Identifying replica objects using canonical forms in content creation systems and applications

Abstract

Embodiments of the present disclosure relate to identifying replica objects using canonical forms in content creation systems and applications. Systems and methods for determining replica objects in an interactive environment are disclosed. Connectivity information of an object may be used to map a set of three linearly independent vectors corresponding to a transform applied to the object. The three linearly independent vectors may be used to form a canonical form of the first object and the second object to determine whether the first object and the second object are replicas or approximate replicas. The replica object or a copy similar to the replica object may then be deleted from the interaction environment and represented by a common object to which one or more additional transformations are applied.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of U.S. non-provisional patent application No. 18 / 477,651, filed on September 29, 2023, entitled “Identifying Duplicate Objects Using a Canonical Form in Content Creation Systems and Applications,” the entire disclosure of which is incorporated herein in its entirety for all purposes. Background Art

[0003] Universal Scene Description (USD) is a file format for describing scenes, such as scenes within a collaborative environment where multiple users can interact with three-dimensional (3D) and two-dimensional (2D) content. The USD file format may include information about data objects for rendering and display within the environment, which may allow users to edit, manipulate, or otherwise interact with the data objects. Data objects may be generated by a variety of different parent applications with different file types that are collected and subsequently merged within the environment. The information of the data objects may include geometric information, textures, colors, and various other data that may be used by the parent application or the interactive environment. Scene descriptions may be difficult to process or save in memory. As scenes within an environment expand to include more objects and greater complexity, the size of the USD file may become unmanageable. This is particularly true where a single object is replicated multiple times within the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0004] Various embodiments according to the present disclosure will be described with reference to the accompanying drawings, in which:

[0005] Figure 1 An example environment for importing an object into an interactive environment according to various embodiments is shown;

[0006] Figure 2 illustrates an example object moving between two different orientations based on an applied transformation in accordance with various embodiments;

[0007] Figure 3A An example transformation determination technique based on connectivity information of an object according to various embodiments is shown;

[0008] Figure 3B An example transformation mapping technique based on connectivity information of an object according to various embodiments is shown;

[0009] Figure 4 An example process for identifying duplicate objects based on connectivity information according to various embodiments is shown;

[0010] Figure 5A An example process for determining a transformation associated with an object is shown in accordance with various embodiments;

[0011] Figure 5B An example process for determining a replica object based on connectivity information according to various embodiments is shown;

[0012] Figure 6 Components of a distributed system that can be used to update or perform inference using a machine learning model are shown in accordance with at least one embodiment;

[0013] Fig. 7A Inference and / or training logic according to at least one embodiment is shown;

[0014] Figure 7B Inference and / or training logic according to at least one embodiment is shown;

[0015] Figure 8 An example data center system is shown in accordance with at least one embodiment;

[0016] Fig. 9 A computer system according to at least one embodiment is shown;

[0017] Fig.10 A computer system according to at least one embodiment is shown;

[0018] Fig.11 illustrates at least a portion of a graphics processor according to one or more embodiments;

[0019] Fig.12 illustrates at least a portion of a graphics processor according to one or more embodiments;

[0020] Fig.13 is an example data flow diagram of a high-level computing pipeline according to at least one embodiment;

[0021] Fig.14 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

[0022] Fig.15A and Fig. 15B A data flow diagram of a process for training a machine learning model, and a client-server architecture for augmenting an annotation tool with a pre-trained annotation model, according to at least one embodiment are shown. DETAILED DESCRIPTION

[0023] Various embodiments will be described in the following description. For the purpose of explanation, specific configurations and details are set forth 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 may be implemented without the specific details. In addition, well-known features may be omitted or simplified to avoid obscuring the described embodiments.

[0024] The systems and methods described herein may be used by, but are not limited to, non-autonomous vehicles or machines, semi-autonomous vehicles or machines (e.g., in in-cabin infotainment or digital or driver virtual assistance applications), autonomous vehicles or machines, manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, spacecraft, boats, shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, aircraft, construction vehicles, trains, underwater vehicles, remotely controlled vehicles (e.g., drones), and / or other vehicle types. In addition, the systems and methods described herein can be used for various 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, safety 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 artificial intelligence (AI), generative AI with large language model (LLM), light transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation of 3D assets, cloud computing, and / or any other suitable application.

[0025] The disclosed embodiments can 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, 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 including one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least in part in a data center, systems for performing conversational AI operations, systems for performing generative AI using LLMs, systems for performing light transport simulations, systems for performing collaborative content creation of 3D assets, systems implemented at least in part using cloud computing resources, and / or other types of systems.

[0026] Methods according to various embodiments may be used to identify duplicate (or near-duplicate) objects within an interactive environment. Various embodiments may identify copies (e.g., duplicate data objects having features within a threshold of each other) placed at various different locations within a scene. For example, an efficiently designed scene may include copies of an object, such as a chair, that is placed multiple times around a table. To improve efficiency, the chair (e.g., an object file associated with the chair) should be stored only once and then copied / replicated at various different locations, such as by using a matrix for each chair to define the position of the chair in the scene. Duplication may save resources and costs associated with network traffic, disk space, memory, and / or the like. In contrast, an inefficient design of a scene representation would define / load a separate chair for each location of the chair within the scene. Thus, additional memory and resources may be consumed. Scaling may be difficult for scenes with multiple duplicate objects, such as an industrial scene with thousands of fasteners or a stadium with thousands of chairs. Various embodiments may include data objects generated by a non-native application, which may include one or more exporters to prepare the data objects for use with an environment. Returning to the example of the chairs, during the export process, the chairs may be depth transformed in order to place the chairs at their intended locations within the scene. In addition, each depth transform may be different for each chair. Therefore, the point coordinates of each copy will be completely different. The described systems and methods can solve problems associated with objects that have been manipulated or otherwise modified by a depth transform in which the point coordinates of a copy or approximate copy are different due to the export.

[0027] For example, the object may correspond to a three-dimensional (3D) object generated using one or more applications. In at least one embodiment, the 3D object may include an object representation using, for example, a mesh-based method, wherein a mesh (e.g., a polygonal mesh, a triangular mesh, etc.) may be formed by a collection of vertices, edges, and faces to define the shape of a polyhedral object. In addition, various embodiments may also be extended to other object representations, including, but not limited to, non-uniform rational basis splines (NURBS), Bezier patches, subdivision surfaces, etc. As described herein, each of these representations may share one or more features that enable the system of the method disclosed herein to be used. For example, a polygonal mesh includes vertices, edges, and faces to represent an object, and a subdivision surface is also represented by a polygonal mesh generated by a recursive algorithm. Similarly, NURBS may include a generalized surface and control points to form a control polygon representing a mesh. In addition, a Bezier surface is defined by a set of control points, wherein the surface is located between the control points to form a patch mesh. Therefore, due to several overlapping features and / or components, the system and method of the present disclosure can be extended to a variety of different object representations, such as 3D object representations, etc. Objects can be provided for use in an interactive environment. If the exporter (e.g., an exporter associated with a native application that creates an object) keeps the grid points unchanged and provides one or more transformations to place the object in the scene, the grid of the replica will be the same (e.g., the same or within a threshold distance from each other). As an alternative, one or more exporters apply these transformations to the points in the grid. In other words, when an object is exported from a native parent application, one or more transformations can be applied to the object at the point-level. Due to the depth transformation, the replica (or approximate replica) object may have different coordinates from the obvious replica due to rounding errors, etc., so the hash (or hash) value between the two objects cannot be used for de-duplication. In some instances, the coordinates of these points may be significantly different. Going back to the example of the chairs, the six chairs around the table, even if the chairs are "the same", will have different coordinates due to their different coordinate positions in the scene. As a result, objects may be stored separately, increasing the size of the Universal Scene Description (USD) file, taking up more storage space, and potentially resulting in a slower or more delayed user experience. In addition, existing methods also suffer from bandwidth usage and wasted time when transmitting data, as well as graphics processing unit (GPU) memory usage due to the additional data for each undetected replica in the scene.These problems may be exacerbated and become particularly difficult to handle for very large scenes such as factories, where, without deduplication, each copy of a screw or fastener may take up additional GPU memory. However, with deduplication, screws, fasteners, etc. can be stored only once (or at least fewer copies than many objects in the scene). Therefore, with deduplication, the GPU memory usage of the scene can be substantially reduced to the number of unique meshes that appear in the scene. Therefore, a deduplicated scene can be loaded on one GPU, while a scene containing replicas may require an entire server cluster. The systems and methods of the present disclosure overcome these challenges by determining a canonical grid for mapping objects after a deep transformation. Therefore, replicas and / or approximate replica objects can be identified and deleted to store only a threshold number of objects (e.g., only one copy). Then, a single copy can be replicated throughout the environment by applying one or more additional transformations to modify the object position in 3D space.

[0028] Various embodiments are directed to receiving an object within an interactive environment from a native source application, and identifying at least three linearly independent vectors from a selected origin. In at least one embodiment, the three linearly independent vectors may not be placed perpendicular to each other (e.g., vector A may not be perpendicular to vector B, and vector B may not be perpendicular to vector C). In certain embodiments, the three linearly independent vectors may be placed perpendicular to each other (e.g., vector A is perpendicular to vector B, and vector B is perpendicular to vector C). The three linearly independent vectors may be designated as the xyz coordinates of the object, and the points forming the three vectors. Then, when comparing another object to determine whether the other object is a replica or an approximate replica, the xyz coordinates may be mapped to the same point of the other object. If the xyz coordinates are mapped to the other object within a threshold range, the objects may be considered replicas or approximate replicas, and therefore, only one copy may be saved to represent the two objects. By identifying replicas and / or approximate replicas, resources may be saved. In addition, converting the object meshes to their canonical form provides a structure for performing other transformations or other modifications to the objects in the interactive environment, thereby maintaining the functionality of the environment. For example, additional transformations may be applied to modify object position or orientation, which may include using one or more rigid transformations (eg, transformations in which vectors are perpendicular and normalized to a length of 1).

[0029] It will be apparent to one of ordinary skill in the art that a variety of such functionality may also be employed within the scope of the various embodiments given the teachings and implications contained herein.

[0030] Figure 1An example environment 100 is shown in which various aspects of the present disclosure can be performed. In this example, a content generation environment 102 can be used to create one or more content elements that can be used in an interactive environment 104. For example, an application 106 can be accessed by one or more users to generate one or more objects 108. Object 108 can correspond to a 3D object including features such as geometric representation, texture, shadow, color, etc. As described above, the object can be represented by a mesh or other representations such as NURBS, Bezier surfaces, subdivision surfaces, and / or the like. In at least one embodiment, object 108 is generated within native application 106 so that object 108 is viewed from one or more perspectives or points. For example, application 106 can include a coordinate system on which object 108 is generated. Thereafter, different views such as perspective, side view, top view, and / or other views can be associated with object 108 so that it is possible to interact with object 108 from various different angles. Object 108 may also be used within a larger representation, such as a representation showing interactions between object 108 and various other objects and / or a representation of the object within an environment that may include different lighting properties or other features.

[0031] The object 108 may be saved in a certain file format, and therefore, different types of data may be stored with the object 108. For example, different file formats may include different metadata, different rendering instructions, etc. In at least one embodiment, the object 108 may be loaded into the interactive environment 104 for further interaction and use. The exporter 110 may be used to format the object 108 and / or adjust one or more features of the object 108 to allow use in the interactive environment 104 and / or capture useful information for replication within the interactive environment 104. The importer 112 may then receive the object 108 (which may be modified by one or more operations of the exporter 110) and format the object 114 for use within the interactive environment 104.

