., electrons) in the registers and / or memory of the computing system into other data represented as physical quantities in the memory, registers, or other such information storage, transmission, or display devices of the computing system.

[0169] In a similar manner, the term "processor" can refer to any device or part of memory that processes electronic data from registers and / or memory and converts that electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" can be a CPU or a GPU. A "computing platform" can include one or more processors. As used herein, a "software" process can include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process can refer to multiple processes that execute instructions sequentially or intermittently, sequentially, or in parallel. The terms "system" and "method" are used interchangeably herein, provided that a system can embody one or more methods, and a method can be considered a system.

[0170] This document refers to the process of acquiring, obtaining, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine. Analog and digital data can be acquired, obtained, received, or input in various ways, such as by receiving data as a parameter to a function call or a call to an application programming interface (API). In some implementations, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data via a serial or parallel interface. In another implementation, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data from a providing entity to an acquiring entity via a computer network. Reference can also be made to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data can be implemented by transmitting data as an input or output parameter to a function call, an API, or an inter-process communication mechanism.

[0171] While the discussion above illustrates example implementations of the described technologies, other architectures can be used to implement the described functionality and are intended to fall within the scope of this disclosure. Furthermore, although specific assignments of responsibilities have been defined above for discussion purposes, various functions and responsibilities can be assigned and divided in different ways depending on the circumstances.

[0172] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or actions described. Rather, specific features and actions are disclosed as exemplary forms for implementing the claims.

Claims

1. A computer-implemented method, comprising: Obtain image data for the object, an indication of the defect type, and one or more environmental conditions; Under one or more environmental conditions, a rendering engine is used to generate one or more images including a representation of the object, the one or more images depicting at least one instance of the defect type to at least a portion of the representation of the object; as well as One or more images are provided as training data to update one or more parameters of a neural network model to detect object defects.

2. The computer-implemented method as described in claim 1, further comprising: One or more images are provided as training data to train a generative network to generate realistic images of defective objects.

3. The computer-implemented method of claim 1, wherein the defect type corresponds to at least one of the following: geometric defect, assembly defect, or material defect.

4. The computer-implemented method as described in claim 1, further comprising: Provides indications of one or more aspects of the defect type to be represented in the one or more images as additional input to the rendering engine.

5. The computer-implemented method of claim 1, wherein the image data for the object is captured for the physical object using at least one of the following: a lidar system, a camera, or an image sensor.

6. The computer-implemented method as described in claim 1, further comprising: The rendering engine is used to generate multiple synthetic environments corresponding to the one or more environmental conditions based on the 3D model of the environment.

7. The computer-implemented method of claim 6, wherein the one or more environmental conditions include at least one of the following: lighting conditions, weather conditions, object location, material conditions, or texture conditions.

8. The computer-implemented method as described in claim 1, further comprising: The rendering engine is used to generate one or more additional images that include a representation of the object having at least one additional defect of the defect type or a different defect type.

9. A processor, comprising one or more circuits, for: Provides image data of the object and an indication of the defect type as input to the generative model; and The generated image is received from the generative model and based on the image data, including a representation of the object having at least one defect of the indicated defect type.

10. The processor of claim 9, wherein the one or more circuits are further configured to: The generated images are provided as training data to train the defect detection model.

11. The processor of claim 9, wherein the defect type corresponds to at least one of the following: geometric defect, assembly defect, or material defect.

12. The processor of claim 9, wherein the one or more circuits are further configured to: Provides an indication of the degree to which the defect type is to be represented in one or more images as additional input to the generative model.

13. The processor of claim 9, wherein the image data for the object is captured against the physical object using at least one of the following: a lidar system, a camera, or an image sensor.

14. The processor of claim 9, wherein the one or more circuits are further configured to: Multiple synthetic environments with one or more environmental conditions are generated using a 3D model of the environment.

15. The processor of claim 9, wherein the one or more circuits are further configured to: The generative model is used to generate one or more additional images of the object, including at least one additional defect having the said defect type or different defect types.

16. The processor of claim 9, wherein the processor is included in a system comprising at least one of the following: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; Systems used to perform digital twin operations; A system for performing optical transmission simulation; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; Systems used to generate or present virtual reality (VR) content; A system for generating or presenting augmented reality (AR) content; A system for generating or presenting mixed reality (MR) content; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; A system for performing hardware tests using simulation; Systems for generating synthetic data; A system for performing generative operations using large language model LLM; A system for performing generative operations using a visual language model (VLM); A collaborative content creation platform for 3D assets; or A system that utilizes cloud computing resources at least in part.

17. A system comprising one or more processors for generating one or more images of a physical object having at least one synthetic defect indicating a defect type using a generative model under one or more environmental conditions, and providing said one or more images as a dataset to train a defect detection model.

18. The system of claim 17, wherein the one or more environmental conditions include at least one of the following: lighting conditions, weather conditions, object location, material conditions, or texture conditions.

19. The system of claim 17, wherein the at least one indicated defect type corresponds to at least one of the following: geometric defect, assembly defect, or material defect.

20. The system of claim 17, wherein the system comprises at least one of the following: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; Systems used to perform digital twin operations; A system for performing optical transmission simulation; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; Systems used to generate or present virtual reality (VR) content; A system for generating or presenting augmented reality (AR) content; A system for generating or presenting mixed reality (MR) content; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; A system for performing hardware tests using simulation; Systems for generating synthetic data; Systems for performing generative operations using large language models (LLMs); Systems for performing generative operations using visual language models (VLMs); A collaborative content creation platform for 3D assets; or A system that utilizes cloud computing resources at least in part.

Images