[0032] In at least one embodiment, the original object 108 differs from the object 114 at least in some parts because one or more operations can be performed on the original object 108 to modify certain aspects of the object 114. For example, one or more transformations can be applied to the object 108 by one or both of the exporter 110 and the importer 112. The transformation can adjust the appearance or orientation of the object 108. For example, the transformation can be used to change the orientation of the object 108 in 3D space so that points, vertices, faces, etc. are arranged in different positions. Although the intended operation of each transformation is to place the object 108 within the scene, as an alternative, each content generation environment 102 applies the transformation to each point, normal, face, etc. of the mesh corresponding to the object 108. These types of transformations can be referred to as "deep transformations" because they are "baked into" or otherwise become part of the object 114. However, the specific depth transformation is unknown to the importer 112 and / or the interactive environment 104. Therefore, the object 108 may appear different from the replica object, which is simply because of how the different objects are arranged in space.

[0033] As described above, the depth transform is applied to the object at the point level for the corresponding mesh or other structure. When the object is added to the interactive environment 104, the transforms applied to the object may not be known by the importer 112 because they may be applied by the content generation environment 102 itself or one or more components of the content generation environment 102 (e.g., the exporter 110 or within the application 106). These transforms may correspond to one or more mathematical operations, in which rounding errors are completed at different locations, which may cause deformation of the object. These deformations may cause problems when trying to identify multiple copies or near-copy objects within a scene. For example, in an industrial environment, an object may be replicated dozens or hundreds of times, and the object has fasteners such as bolts, nuts, screws, nails, and / or the like. Each fastener in a set of fasteners may be a copy and / or a near-copy of another fastener (e.g., a 3 / 8 inch hexagonal bolt with a coarse thread type is essentially a copy of another 3 / 8 inch hexagonal bolt with a coarse thread type, regardless of the orientation of the bolt). However, due to the transformation, the object may not appear as a duplicate. In addition, traditional duplicate identification methods are not sufficient to identify these objects. For example, paired shape matching is not enough to overcome these problems because of the complexity of the algorithm used and the quadratic nature of paired comparisons. In scenes with hundreds or thousands of possible duplicates, such methods will require too much time and use too many computing resources. Some traditional hashing methods for duplicate identification are also inadequate because the transformation and its associated deformation modify and change the hash value of a single object, so that the duplicate is no longer identified using only the hash value. The systems and methods discussed herein solve these problems by hashing only the connectivity data, which does not change even through the deformations applied by various transformations. That is, various embodiments can still use hashing for the connectivity information of the mesh, as an example, as described herein, because the depth transformation modifies the point coordinates and / or direction attributes without modifying the connectivity information. Therefore, the connectivity and / or topology (e.g., vertices, edges, faces, etc.) of the mesh associated with each data object will not change. In contrast, the depth transformation changes the coordinates of the points associated with each vertex, but at the topological level, the object remains unchanged. Because each vertex maintains the same vertex connections as before, and because the connectivity of edges and faces also remains unchanged, the described systems and methods can use this data for hashing. By utilizing hashing on topological information that does not change, various embodiments significantly reduce the number of meshes compared to other approaches.

[0034] Various embodiments address issues caused by deep transforms, such as increasing the size of USD files with geometry of duplicate or near-duplicate objects. By replacing the geometry of duplicates and near-duplicates, the systems and methods described can reduce the amount of geometry data associated with USD files. As a result, less data needs to be retrieved from the driver, less data can be sent over the network, less data can be uploaded to a processor (such as a GPU), less data can occupy GPU memory, and / or less data can occupy ordinary system memory such as random access memory (RAM).

[0035] Figure 2 A representation 200 of an object 202 is shown in a first orientation 204 and a second orientation 206. For simplicity and clarity, the example object 202 is shown as a rectangle, but the system and method can be applied to any object with different shapes and more complex meshes or other representations. Coordinate system 208 represents an xyz coordinate system, wherein the different axes of the coordinate system 208 are arranged perpendicular to each other. A first point 210A is located at a vertex corresponding to a specific position (e.g., (0, 1, 0)), and a second point 210B is located at a vertex corresponding to another specific position (e.g., (0, 0, -1)). Additional points and faces can also be used to represent the object 202. For example, when it comes to a polygonal mesh that can be used to form the object 202, a mesh of face-vertex can be provided to describe the geometric connectivity of the object 202, such as listing the different vertices that form the face and / or providing the coordinates of the different vertices and the associated face. In addition, for simplicity, a vertex can be described by any point along the face or edge of the object 202 used in the systems and methods described herein. As described herein, although various embodiments may be discussed with respect to polygonal meshes, the described systems and methods may also be applied to different object representations.

[0036] In this example, object 202 has specific coordinates in a first orientation 204 that are shifted or otherwise changed when positioned in a second orientation 206. For example, rotating object 202 about the z-axis changes first point 210A to position (0+T, 1+T, 0) and also changes second point 210B to position (0+T, 0+T, -1), where T is a value shifted between first orientation 204 and second orientation 206 by a transformation applied. If the transformation applied is a depth transformation, as described above, object 202 can be provided to an interactive environment with different hash values ​​representing duplicate or near-duplicate objects. Thus, the interactive environment can store object 202 separately at different orientations, even though the geometry may be substantially consistent (e.g., outside a certain threshold amount), thereby consuming unnecessary resources. The systems and methods of the present disclosure may address this problem by using connectivity data for object 202 to identify duplicates and / or near duplicates, determining a coordinate system for object 202 , and then applying a transformation to object 202 to modify the position of the single stored copy of object 202 .

[0037] Although depth transforms change the coordinates of points (and normals), their application does not change the order in which the points are stored. In addition, depth transforms do not change the connectivity information of the mesh. For example, faceVertexCounts and faceVertexIndices remain essentially unchanged even after a depth transform is applied. Therefore, the systems and methods disclosed in this application can use this information to hash the connectivity data. Doing so can maintain the linearity of the duplicate detection algorithm.

[0038] Various embodiments of the present disclosure may be used to determine a linear transformation to map a mesh of a first object to a second object, that is, a first mesh may be mapped onto another mesh based at least in part on determining that the two meshes have the same (or substantially the same) connectivity data. For example, if the transformation applied to the mesh is known, but the depth transformation is not, then the problem may be defined as:

[0039]

[0040] Where T1 corresponds to the first transformation, M1 corresponds to the first grid, T2 corresponds to the second transformation, and M2 corresponds to the second grid.

[0041] Therefore, the second grid (M2) can be defined as:

[0042]

[0043] However, as described herein, when processing depth transforms, M, T1, and T2 are unknown. For example, the transforms may be applied by a native application used to generate an object, and may be applied to the points themselves, rather than being used as a general equation to operate on groups of points, vertices, faces, etc. The described systems and methods may address this issue by determining alternative transforms T′1 and T′2 such that:

[0044]

[0045] Mapping between M1 and M2 is allowed by the following operations:

[0046]

[0047] The mesh M' can represent the "canonical form" of the original mesh M, and can be determined using a variety of different strategies, as will be described herein. Each of these different strategies takes advantage of the fact that deep transformations do not change the order given by the points in the mesh. Thus, the described systems and methods can be used to identify a linearly independent set of vectors for a given object, map the vector set to a suspected duplicate (using the same points), and then determine whether the object is a duplicate (within a certain threshold). The identification of duplicates and the associated transformations allow a single copy to be retained and modified throughout an interactive environment.

[0048] In at least one embodiment, a mesh M' is defined using four (4) linearly independent points of M1, where the first point is mapped to the origin and the other three points are mapped to three unit vectors of the three principal axes (e.g., x, y, and z). Thus, T'1 can be defined using these points / vectors and its inverse. Then, in the case where the mesh is a replica and / or a near replica, a similar approach to M2 is used to compute the transformation that maps M1 to M2.

[0049] Figure 3AA representation 300 is shown in which a series of unit vectors are used to establish a coordinate system to map a first mesh to a second mesh. In this example, an object 202 is positioned according to a coordinate system 208. As described above, for clarity, the object 202 is represented as a rectangle, and the object 202 can be any combination of shapes, etc., and can be represented as a mesh including polygons (e.g., triangles, etc.) that form the faces of the object 202. In at least one embodiment, the object 202 can be represented by a vertex list 302 and / or some other text representation that provides information about the location of one or more features of the object 202, such as points, vertices, faces, etc. In this example, the vertex list 302 includes vertex locations represented by the xyz coordinate system 208. For example, the vertex 304A represented by v0 is located at the point (0, 0, 0). Additional vertices including v1, v2, v4, v5, and v7 are shown on the object 202. Each of these vertices 304B-304F can be associated with a position in 3D space based at least in part on vertex list 302. Furthermore, the ordering of these vertices 304A-304F can remain constant for each object provided to the interactive environment, such that v0 always corresponds to a particular vertex, regardless of its position in 3D space.

[0050] The systems and methods of the present disclosure can be used to identify linearly independent vectors extending from a selected origin in order to form a transformation to map between different meshes to identify replicas and / or approximate replicas. Four points, in this example vertices, can be used to identify linearly independent vectors. These points can be randomly selected from the vertex list 302, or selected at least in part based on one or more methods, as will be described herein. In addition, although vertices are used in this example, the systems and methods can be extended to any points, such as points along a face, points along an edge, and / or combinations thereof.

[0051] In this example, the order of points (e.g., vertices) provided in vertex list 302 can be traversed to generate different vectors (e.g., directions), determine the linear independence of these vectors, and generate a set of vectors (e.g., tuples) that can be used to convert the mesh representation of the object to a canonical form. In this example, the first vertex 304A, denoted as v0, is selected as the origin. The origin will be used for each of the vectors generated for subsequent points. Traversing vertex list 302, the next point provided is the second vertex 304B, denoted as v1. A first vector 306A is generated from v0 to v1.

[0052] Next, a second vertex 304C, denoted as v2, is selected from the vertex list 302, and a second vector 306B is generated from v0 to v2. As shown, vectors 306A and 306B are linearly independent of each other, even if they are in a common plane, because the first vector 306A can be said to be only along the x-axis, while the second vector 306B is tilted upward along the y-axis. Continue to traverse the vertex list 302, select the third vertex 304D, denoted as v3, and generate a third vector 306C from v0 to v3. However, as described herein, vectors must be linearly independent. For example, the start and end positions of the vector set can be evaluated to ensure that all vectors are not arranged in a common plane. When evaluating the third vector 306C, it can be seen that the third vector 306C is not linearly independent because it is in a common plane with both the first vector 306A and the second vector 306B. Therefore, the third vector 306C is discarded, and the process can continue to select the next point in the vertex list 302, which is the fourth vertex 304E, denoted as v4.

[0053] Generating a fourth vector 306D from v0 to v4 provides a vector that is outside the plane of vectors 306A and 306B and therefore can be considered linearly independent. As the tuple is generated, a vector representation 308 of object 202 is shown, which can be used to convert the mesh representation to a canonical form to identify duplicates and / or approximate duplicates.

[0054] Figure 3B is 320, when Figure 3A When the first direction 204 and the second direction 206 are compared, such as the difference between the first direction 204 and the second direction 206, the object 202 is transformed. Therefore, as shown in the vertex list 302, the various vertices may be in different positions. However, the order of the vertex list 302 is maintained even if the particular vertices are in different positions. Therefore, by drawing vectors from the same selected point, the vector representation 308 can be mapped to Figure 3B 304A) to the selected points (vertices 304B, 304C, 304D). If the vectors are aligned, it can be determined that the object is a duplicate and / or a near duplicate. Thus, as described herein, a transformation of the canonical grid can be determined for the object 202, and only a single copy of the object can be stored and then transformed according to the resulting transformation in order to place the object 202 within the environment multiple times.

[0055] Selecting the first four points for the object may span only one linear subspace. Therefore, the vectors from these points will not be linearly independent, and more points will need to be selected. In addition, the points may result in a set of vectors that, while linearly independent, will result in a poorer transformation when compared to more linearly independent vectors. Therefore, the systems and methods of the present disclosure may combine techniques for point selection with a threshold or reference standard for vector linear independence.

[0056] In at least one embodiment, the vector representation 308 generated from the vectors 306A, 306B, 306D may include vectors that are not perpendicular to each other, and thus may result in skewed transformations. Therefore, it may be desirable to apply one or more methods to perform point selection (as described above, points are not necessarily vertices) in order to obtain sufficiently linearly independent vectors while maintaining numerical stability for subsequent transformations. For example, a highly mosaic sphere may include a set of the first four points, all of which are in the same region, meaning that these points may be barely linearly independent. In this case, it may be beneficial to set a threshold for linear independence, which will cause the system to continue searching for different points. For a mosaic sphere, many points may fall within a region that does not have a threshold amount of linear independence. In addition, even if these points are able to exceed the threshold, the combination of points may only be barely considered linearly independent, and therefore may be worse than other sets that can be more easily identified with improved results.

[0057] One example technique includes pseudo-random point selection. This technique can exploit the idea that the first four points may not be necessary to match two different meshes as long as the same four points are selected between the meshes. Therefore, a pseudo-random shuffle of the points can be applied to each mesh using the same seed, and then the first four sufficiently linearly independent points can be selected from the new order of the points. This shuffle can provide a selection of points that are well distributed over the mesh, and therefore most likely produce a more stable transformation than a transformation that selects only the first four points. In addition, this approach can also support non-uniform scaling and shearing.

[0058] In at least one embodiment, a pseudo-maximum selection can be used to identify points. With this technique, a set of points is selected using a heuristic method. Starting from a reference point such as a first point or centroid, the technique includes a first pass over the set of points to select the longest difference vector from the reference point. Then, a second pass can select the vector that is most perpendicular to the first vector. Then, a third pass can select the vector that generates the maximum determinant. This technique can provide some benefits, such as no longer relying on randomization plus some thresholds. Alternatively, various embodiments can use the described techniques to optimize the selected set of points. For example, although such a method can be used in which all possible vertex quads are evaluated and then the quad that provides the most linearly independent set of vectors is selected, this method may not be practical due to the time required to enumerate all quads. Alternatively, various embodiments can select different first vertices, second vertices, and third vertices, assuming that these points will be linear enough.

[0059] However, as described herein, due to the initial application of the depth transform, there may be rounding errors within the points describing the object. Thus, when this technique is applied to a symmetrical object such as a cube, there may be several vectors that would establish a maximum, but due to rounding errors, one of the vectors may be "larger". Thus, the selection is essentially random. Embodiments may adjust for such rounding errors by weighting or applying a preference to the vector that is found first, and only selecting a new vector if it exceeds some relative threshold.

[0060] In various embodiments, the vector representation 308 can be configured as a rigid transformation, where each vector is perpendicular to each other and the length of the vector is set to 1. A rigid transformation can provide less skewing and / or stretching when modifying the underlying object representation. Therefore, when selecting points, faces, and / or the like to generate vectors, specific areas can be set to be perpendicular to each other to drive the generation of a rigid transformation.

[0061] In some embodiments, the largest vector portion may not support non-uniform scaling and shearing because the change in metric prevents the same vector from being selected. However, this may not be a problem in some industries (such as manufacturing) because essentially all deep transformations that occur in manufacturing environments are rigid transformations.

[0062] Figure 4An example process 400 for identifying and removing duplicate objects from an interactive environment is shown. It should be understood that, unless otherwise stated, additional, fewer, or alternative operations may be performed in a similar or alternative order, or at least partially in parallel, for this process and other processes described herein within the scope of various embodiments. In this example, multiple objects for use within an interactive environment are received (402). The objects may correspond to 3D objects that may be located in a 3D space. For example, the objects may be represented by meshes, NURBS, Bezier patches, subdivision surfaces, points, colors, textures, etc. In at least one embodiment, for example, each of the multiple objects may be selected (404) in the order received, by a command, etc., and a hash value of the selected object may be calculated (406) based on the object topology. As previously described, various techniques based on hash values ​​at point locations may result in errors due to depth transformations. The systems and methods of the present disclosure may perform hashing based on topological information to reduce the possibility of such errors. The hashing process may provide an integer value based on a given input, and therefore meshes with the same hash should be placed in the same bucket to indicate that associated meshes (as a non-limiting example) are likely to be the same.

[0063] In at least one embodiment, multiple objects are bucketed according to their respective hash values. Therefore, when a selected object is hashed, the object can be bucketed (408) (e.g., sorted) based at least on its hash value 406. Sorting objects or describing an operation as "bucketing" or the like can include storing information associated with an object at a given location or otherwise tracking the value of an object. In operation, since the hash value of the topological information is used, it is very likely that all grids that are ultimately located in the same bucket have the same topology. Applying this assumption can be important for runtime considerations. However, it may still be necessary to check whether another object that is classified into the same bucket is indeed equal to the first object associated with the bucket. For example, two different topologies may result in the same hash value. Therefore, a bucket can include multiple hash values ​​associated with multiple object representations.

[0064] In at least one embodiment, each bucket (e.g., bin) contains a list of meshes that have been determined to not be copies of each other, where one or more of the meshes may be referred to as prototype meshes. At some point during the comparison, such as at the beginning or early in the evaluation process, the list may be empty. For a new mesh, a hash value is first calculated, and then the mesh is inserted into the corresponding bucket. Within the bucket, comparisons may be made by iterating over the list of prototype meshes. If the new mesh is a copy of the prototype mesh, the new mesh, which is a copy, is deleted from the scene and replaced with a reference, which may then be modified by one or more shallow transforms to position the prototype in the appropriate location. Otherwise, the new mesh is added to the prototype list in the bucket.

[0065] Various embodiments can be used to verify replicas between grids using the systems and methods described herein. In at least one embodiment, a topological hashing process is applied to each object (e.g., once). Thereafter, the object is placed in an appropriate bucket and is not checked against other grids with different hash values. The object may or may not be the first object in the bucket. If so, the object is retained as the representative grid of the bucket. However, if another object already exists in the bucket, or another object with a suitable hash is received, the newly arrived grid can be compared with the grids in the bucket.

[0066] Because common objects should have the same hash value, objects with the same hash value will be placed in the same bucket. Therefore, when an object is selected to be hashed and bucketed, it is determined whether the object (e.g., a mesh or representation of the object) is already stored (410) in the bucket. If not, the object can be added to the bucket as a new prototype mesh (412), and it can be determined whether there are additional objects from the multiple objects (414). If so, the process can select a new object and repeat. If not, the process ends (416), which can include rendering a scene within the interactive environment or providing a notification to the user, among other options.

[0067] If there is an additional object (e.g., a prototype mesh) in the bucket, the canonical form of the other object is mapped to the canonical form of the object (418). An alignment between the mappings can be determined (420). If there is a misalignment or an alignment that exceeds a threshold, the object can be added to the bucket as a new prototype mesh (412). If the alignment is within the threshold, it can be determined that the object is a duplicate of the other object (422), and the object can be deleted (424). For example, one or more deduplication actions can be applied to only include the other object as a reference or reference (e.g., a prototype mesh) in the bucket.

[0068] Various embodiments of the present disclosure may be further described by the following pseudo code for evaluation of a grid and / or other representation:

[0069] if topologies are not identical,return false(likewise with

[0070] other data,such as uv coordinates that are not affected by the

[0071] canonicalization

[0072] for meshes M1 and M2 compute canonical forms M1'of M1

[0073] and M2'of M2

[0074] if sequence of all points of M1'and M2'differ more than

[0075] tolerance threshold,return false

[0076] if sequence of all Normals of M1'and M2'differ more than

[0077] tolerance threshold,return false(likewise with other directional

[0078] data such as velocity or acceleration)

[0079] (If the topology is different, an error is returned (the same is true for other data

[0080] This, for example, does not affect UV coordinates.

[0081] For meshes M1 and M2, calculate the canonical form M1' of M1 and the canonical form M2' of M2.

[0082] Model M2'

[0083] If the sequences of all points of M1' and M2' differ by more than the tolerance threshold, then return

[0084] mistake

[0085] If the sequence of all normals of M1' and M2' differs by more than the tolerance threshold, then return

[0086] The return value is incorrect (the same is true for other directional data such as speed or acceleration)

[0087] Figure 5A An example process 500 for determining a transformation that puts a mesh into a canonical form is shown. In this example, a sequence of points corresponding to an object is determined (502). The sequence can be associated with connectivity data for the object. A reference point (504) can be selected from the sequence of points. The reference point can be the first point in the sequence, the center of the object, a pseudo-randomly selected point, or some combination thereof. In at least one embodiment, three additional points can be selected from the sequence of points (506). The three additional points can be three points after the reference point in the sequence, randomly selected points, or any other reasonably selected points.

[0088] In at least one embodiment, vectors extending from the reference point to each of the three other selected points are determined (508). For example, a first vector may extend from the reference point to a first additional point, a second vector may extend from the reference point to a second additional point, and a third vector may extend from the reference point to a third additional point. The vectors may be analyzed to determine their linear independence (510), and whether the vectors are linearly independent by a threshold amount (512). If so, then the vectors may be used to determine a transformation to be applied to the object (514). If not, a new reference or reference may be selected to restart the process.

[0089] The systems and methods of the present disclosure may be directed to a deterministic process for receiving a first mesh and a second mesh, the first mesh defining a sequence of its points, the process deriving a first ordered tuple of four points from a first sequence of points derived from the first mesh, the first ordered tuple defining a first linear reversible transformation, the first transformation transforming the first mesh into a first normalized form of the first mesh. Similarly, the process may also include deriving a second tuple of four points from the second mesh, a second transformation, and a second normalized form, and determining that the first mesh and the second mesh are considered duplicates as long as the first normalized form and the second normalized form are sufficiently similar.

[0090] Figure 5B An example process 520 for determining whether a first canonical form of a first object is sufficiently similar to a second canonical form of a second object is shown. In this example, a first mesh is received, and a second mesh is received (522). The first mesh may correspond to a representation of the first object, and the second mesh may correspond to a representation of the second object. The first object and the second object may be copies and / or approximate copies, and various embodiments of the present disclosure may be used to make such a determination. For example, a sequence of points may be defined for the first mesh (524). The sequence of points may correspond to different mesh locations, such as, but not limited to, vertices, faces, etc. Using the first sequence of points, a first tuple may be generated for the first mesh (526). The first tuple may be a first tuple corresponding to four points in the sequence of points. For example, the first tuple may include information associated with a set of vectors extending between points in the set of points, such as three vectors each extending from a common origin. In at least one embodiment, the first tuple may be used to convert the first mesh into a canonical form 528.

[0091] A similar process may be used to evaluate a second mesh and prepare the second mesh for comparison. For example, a second sequence of points may be defined for the second mesh (530), and a second tuple may be generated for the second mesh (532). As described, the second tuple may correspond to four points in the sequence of points, and in at least one embodiment, may correspond to information associated with a vector extending from a common origin. Various embodiments may select the same points from the sequence of points used to generate the first tuple. The second tuple may then be used to convert the second mesh into a second canonical form (534). Thereafter, the first canonical form may be compared to the second canonical form (536). The comparison may include evaluating the positions of various points (e.g., positions of vertices, faces, etc.) of the different canonical forms.

[0092] In at least one embodiment, a determination may be made to determine whether the first canonical form and the second canonical form are sufficiently similar (538). For example, an exact copy may not be required and a threshold amount of similarity may be defined, such as vertices having positions within a percentage difference of each other and / or various other metrics. If the canonical forms are sufficiently similar, then it may be determined that the first mesh and the second mesh are copies (540). If not, then it may be determined that the first mesh and the second mesh are not copies (542).

[0093] Various embodiments may also be directed to finding corresponding tuples by using a sufficiently linearly independent first tuple. Different techniques may be used for linear independence, such as pseudo-random shuffling, determining the most independent tuple (by enumeration), heuristic greedy selection of the most promising next point, and specific heuristics using a maximization strategy of some measure related to linear independence (e.g., 1D maximum length, 2D dot product, 3D determinant, etc.). Embodiments may also be directed to using topological hashing to speed up one or more processes.

[0094] As discussed, various aspects of the various methods presented herein can be sufficiently lightweight to be executed in real time on a device such as a client device (e.g., a personal computer or a gaming console). Such processing can be performed on or for content generated on a client device or content received by the client device from an external source (e.g., streaming data or other content received over at least one network). In some instances, the processing and / or determination of the content can be performed by one of these other devices, systems, or entities and then provided to the client device (or other such recipient) for rendering or another such use.

[0095] As an example, Figure 6An example network configuration 600 is shown that can be used to provide, generate, modify, encode, process and / or transmit image data or other such content. In at least one embodiment, a client device 602 can generate or receive data for a session using components of a control application 604 on the client device 602 and data stored locally on the client device. In at least one embodiment, a content application 624 executing on a server 620 (e.g., a cloud server or an edge server) can initiate a session associated with at least one client device 602, such as can utilize a session manager and user data stored in a user database 636, and can cause a content manager 626 to determine content from an asset repository 634, such as one or more digital assets (e.g., object representations), etc. The content manager 626 can work with an image composition module 628 to generate or compose new objects, digital assets, or other such content to be provided for presentation via the client device 602. In at least one embodiment, the image composition module 628 can use one or more neural networks or machine learning models, which can be trained or updated using a training module 632 or a system on or in communication with the server 620. This may include training and / or using a diffusion model 630 to generate content tiles that may be used by an image synthesis module 628 to, for example, apply a non-repeating texture to an area of ​​an environment for which image or video data is presented via a client device 602. At least a portion of the generated content may be transmitted to the client device 602 by downloading, streaming, or other such transmission channel using a suitable transmission manager 622. An encoder may be used to encode and / or compress at least some of the data prior to transmission to the client device 602. In at least one embodiment, a client device 602 receiving such content may provide the content to a corresponding control application 604, which may also or alternatively include a graphical user interface (GUI) 610, a content manager 612, and an image synthesis or diffusion module 614 for providing, synthesizing, modifying, or using content for presentation on or via the client device 602 (or other purposes). The decoder can also be used to decode data received over the network 640 for presentation via the client device 602, such as images or video content presented via a display 606, and audio (e.g., sounds, music, etc.) presented via at least one audio playback device 608 (e.g., speakers or headphones).In at least one embodiment, at least a portion of the content may already be stored on the client device 602, rendered on the client device 602, or accessible by the client device 602, so that the at least a portion of the content does not need to be transmitted over the network 640, for example, the content may have been previously downloaded or stored locally on a hard drive or optical disk. In at least one embodiment, a transmission mechanism such as data streaming can be used to transmit the content from the server 620 or the user database 636 to the client device 602. In at least one embodiment, at least a portion of the content may be obtained, enhanced and / or streamed from another source (e.g., a third-party service 660 or other client device 650), which may also include a content application 662 for generating, enhancing or providing content. In at least one embodiment, multiple computing devices or multiple processors within one or more computing devices may be used to perform part of the function, and one or more computing devices may include a combination of CPU and GPU, for example.

[0096] In this example, the client devices may include any suitable computing device, such as a desktop computer, a laptop computer, a set-top box, a streaming device, a game console, a smart phone, a tablet computer, a VR headset, an AR glasses, a wearable computer, or a smart TV. Each client device may submit a request through 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, the requests may be submitted to an address associated with a cloud provider, and the cloud provider may operate or control one or more electronic resources in the cloud provider environment, such as a data center or a server cluster. In at least one embodiment, the request may be received or processed by at least one edge server, which is located at the edge of the network and outside of at least one security layer associated with the cloud provider environment. In this way, latency can be reduced by enabling client devices to interact with closer servers, while also improving the security of resources in the cloud provider environment.

[0097] In at least one embodiment, such a system can be used to perform graphics rendering operations. In other embodiments, such a system can be used for other purposes, such as for providing image or video content to test or verify autonomous machine applications, or for performing deep learning operations. In at least one embodiment, such a system can be implemented using an edge device, or can be combined with one or more virtual machines (VMs). In at least one embodiment, such a system can be implemented at least in part in a data center, or at least in part using cloud computing resources.

[0098] Reasoning and training logic

[0099] Fig. 7A Inference and / or training logic 715 is shown for performing reasoning and / or training operations associated with one or more embodiments. Fig. 7A and / or Figure 7B Details regarding the inference and / or training logic 715 are provided.

[0100] In at least one embodiment, the 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 for configuring neurons or layers of a neural network trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, the 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, where weights and / or other parameter information is loaded to configure logic, including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, the code (such as graph code) loads weights or other parameter information into a processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, the code and / or data storage 701 stores input / output data during training and / or inference using aspects of one or more embodiments and / or weight parameters during forward propagation of each layer of a neural network trained or used in conjunction with one or more embodiments. In at least one embodiment, any portion of code and / or data storage 701 may be included within other on-chip or off-chip data storage, including a processor's L1, L2, or L3 cache or system memory.

[0101] In at least one embodiment, any portion of 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, code and / or data storage 701 may be 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 code and / or data storage 701 is internal or external to a processor, for example, or consists of DRAM, SRAM, flash memory, or some other storage type, may depend on the available storage space on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in inference and / or training of the neural network, or some combination of these factors.

[0102] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 705 for storing reverse 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 aspects of one or more embodiments. In at least one embodiment, during training and / or inference using aspects of one or more embodiments, the 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 conjunction with one or more embodiments during back propagation of input / output data and / or weight parameters. In at least one embodiment, the 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 weights and / or other parameter information is loaded to configure logic including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, code (such as graph code) loads weights or other parameter information into a processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of 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. In at least one embodiment, any portion of 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, 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 of whether code and / or data storage 705 is internal or external to the processor, for example, whether it is composed of DRAM, SRAM, flash memory, or some other storage type, 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.

[0103] 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 the same storage structure 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.

[0104] 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 based at least in part on or as directed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from a layer or neuron within a neural network) stored in activation storage 720, which is a function 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, activations are performed in response to executing instructions or other code, linear algebra and / or matrix-based mathematics performed by ALU 710 to generate activations stored in activation storage 720, where weight values ​​stored in code and / or data storage 705 and / or in 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, any or all of which may be stored in code and / or data storage 705 or code and / or data storage 701 or other on-chip or off-chip storage.

[0105] 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 outside a processor or other hardware logic device or circuit that uses them (e.g., a coprocessor). In at least one embodiment, one or more ALUs 710 may be included within an execution unit of a processor, or otherwise included in a group of ALUs accessible by an execution unit of a processor, which may be within the same processor or distributed between 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 circuit, while in another embodiment, they may be in different processors or other hardware logic devices or circuits or some combination of the same and different processors or other hardware logic devices or circuits. In at least one embodiment, any portion of activation storage 720 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Additionally, inference and / or training code may be stored with other code accessible to a 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.

[0106] In at least one embodiment, activation storage 720 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, activation storage 720 may be completely or partially internal or external to one or more processors or other logic circuits. In at least one embodiment, activation storage 720 may be selected to be internal or external to a processor, for example, or include DRAM, SRAM, flash memory, or other storage types, depending on the storage available on-chip or off-chip, the latency requirements for performing training and / or inference functions, the batch size of data used in inferencing and / or training neural networks, or some combination of these factors. In at least one embodiment, Fig. 7A The inference and / or training logic 715 shown in FIG. 7 may be used in conjunction with an application specific integrated circuit (“ASIC”), such as the ASIC from Google. Processing unit from Graphcore TM Inference Processing Unit (IPU) from Intel (e.g., "LakeCrest") processor. In at least one embodiment, Fig. 7A The illustrated inference and / or training logic 715 may be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as a field programmable gate array (“FPGA”).

[0107] Figure 7B Inference and / or training logic 715 is shown in accordance with at least one or more embodiments. In at least one embodiment, the reasoning and / or training logic 715 may include, but is not limited to, hardware logic in which computing 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 in FIG. 7 may be used in conjunction with an application specific integrated circuit (ASIC), such as the ASIC from Google. Processing unit from Graphcore TM Inference Processing Unit (IPU) from Intel (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7BThe inference and / or training logic 715 shown in 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 in , each of code and / or data storage 701 and code and / or data storage 705 is associated with a dedicated computing resource (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) solely on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of performing the functions are stored in activation storage 720.

[0108] In at least one embodiment, each of the code and / or data stores 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activations from one "storage / compute pair 701 / 702" of the code and / or data store 701 and computing hardware 702 are provided as inputs to the next "storage / compute pair 705 / 706" of the code and / or data store 705 and computing hardware 706, so as to reflect the conceptual organization of the neural network. In at least one embodiment, each storage / compute pair 701 / 702 and 705 / 706 can correspond to more than one neural network layer. In at least one embodiment, additional storage / compute pairs (not shown) can be included in the inference and / or training logic 715 after or in parallel with the storage / compute pairs 701 / 702 and 705 / 706.

[0109] Data Center

[0110] Figure 8 An example data center 800 is shown in which at least one embodiment may be used. 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.

[0111] In at least one embodiment, Figure 8As shown, the data center infrastructure layer 810 may include a resource coordinator 812, grouped computing resources 814, and node computing resources ("node CRs") 816(1)-816(N), where "N" represents any positive integer. In at least one embodiment, the node CRs 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 memories), 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 of the node CRs 816(1)-816(N) may be a server having one or more of the above computing resources.

[0112] In at least one embodiment, the grouped computing resources 814 may include a separate grouping (not shown) of node CRs housed in one or more racks, or many racks (also not shown) housed in data centers at various geographic locations. The separate grouping of node CRs within the grouped computing resources 814 may include computing, networks, memory, or storage resources that can be configured or allocated to support groupings of one or more workloads. In at least one embodiment, several node CRs including a CPU or processor may be grouped in one or more racks to provide computing resources to support one or more workloads. In at least one embodiment, one or more racks may also include any number of power modules, cooling modules, and network switches in any combination.

[0113] In at least one embodiment, resource coordinator 812 may configure or otherwise control one or more node CRs 816(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 812 may include hardware, software, or some combination thereof.

[0114] In at least one embodiment, Figure 8As shown, the 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, the framework layer 820 may include a framework that supports software 832 of the software layer 830 and / or one or more applications 842 of the application layer 840. In at least one embodiment, the software 832 or the application 842 may include a web-based service software or application, such as a service or application provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 820 may be, but is not limited to, a free and open source software network application framework, such as Apache SparkTM (hereinafter referred to as "Spark") that can utilize the distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, the job scheduler 832 may include a Spark driver to facilitate scheduling of workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be able to configure different layers, such as the software layer 830 and the framework layer 820 including Spark and a distributed file system 828 for supporting large-scale data processing. In at least one embodiment, the resource manager 826 can manage cluster or group computing resources mapped to or allocated to support the distributed file system 828 and the job scheduler 822. In at least one embodiment, the cluster or group computing resources can include group computing resources 814 on the data center infrastructure layer 810. In at least one embodiment, the resource manager 826 can coordinate with the resource coordinator 812 to manage these mapped or allocated computing resources.

[0115] 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 node CRs 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The 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.

[0116] In at least one embodiment, one or more applications 842 included in the application layer 840 may include one or more types of applications used by at least a portion of the node CRs 816(1)-816(N), the 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.

[0117] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can implement any number and type of self-modification actions based on any number and type of data acquired in any technically feasible manner. In at least one embodiment, the self-modification actions can relieve a data center operator of the data center 800 from making potentially bad configuration decisions and can avoid underutilized and / or poorly performing portions of the data center.

[0118] In at least one embodiment, the data center 800 may include tools, services, software, or other resources to train one or more machine learning models or 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 may be trained by calculating weight parameters according to a neural network architecture using the software and computing resources described above with respect to the data center 800. In at least one embodiment, by using weight parameters calculated by one or more training techniques described herein, information may be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to the data center 800.

[0119] In at least one embodiment, the data center can use a CPU, an application-specific integrated circuit (ASIC), a GPU, an FPGA, or other hardware to use the above resources to perform training and / or reasoning. In addition, one or more of the above software and / or hardware resources can be configured as a service to allow users to train or perform information reasoning, such as image recognition, speech recognition, or other artificial intelligence services.

[0120] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Details about the reasoning and / or training logic 715 are provided in conjunction with the following contents. Fig. 7A and / or Figure 7BIn at least one embodiment, the reasoning and / or training logic 715 may be provided in the system Figure 8 for use in a system for performing inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0121] Such components can be used for replica identification.

[0122] Computer Systems

[0123] Fig. 9 900, which may be a system of interconnected devices and components, a system on a chip (SOC), or some combination thereof formed with a processor that may include an execution unit to execute instructions. In at least one embodiment, in accordance with the present disclosure, such as the embodiments described herein, the computer system 900 may include, but is not limited to, components such as a processor 902, whose execution unit includes logic to execute algorithms for processing data. In at least one embodiment, the computer system 900 may include a processor such as a processor available from Intel Corporation of Santa Clara, California. Processor family, XeonTM, XScaleTM and / or StrongARMTM, Core TM or Nervana TM microprocessor, although other systems (including PCs with other microprocessors, engineering workstations, set-top boxes, etc.) 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, Wash., although other operating systems (e.g., UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0124] Embodiments may be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol (Internet Protocol) 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, 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.

[0125] 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 reasoning 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 multi-processor system. In at least one embodiment, the processor 902 may include, but is not limited to, a complex instruction set computing ("CISC") microprocessor, a reduced instruction set computing ("RISC") microprocessor, a very long instruction word ("VLIW") computing microprocessor, a processor that implements an 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 may transmit data signals between the processor 902 and other components in the computer system 900.

[0126] 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. Other embodiments may also include a combination of internal and external caches, depending on the particular implementation and needs. 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.

[0127] In at least one embodiment, one or more execution units 908, including but not limited to logic to perform integer and floating point operations, are also located in the processor 902. In at least one embodiment, the processor 902 may also include a microcode ("ucode") read-only memory ("ROM") for storing microcode for certain macroinstructions. In at least one embodiment, the one or more execution units 908 may include logic for processing a packed instruction set 909. In at least one embodiment, by including the packed instruction set 909 in the instruction set of a general purpose processor, and the associated circuitry to execute the instructions, operations used by many multimedia applications may be performed using packed data in the processor 902. In one or more embodiments, many multimedia applications may be executed faster and more efficiently by using the full width of the processor's data bus to perform operations on packed data, which may not require the transfer of smaller units of data on the processor's data bus to perform one or more operations one data element at a time.

[0128] In at least one embodiment, one or more execution units 908 may also be used in microcontrollers, embedded processors, graphics devices, DSPs, and other types of logic circuits. In at least one embodiment, 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 may be executed by processor 902.

[0129] In at least one embodiment, the system logic chip can be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip can include, but is not limited to, a memory controller hub ("MCH") 916, and the processor 902 can communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 can provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage and for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 can 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 can provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 can be coupled to the memory 920 via a high-bandwidth memory path 918, and the graphics / video card 912 can be coupled to the MCH 916 via an Accelerated Graphics Port ("AGP") interconnect 914.

[0130] In at least one embodiment, the computer system 900 may use a system I / O 922, which is a proprietary hub interface bus to couple the MCH 916 to an I / O controller hub ("ICH") 930. In at least one embodiment, the ICH 930 may provide direct connections to certain I / O devices through 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 used to connect peripheral devices to the memory 920, chipset, and processor 902. Examples may include, but are not limited to, an audio controller 929, a firmware hub ("FlashBIOS") 928, a wireless transceiver 926, a data store 924, a traditional I / O controller 923 including a user input and keyboard interface, a serial expansion port 927 (e.g., a universal serial bus (USB) port), and a network controller 934. The data store 924 may include a hard drive, a floppy drive, a CD-ROM device, a flash memory device, or other mass storage device.

[0131] In at least one embodiment, Fig. 9 A system comprising interconnected hardware devices or "chips" is shown, while in other embodiments, Fig. 9An exemplary system on chip (SoC) may be shown. In at least one embodiment, the devices 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 computer system 900 are interconnected using a compute express link (CXL) interconnect.

[0132] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations related to one or more embodiments. Details about the reasoning and / or training logic 715 are provided in conjunction with the following contents. Fig. 7A and / or Figure 7B In at least one embodiment, the inference and / or training logic 715 may be Fig. 9 for use in a system for performing inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0133] Such components can be used for replica identification.

[0134] Fig.10 1 is a block diagram illustrating an electronic device 1000 for utilizing 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 notebook computer, a tower server, a rack server, a blade server, a laptop computer, a desktop computer, a tablet computer, a mobile device, a phone, an embedded computer, or any other suitable electronic device.

[0135] In at least one embodiment, the electronic system 1000 may include, but is not limited to, a processor 1010 communicatively coupled to any suitable number or kind of components, peripherals, modules, or devices. In at least one embodiment, the processor 1010 is coupled using a bus or interface, such as a Ic bus, a system management bus ("SMBus"), a low pin count (LPC) bus, a serial peripheral interface ("SPI"), a high-definition audio ("HDA") bus, a serial advanced technology attachment ("SATA") bus, a universal serial bus ("USB") (versions 1, 2, 3), or a universal asynchronous receiver / transmitter ("UART") bus. In at least one embodiment, Fig.10 A system is shown that includes interconnected hardware devices or "chips", while in other embodiments, Fig.10 An exemplary system on chip (SoC) may be shown. In at least one embodiment, Fig.10 The devices shown in can be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, Fig.10 One or more components of the system are interconnected using Compute Express Link (CXL) interconnect lines.

[0136] In at least one embodiment, Fig.10 It may include a display 1024, a touch screen 1025, a touch pad 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 memory (“BIOS, FWFlash”) 1022, a DSP 1060, a drive 1020 (e.g., a solid state disk (“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 with, for example, the LPDDR3 standard. These components may each be implemented in any suitable manner.

[0137] In at least one embodiment, other components may be communicatively coupled to the processor 1010 through the components described above. In at least one embodiment, the accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to the sensor hub 1040. In at least one embodiment, the thermal sensor 1039, fan 1037, keyboard 1036, and touchpad 1030 may be communicatively coupled to the EC 1035. In at least one embodiment, the speaker 1063, earphone 1064, and microphone (“mic”) 1065 may be communicatively coupled to the audio unit (“audio codec and class D amplifier”) 1062, which in turn may be communicatively coupled to the DSP 1060. In at least one embodiment, the audio unit 1062 may include, for example, but not limited to, an audio encoder / decoder (“codec”) and a class D amplifier. In at least one embodiment, the SIM card (“SIM”) 1057 may be communicatively coupled to the WWAN unit 1056. In at least one embodiment, components such as the WLAN unit 1050 and the Bluetooth unit 1052 and the WWAN unit 1056 may be implemented as a next generation form factor (NGFF).

[0138] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Details about the reasoning and / or training logic 715 are provided in conjunction with the following contents. Fig. 7A and / or Figure 7B In at least one embodiment, the inference and / or training logic 715 may be Fig.10Systems for performing inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0139] Such components can be used for replica identification.

[0140] Fig.11 1100 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 can be a single-processor desktop system, a multi-processor workstation system, or a server system with 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-chip (SoC) integrated circuit for use in a mobile, handheld, or embedded device.

[0141] In at least one embodiment, the system 1100 may include or be incorporated into a server-based gaming platform, including a gaming console, a mobile gaming console, a handheld gaming console, or an online gaming console for gaming and media consoles. In at least one embodiment, the processing system 1100 is a mobile phone, a smart phone, a tablet computing device, or a mobile Internet device. In at least one embodiment, the system 1100 may also include a wearable device coupled to or integrated in a wearable device, such as a smart watch wearable device, a smart glasses device, an augmented reality device, or a virtual reality device. In at least one embodiment, the 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.

[0142] In at least one embodiment, one or more processors 1102 each include one or more processor cores 1107 to process instructions that, when executed, perform operations for 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 group 1109. In at least one embodiment, the instruction group 1109 can facilitate complex instruction set computing (CISC), reduced instruction set computing (RISC), or calculate by very long instruction words (VLIW). In at least one embodiment, one or more processor cores 1107 can each process different instruction groups 1109, which can include instructions that help emulate other instruction groups. In at least one embodiment, one or more processor cores 1107 can also include other processing devices, such as digital signal processors (DSPs).

[0143] In at least one embodiment, one or more processors 1102 include cache memory 1104. In at least one embodiment, one or more processors 1102 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory is shared between various components of one or more processors 1102. In at least one embodiment, one or more processors 1102 also use an external cache (e.g., a level 3 (L3) cache or a last level cache (LLC)) (not shown), which may be shared between one or more processor cores 1107 using known cache coherence techniques. In at least one embodiment, one or more processors 1102 additionally include a register file 1106, and the processor may include different types of registers (e.g., integer registers, floating point registers, status registers, and instruction pointer registers) for storing different types of data. In at least one embodiment, the register file 1106 may include general registers or other registers.

[0144] 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 one or more processors 1102 and other components in the system 1100. In at least one embodiment, one or more interface buses 1110 may be a processor bus, such as a version of a direct media interface (DMI) bus, in one embodiment. In at least one embodiment, one or more interface buses 1110 are not limited to DMI buses, 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 connections to I / O devices through a local I / O bus.

[0145] In at least one embodiment, the memory device 1120 can 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 having appropriate performance to be used as a processor memory. In at least one embodiment, the memory device 1120 can be operated as a system memory of the processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process.

[0146] In at least one embodiment, the memory controller 1116 is also coupled to an optional external graphics processor 1112, which can communicate with one or more graphics processors 1108 in the processor 1102 to perform graphics and media operations. In at least one embodiment, a display device 1111 can be connected to the processor 1102. In at least one embodiment, the display device 1111 can include one or more of the internal display devices, such as in a mobile electronic device or laptop device or an external display device connected through a display interface (e.g., DisplayPort, etc.). In at least one embodiment, the display device 1111 can include a head-mounted display (HMD), such as a stereoscopic display device used in virtual reality (VR) applications or augmented reality (AR) applications.

[0147] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to be connected to the storage device 1120 and one or more processors 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripherals 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, a data storage device 1124 (e.g., a hard drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 can 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 can include a touch screen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 can be a Wi-Fi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or long-term evolution (LTE) transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and can be, for example, a unified extensible firmware interface (UEFI). In at least one embodiment, the network controller 1134 can enable a network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to the interface bus 1110. In at least one embodiment, the audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, the system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to the system 1100. In at least one embodiment, the platform controller hub 1130 can also be connected to one or more universal serial bus (USB) controllers 1142, which connect input devices such as a keyboard and mouse 1143 combination, a camera 1144, or other USB input devices.

[0148] In at least one embodiment, instances of 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, platform controller hub 1130 and / or 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 a peripheral controller hub in a system chipset that communicates with processor 1102.

[0149] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. Details about the reasoning and / or training logic 715 are provided in conjunction with the following contents. Fig. 7A and / or Figure 7B In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the graphics processor 1500. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs that are embodied in the graphics processor. In addition, in at least one embodiment, the inference and / or training operations described herein may use a plurality of ALUs that are embodied in the graphics processor. Fig. 7A and / or Figure 7B 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) that configure the ALU of the graphics processor to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0150] Such components can be identified by replicas.

[0151] Fig.12 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 the additional core 1202N represented by the dashed box. 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 have access to one or more shared cache units 1206.

[0152] In at least one embodiment, the internal cache units 1204A-1204N and the shared cache unit 1206 represent a cache memory hierarchy within the processor 1200. In at least one embodiment, the 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 mid-level cache, such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, where the highest level of cache before external memory is categorized as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0153] In at least one embodiment, the processor 1200 may also include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, the 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).

[0154] In at least one embodiment, one or more processor cores 1202A-1202N include support for multiple threads simultaneously. In at least one embodiment, system agent core 1210 includes components for coordinating and operating processor cores 1202A-1202N during multithreaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) that includes logic and components for regulating one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0155] In at least one embodiment, the processor 1200 also includes a graphics processor 1208 for performing graphics processing operations. In at least one embodiment, the graphics processor 1208 is coupled to a shared cache unit 1206 and a system agent core 1210 including one or more integrated memory controllers 1214. In at least one embodiment, the system agent core 1210 also includes a display controller 1211 for driving the graphics processor output to one or more coupled displays. In at least one embodiment, the display controller 1211 may also be a separate module coupled to the graphics processor 1208 via at least one interconnect, or may be integrated within the graphics processor 1208.

[0156] In at least one embodiment, a ring-based interconnect unit 1212 is used to couple the internal components of the processor 1200. In at least one embodiment, alternative interconnect units may be used, such as point-to-point interconnects, switched interconnects, or other technologies. In at least one embodiment, the graphics processor 1208 is coupled to the ring-based interconnect unit 1212 via an I / O link 1213.

[0157] 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 modules 1218 (e.g., eDRAM modules). In at least one embodiment, each of processor cores 1202A-1202N and graphics processor 1208 uses embedded memory modules 1218 as a shared last level cache.

[0158] In at least one embodiment, processor cores 1202A-1202N are homogeneous cores that execute a common instruction set architecture. Details regarding inference and / or training logic 715 are provided below in conjunction with Fig. 7A and / or Figure 7B Provided. In at least one embodiment, the processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), wherein one or more processor cores 1202A-1202N execute 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, the processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, wherein one or more cores with relatively high power consumption are coupled with one or more power cores with lower power consumption. In at least one embodiment, the processor 1200 can be implemented on one or more chips or as a SoC integrated circuit.

[0159] The reasoning and / or training logic 715 is used to perform reasoning and / or training operations associated with one or more embodiments. In at least one embodiment, some or all of the reasoning and / or training logic 715 may be incorporated into the processor 1200. For example, in at least one embodiment, the training and / or reasoning techniques described herein may use one or more ALUs embodied in Fig.12 In addition, in at least one embodiment, the inference and / or training operations described herein may use the inference and / or training operations described herein. Fig. 7A and / or Figure 7BIn at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALU of the graphics processor 1200 to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0160] Such components can be used for replica identification.

[0161] Virtualized computing platform

[0162] Fig.13 is an example data flow diagram of a process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, the process 1300 can be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. The process 1300 can be executed within a training system 1304 and / or a deployment system 1306. In at least one embodiment, the training system 1304 can be used to perform training, deployment, and implementation of machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use with the deployment system 1306. In at least one embodiment, the deployment system 1306 can be configured to offload processing and computing resources in a distributed computing environment to reduce infrastructure requirements of the facility 1302. In at least one embodiment, one or more applications in the pipeline can use or call services (e.g., reasoning, visualization, computation, AI, etc.) of the deployment system 1306 during application execution.

[0163] In at least one embodiment, some applications used in the high-level processing and reasoning pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, the machine learning model may be trained at the facility 1302 using data 1308 (e.g., imaging data) generated at the facility 1302 (and stored on one or more picture archiving and communication system (PACS) servers at the facility 1302), the machine learning model may be trained using imaging or sequencing data 1308 from another one or more facilities, or a combination thereof. In at least one embodiment, the training system 1304 may be used to provide applications, services, and / or other resources to generate a working, deployable machine learning model for the deployment system 1306.

[0164] In at least one embodiment, the model registry 1324 can be backed by an object store, which can support versioning and object metadata. In at least one embodiment, the object store can be accessed from within the cloud platform through, for example, a cloud storage compatible application programming interface (API). In at least one embodiment, the machine learning models within the model registry 1324 can be uploaded, listed, modified, or deleted by developers or partners 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 a model with an application so that the model can be executed as part of the execution of a containerized instantiation of the application.

[0165] In at least one embodiment, the training system 1304 ( Fig.13 ) may include situations where the facility 1302 is training their own machine learning model, or has an existing machine learning model that needs to be optimized or updated. In at least one embodiment, imaging data 1308 generated by an imaging device, a sequencing device, and / or other type of device may be received. In at least one embodiment, once the imaging data 1308 is received, the AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 to be used as ground truth data for the machine learning model. In at least one embodiment, the AI-assisted annotation 1310 may include one or more machine learning models (e.g., a convolutional neural network (CNN)) that may be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, the AI-assisted annotation 1310 may then be used directly, or may be adjusted or fine-tuned using an annotation tool to generate ground truth data. In at least one embodiment, the AI-assisted annotation 1310, the labeled data 1312, or a combination thereof may be used as ground truth data for training a machine learning model. In at least one embodiment, the trained machine learning model can be referred to as an output model 1316 and can be used by the deployment system 1306 as described herein.

[0166] In at least one embodiment, the training pipeline may include a scenario where the facility 1302 requires a machine learning model for performing one or more processing tasks for one or more applications in the deployment system 1306, but the facility 1302 may not currently have such a machine learning model (or may not have a model that is optimized, efficient, or effective for this purpose). In at least one embodiment, an existing machine learning model may be selected from the model registry 1324. In at least one embodiment, the model registry 1324 may include machine learning models that are trained to perform a variety of different reasoning tasks on imaging data. In at least one embodiment, the machine learning models in the model registry 1324 may be trained on imaging data from a different facility (e.g., a facility located far away) rather than the facility 1302. In at least one embodiment, the machine learning model may have been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training is performed on imaging data from a specific location, the training may be performed at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts the transfer of the imaging data from off-site. In at least one embodiment, once a model is trained or partially trained at one location, the machine learning model can be added to the 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 the model registry 1324. In at least one embodiment, the machine learning model can then be selected from the model registry 1324 (and referred to as the output model 1316) and can be deployed in the deployment system 1306 to perform one or more processing tasks for one or more applications of the deployment system.

[0167] In at least one embodiment, the scenario may include a facility 1302 that requires a machine learning model for performing one or more processing tasks for one or more applications in the deployment system 1306, but the 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 the model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at the facility 1302 due to population differences, robustness of the training data used to train the machine learning model, diversity of training data anomalies, and / or other issues with the training data. In at least one embodiment, AI-assisted annotations 1310 can be used to help generate annotations corresponding to the imaging data 1308 for use as ground truth data for training or updating the machine learning model. In at least one embodiment, labeled clinical data 1312 can be used as ground truth data for training the machine learning model. In at least one embodiment, retraining or updating the machine learning model can be referred to as model training 1314. In at least one embodiment, model training 1314 (e.g., AI-assisted annotations 1310, labeled data 1312, or a combination thereof) can be used as ground truth data to retrain or update a machine learning model. In at least one embodiment, the trained machine learning model can be referred to as an output model 1316 and can be used by the deployment system 1306, as described herein.

[0168] In at least one embodiment, the deployment system 1306 may include software 1318, services 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, the deployment system 1306 may include a software "stack" such that the software 1318 may be built on top of the services 1320 and may use the services 1320 to perform some or all of the processing tasks, and the services 1320 and software 1318 may be built on top of the hardware 1322 and use the hardware 1322 to perform the processing, storage, and / or other computing tasks of the deployment system. In at least one embodiment, the software 1318 may include any number of different containers, each of which may perform an instantiation of an application. In at least one embodiment, each application may perform one or more processing tasks (e.g., reasoning, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in a high-level processing and reasoning pipeline. In at least one embodiment, in addition to receiving and configuring imaging data for use by each container and / or containers used by facility 1302 after processing through the pipeline, a high-level processing and reasoning pipeline can also be defined based on the selection of different containers desired or required to process imaging data 1308 (e.g., to convert the output back into a usable data type. In at least one embodiment, the combination of containers within software 1318 (e.g., which constitute a pipeline) can be referred to as a virtual instrument (as described in more detail herein), and the virtual instrument can utilize services 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated in a container.

[0169] In at least one embodiment, the data processing pipeline can 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 the deployment system 1306). In at least one embodiment, the input data can 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 can be pre-processed as part of the data processing pipeline to prepare the data for processing by one or more applications. In at least one embodiment, post-processing can 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 prepare the output data for transmission and / or use by the user (e.g., as a response to the inference request). In at least one embodiment, the inference task can be performed by one or more machine learning models, such as a trained or deployed neural network, which can include the output model 1316 of the training system 1304.

[0170] In at least one embodiment, tasks of a data processing pipeline may 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 may be published to a private (e.g., limited access) area of ​​a container registry (described in more detail herein), and trained or deployed models may be stored in the 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) may be available in a container registry, and once a user selects an image from a container registry for deployment in a pipeline, the image may be used to generate an instantiated container for the application for use by the user's system.

[0171] In at least one embodiment, a developer (e.g., a software developer, a clinician, a physician, etc.) can develop, publish, and store applications (e.g., as containers) for performing image processing and / or reasoning on provided data. In at least one embodiment, the development, publishing, and / or storage can be performed using a software development kit (SDK) associated with the system (e.g., to ensure that the developed applications and / or containers conform to or are compatible with the system). In at least one embodiment, the developed applications can be tested locally (e.g., at a first facility, on data from the first facility) using the SDK, which is installed as part of the system (e.g., Fig.12 Processor 1200 in the process 1300) may support at least some services 1320. In at least one embodiment, because a DICOM object may contain from one to hundreds of images or other data types, and because the data varies, the developer may be responsible for managing (e.g., setting up constructs for building pre-processing into the application, etc.) the extraction and preparation of the incoming data. In at least one embodiment, once validated by process 1300 (e.g., for accuracy), the application is made available in the container registry for selection and / or implementation by the user to perform one or more processing tasks on the data at the user's facility (e.g., a second facility).

[0172] In at least one embodiment, the developer can then share the application or container over a network for use by a system (e.g., Fig.131300). In at least one embodiment, the completed and validated application or container can be stored in the container registry, and the associated machine learning model can be stored in the model registry 1324. In at least one embodiment, the requesting entity (which provides the reasoning or image processing request) can browse the container registry and / or the model registry 1324 to obtain applications, containers, data sets, machine learning models, etc., select the desired combination of elements to be included in the data processing pipeline, and submit the image processing request. In at least one embodiment, the request may include the input data necessary to execute the request (and in some examples, patient-related data), and / or may include a selection of applications and / or machine learning models to be executed when processing the request. In at least one embodiment, the request can then be passed to one or more components (e.g., a cloud) of the deployment system 1306 to perform processing of the data processing pipeline. In at least one embodiment, the processing performed by the deployment system 1306 may include referencing elements (e.g., applications, containers, models, etc.) selected from the container registry and / or the model registry 1324. In at least one embodiment, once the results are generated by the pipeline, the results may be returned to the user for reference (eg, for viewing in a viewing application suite executing locally, on a local workstation or terminal).

[0173] In at least one embodiment, to assist in processing or executing applications or containers in the pipeline, services 1320 may be utilized. In at least one embodiment, services 1320 may include computing services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, services 1320 may provide functionality common to one or more applications in software 1318, and thus may abstract functionality into services that may be called or utilized by applications. In at least one embodiment, the functionality provided by services 1320 may run dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using Fig.12In at least one embodiment, rather than requiring that each application that shares the same functionality provided by the service 1320 must have a corresponding instance of the service 1320, the 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 that can provide machine learning model training and / or retraining capabilities. In at least one embodiment, a data enhancement service may be further included that can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, REST-compliant, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used that 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 that provides beamforming, segmentation, reasoning, imaging, and / or support for other applications within the pipeline of the virtual instrument.

[0174] In at least one embodiment, where the service 1320 includes an AI service (e.g., an inference service), as part of the execution of an application, one or more machine learning models can be executed by calling (e.g., as an API call) an inference service (e.g., an inference server) to execute one or more machine learning models or processing thereof. In at least one embodiment, where another application includes one or more machine learning models for a segmentation task, the application can call the inference service to execute the machine learning model for performing one or more processing operations associated with the segmentation task. In at least one embodiment, the software 1318 implementing the high-level processing and inference pipeline, which includes a segmentation application and anomaly detection application, can be pipelined because each application can call the same inference service to perform one or more inference tasks.

[0175] In at least one embodiment, the hardware 1322 may include a GPU, a CPU, a graphics card, an AI / deep learning system (e.g., an AI supercomputer such as NVIDIA's DGX), a cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, purpose-built support for the software 1318 and services 1320 in the deployment system 1306. In at least one embodiment, the use of GPU processing may be implemented to perform local processing (e.g., at the facility 1302) within the AI / deep learning system, in the cloud system, and / or other processing components of the deployment system 1306 to improve the efficiency, accuracy, and effectiveness of image processing and generation. In at least one embodiment, as a non-limiting example, with respect to deep learning, machine learning, and / or high-performance computing, the software 1318 and / or services 1320 may be optimized for GPU processing. In at least one embodiment, at least some of the computing environments of the deployment system 1306 and / or training system 1304 may be executed in a data center, one or more supercomputers, or high-performance computer systems with GPU-optimized software (e.g., a combination of hardware and software of an NVIDIA DGX system). In at least one embodiment, as described herein, hardware 1322 may include any number of GPUs that may be called 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 computing tasks. In at least one embodiment, an AI / deep learning supercomputer and / or GPU optimized software (e.g., as provided on NVIDIA's DGX system) may be used as a hardware abstraction and scaling platform to execute a cloud platform (e.g., NVIDIA's NGC). In at least one embodiment, the cloud platform may integrate an application container cluster system or coordination system (e.g., Kubernetes) on multiple GPUs to enable seamless scaling and load balancing.

[0176] Fig.14 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, the system 1400 can be used to implement Fig.13 The process 1300 and / or other processes of the system 1400 may include a high-level processing and reasoning pipeline. In at least one embodiment, the system 1400 may include a training system 1304 and a deployment system 1306. In at least one embodiment, the training system 1304 and the deployment system 1306 may be implemented using software 1318, services 1320, and / or hardware 1322, as described herein.

[0177] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) can be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 can be implemented locally (with respect to a healthcare service facility) or as a combination of cloud computing resources and local computing resources. In at least one embodiment, access to APIs in cloud 1426 can be restricted to authorized users by establishing security measures or protocols. In at least one embodiment, the security protocol can include a network token, which can be signed by an authentication (e.g., AuthN, AuthZ, Gluecon, etc.) service and can carry appropriate authorization. In at least one embodiment, the API of the virtual instrument (described herein) or other instances of system 1400 can be restricted to a set of public IPs that have been audited or authorized for interaction.

[0178] In at least one embodiment, the various components of system 1400 can 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, communications between facilities and components of system 1400 (e.g., for sending inference requests, for receiving results of inference requests, etc.) can be transmitted via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet), etc.

[0179] In at least one embodiment, similar to the present disclosure regarding Fig.13 As described, the training system 1304 can execute the training pipeline 1404. In at least one embodiment, where the deployment system 1306 will use one or more machine learning models in the deployment pipeline 1410, the 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 the training pipeline 1404, an output model 1316 can be generated. In at least one embodiment, the training pipeline 1404 can include any number of processing steps, such as, but not limited to, conversion 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 the deployment system 1306. In at least one embodiment, similar to the description regarding Fig.13 The first example training pipeline 1404 described may be used for a first machine learning model, similar to the training pipeline 1404 described with respect to FIG. Fig.13 The second example training pipeline 1404 described may be used for a second machine learning model, similar to the one described with respect to Fig.13The training pipeline 1404 of the third example described may be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 may 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 been trained and ready for deployment, so the training system 1304 may not perform any processing on the machine learning model, and one or more machine learning models may be implemented by the deployment system 1306.

[0180] In at least one embodiment, the output model 1316 and / or the pre-trained model 1406 may include any type of machine learning model, depending on the implementation or embodiment. In at least one embodiment and without limitation, the machine learning model used by the system 1400 may include using linear regression, logistic regression, decision tree, support vector machine (SVM), naive Bayes, k-nearest neighbor (Knn), k-means clustering, random forest, dimensionality reduction algorithm, gradient boosting algorithm, neural network (e.g., autoencoder, convolution, recursion, perceptron, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machine, etc.), and / or other types of machine learning models.

[0181] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotation, as described herein with respect to at least Fig.14In more detail. In at least one embodiment, the labeled clinical data 1312 (e.g., traditional annotations) can be generated by any number of techniques. In at least one embodiment, in some examples, labels or other annotations can be generated in a drawing program (e.g., an annotation program), a computer-aided design (CAD) program, a labeling program, another type of application suitable for generating ground-truth annotations or labels, and / or can be hand-drawn. In at least one embodiment, the ground-truth data can be synthetically generated (e.g., generated from a computer model or rendering), truly generated (e.g., designed and generated from real-world data), machine-generated (e.g., using feature analysis and learning to extract features from data and then generate labels), manually annotated (e.g., a labeler or annotation expert, defining the location of the label), and / or a combination thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by machine learning models), there can be corresponding ground-truth data generated by the training system 1304. In at least one embodiment, AI-assisted annotations can be performed as part of the deployment pipeline 1410; supplementing or replacing the AI-assisted annotations included in the training pipeline 1404. In at least one embodiment, the system 1400 may include a multi-layer platform that may include a software layer (e.g., software 1318) of a diagnostic application (or other application type) that may perform one or more medical imaging and diagnostic functions. In at least one embodiment, the system 1400 may be communicatively coupled (e.g., via an encrypted link) to a PACS server network of one or more facilities. In at least one embodiment, the system 1400 may be configured to access and reference data from a PACS server to perform operations such as training a machine learning model, deploying a machine learning model, image processing, reasoning, and / or other operations.

[0182] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or authenticated API through which an application or container may be invoked (e.g., called) from an external environment (e.g., facility 1302). In at least one embodiment, the application may then call or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with the respective application, and the software 1318 and / or services 1320 may utilize hardware 1322 to perform processing tasks in an effective and efficient manner. In at least one embodiment, communications received by or sent to the training system 1304 and deployment system 1306 may occur using a pair of DICOM adapters 1402A, 1402B.

[0183] In at least one embodiment, the deployment system 1306 can execute a deployment pipeline 1410. In at least one embodiment, the deployment pipeline 1410 can include any number of applications, which can be sequential, non-sequential, or otherwise applied to imaging data (and / or other data types) - including AI-assisted annotations, generated by imaging devices, sequencing devices, genomics devices, etc., as described above. In at least one embodiment, as described herein, the deployment pipeline 1410 for an individual device can be referred to as a virtual instrument for the device (e.g., a virtual ultrasound instrument, a virtual CT scanning instrument, a virtual sequencing instrument, etc.). In at least one embodiment, there can be more than one deployment pipeline 1410 for a single device, depending on the information desired from the data generated by the device. In at least one embodiment, there can be a first deployment pipeline 1410 in the case where an abnormality is desired to be detected from an MRI machine, and there can be a second deployment pipeline 1410 in the case where image enhancement is desired from the output of the MRI machine.

[0184] In at least one embodiment, the image generation application may include a processing task that includes the use of a machine learning model. 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 an application that performs a processing task. In at least one embodiment, the application may be selectable and customizable, and by defining the construction of the application, the deployment and implementation of the application for a particular user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of the system 1400 (e.g., services 1320 and hardware 1322), the deployment pipeline 1410 may be more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0185] In at least one embodiment, the deployment system 1306 may include a user interface 1414 (e.g., a graphical user interface, a web interface, etc.) that may be used to select applications to be included in the deployment pipeline 1410, to arrange applications, to modify or change applications or their parameters or configurations, to use and interact with the deployment pipeline 1410 during setup and / or deployment, and / or to otherwise interact with the deployment system 1306. In at least one embodiment, although not shown with respect to the training system 1304, the UI 1414 (or a different user interface) may be used to select models for use in the deployment system 1306, to select models for training or retraining in the training system 1304, and / or to otherwise interact with the training system 1304.

[0186] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may be used to manage the interaction between the application or container of the deployment pipeline 1410 and the service 1320 and / or the hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate the interaction 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 the software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in the 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 a logical unit 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 be executed in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0187] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed separately (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), which can allow for focus and attention 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 assist in communication and collaboration between different containers or applications. In at least one embodiment, as long as 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), the application coordination system 1428 and / or the pipeline manager 1412 can facilitate communication and sharing of resources between and among each 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 among the various applications or containers. In at least one embodiment, the scheduler can be used to track resource requirements of applications or containers, current or planned use of those resources, and resource availability. Thus, in at least one embodiment, the scheduler can allocate resources to different applications and allocate resources between and among applications, taking into account the needs and availability of the system. 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.

[0188] In at least one embodiment, the services 1320 utilized and shared by the applications or containers in the deployment system 1306 may include computing services 1416, AI services 1418, visualization services 1420, and / or other service types. In at least one embodiment, an application may call (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 services 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 a parallel computing platform 1430) to process data substantially simultaneously by one or more applications and / or one or more tasks of a single application. In at least one embodiment, a parallel computing platform 1430 (e.g., NVIDIA's CUDA) may enable general purpose computing on a GPU (GPGPU) (e.g., GPU / graphics 1422). In at least one embodiment, a software layer of a parallel computing platform 1430 may provide access to a virtual instruction set and parallel computing elements of a GPU 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 among multiple containers, and / or between and among 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 a container to enable the same data (e.g., where multiple different stages of an application or multiple applications are processing the same information) to be used for a shared memory segment from the parallel computing platform 1430. In at least one embodiment, instead of copying data and moving the data to different locations in memory (e.g., read / write operations), the same data in the same location of the memory may be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, since the data as a result of processing is used to generate new data, this information of the new location of the data may be stored and shared between various applications. 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 to understand the payload in the container.

[0189] In at least one embodiment, the AI ​​service 1418 may be utilized to perform a reasoning service for executing a machine learning model associated with an application (e.g., a task is to execute one or more processing tasks of an application). In at least one embodiment, the AI ​​service 1418 may utilize the 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 reasoning tasks. In at least one embodiment, the application of the deployment pipeline 1410 may use one or more output models 1316 of the self-training system 1304 and / or other models of the application to perform reasoning on the imaging data. In at least one embodiment, two or more examples of reasoning using the application coordination system 1428 (e.g., a scheduler) may be available. In at least one embodiment, the first category may include a high priority / low latency path that can achieve a higher service level agreement, such as for performing reasoning on an urgent request in an emergency, or for a radiologist during a diagnostic process. In at least one embodiment, the second category may include a standard priority path that may be used for requests that may not be urgent or where analysis can be performed at a later time. In at least one embodiment, application coordination system 1428 can allocate resources (e.g., services 1320 and / or hardware 1322) for different reasoning tasks of AI service 1418 based on priority paths.

[0190] In at least one embodiment, the shared memory may be installed to the AI ​​service 1418 in the system 1400. In at least one embodiment, the 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 the 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, in order to process the request, the request may be entered into a database, and if it is not already in the cache, the machine learning model may be located from the model registry 1324, a verification step may ensure that the appropriate machine learning model is loaded into the cache (e.g., shared storage), and / or a copy of the model may be saved to the cache. In at least one embodiment, if the application is not yet running or there are not enough instances of the application, a scheduler (e.g., a scheduler of the pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if the inference server has not yet been started to execute the model, the 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 beneficial. In at least one embodiment, the inference servers can be statically loaded into the corresponding distributed servers.

[0191] In at least one embodiment, inference can be performed using an inference server running in a container. In at least one embodiment, an instance of an inference server can be associated with a model (and optionally with multiple versions of a model). In at least one embodiment, if an instance of an inference server does not exist when a request is received to perform inference on a model, a new instance can be loaded. In at least one embodiment, when the inference server is started, the model can be passed to the inference server so that the same container can be used to serve different models as long as the inference server is running as a different instance.

[0192] In at least one embodiment, during application execution, a request for reasoning for a given application may be received, and a container (e.g., an instance of a hosted reasoning server) may be loaded (if not already loaded), and a launcher may be called. In at least one embodiment, preprocessing logic in the container may load, decode, and / or perform any additional preprocessing on the incoming data (e.g., using a CPU and / or GPU). In at least one embodiment, once the data is ready for reasoning, the container may perform reasoning on the data as needed. In at least one embodiment, this may include a single reasoning call for one image (e.g., a hand X-ray), or may require reasoning for hundreds of images (e.g., a chest CT). In at least one embodiment, the application may 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 may 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 may be measured from a requesting mechanism or entity and may include collaborative network traversal time as well as execution time of an inference service.

[0193] In at least one embodiment, the transmission of requests between the service 1320 and the reasoning application can be hidden behind a software development kit (SDK), and robust transmission can be provided through queues. In at least one embodiment, requests will be placed in queues through an API for individual application / tenant ID combinations, and the SDK will pull requests from the queue and provide the request to the application. In at least one embodiment, the name of the queue can be provided in the environment from which the SDK will pick up the queue. In at least one embodiment, asynchronous communication through queues may be useful because it can allow any instance of the application to pick up work when it is available. Results can be transmitted back through the queue to ensure that no data is lost. In at least one embodiment, the queue can also provide the ability to split the work, because the highest priority work can enter the queue connected to most instances of the application, and the lowest priority work can enter the queue connected to a single instance, which processes the tasks in the order received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in the cloud 1426, and the reasoning service can perform reasoning on the GPU.

[0194] In at least one embodiment, visualization services 1420 may be utilized to generate visualizations for viewing application and / or deployment pipeline 1410 outputs. In at least one embodiment, visualization services 1420 may utilize GPU / graphics 1422 to generate visualizations. In at least one embodiment, visualization services 1420 may implement rendering effects such as ray tracing to generate higher quality visualizations. In at least one embodiment, visualizations may include, but are not limited to, 2D image rendering, 3D volume rendering, 3D volume reconstruction, 2D tomographic slices, virtual reality displays, augmented reality displays, and the like. In at least one embodiment, a virtualized environment may be used to generate a virtual interactive display or environment (e.g., a virtual environment) for system users (e.g., doctors, nurses, radiologists, etc.) to interact with. In at least one embodiment, visualization services 1420 may include internal visualizers, movies, and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0195] In at least one embodiment, hardware 1322 may include GPU / graphics 1422, AI system 1424, cloud 1426, and / or any other hardware for executing 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 may be used to perform processing tasks for any feature or functionality of compute services 1416, AI services 1418, visualization services 1420, other services, and / or software 1318. For example, for AI services 1418, GPU / graphics 1422 may be used to perform pre-processing on imaging data (or other data types used by machine learning models), post-processing on the output of machine learning models, and / or perform 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 cloud 1426 (or at least part of a task being deep learning or reasoning) may be executed using one or more AI systems 1424. Likewise, while hardware 1322 is shown as discrete components, 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.

[0196] In at least one embodiment, AI system 1424 may include a purpose-built computing system (e.g., a supercomputer or HPC) configured for reasoning, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, in addition to CPU, RAM, storage, 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 use multiple GPUs / graphics 1422 to perform GPU-optimized tasks. 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.

[0197] In at least one embodiment, cloud 1426 may include a GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that may provide a GPU-optimized platform for executing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include an AI system 1424 for executing 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 an application coordination system 1428 that utilizes multiple GPUs to enable seamless scaling and load balancing between and among applications and services 1320. In at least one embodiment, cloud 1426 may be responsible for executing at least some services 1320 of system 1400, including compute services 1416, AI services 1418, and / or visualization services 1420, as described herein. In at least one embodiment, cloud 1426 can perform large and small batch inference (e.g., executing NVIDIA's TENSOR RT), provide accelerated parallel computing APIs and parallel computing platforms 1430 (e.g., NVIDIA's CUDA), execute application coordination system 1428 (e.g., KUBERNETES), provide graphics rendering APIs and platforms (e.g., for ray tracing, 2D graphics, 3D graphics, and / or other rendering techniques to produce higher quality movie effects), and / or can provide other functionality for system 1400.

[0198] Fig.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 may be used. Fig.14The process 1500 may be performed by the system 1400 of FIG. 1400. In at least one embodiment, the process 1500 may utilize the service 1320 and / or the hardware 1322 as described herein. In at least one embodiment, the refined model 1512 generated by the process 1500 may be executed by the deployment system for one or more containerized applications in a deployment pipeline.

[0199] In at least one embodiment, model training 1514 may include retraining or updating an initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data (such as customer data set 1506), and / or new ground truth 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 take as long or require as much processing as training the model from scratch. In at least one embodiment, during model training 1514, by resetting or replacing the output or loss layer of the initial model 1504, when generating predictions on the new customer data set 1506, the parameters for the new data set may be updated and re-adjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0200] 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 in part at one or more facilities other than the facility performing process 1500. In at least one embodiment, in order to protect the privacy and rights of patients, subjects, or customers of 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 cloud and / or other hardware may be used to train the pre-trained model 1506, but confidential, privacy-protected patient data may not be transmitted to any component of the cloud (or other non-local hardware), used by it, or accessed by it. 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, for example where customer or patient data has been issued privacy issues (e.g., by being waived, used for experimental purposes, etc.), or where the customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train pre-trained model 1506 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0201] In at least one embodiment, when selecting an application to use in a deployment pipeline, a user may also select a machine learning model to use for a particular application. In at least one embodiment, a user may not have a model to use, 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 customer data set 1506 of the user facility (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 it is deployed into a deployment pipeline for use with one or more applications.

[0202] In at least one embodiment, a user may select a pre-trained model to update, retrain, and / or fine-tune, and the pre-trained model may be referred to as an initial model 1504 for training the system in process 1500. In at least one embodiment, a customer data set 1506 (e.g., imaging data, genomic data, sequencing data, or other data types generated by equipment at a 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 truth data corresponding to the customer data set 1506 may be generated by the training system 1304. In at least one embodiment, the ground truth data may be generated, at least in part, at the facility by a clinician, scientist, physician, practitioner.

[0203] In at least one embodiment, AI-assisted annotation can be used in some examples to generate ground truth data. In at least one embodiment, AI-assisted annotation (e.g., implemented using an AI-assisted annotation SDK) can utilize a machine learning model (e.g., a neural network) to generate ground truth data for suggestions or predictions for a customer data set. In at least one embodiment, a user can use the annotation tool within a user interface (graphical user interface (GUI)) on a computing device.

[0204] 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, a polygon editing feature can be used to move vertices of a polygon to a more precise or fine-tuned position.

[0205] In at least one embodiment, once the customer dataset 1506 has associated ground truth data, the ground truth data (e.g., from AI-assisted annotations, manual labeling, etc.) can be used during model training to generate a refined model 1512. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 any number of times, and the ground truth 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, the refined model 1512 can be deployed within one or more deployment pipelines at a facility for use in performing one or more processing tasks with respect to medical imaging data.

[0206] In at least one embodiment, the refined model 1512 can be uploaded to the pre-trained models in the model registry to be selected by another facility. In at least one embodiment, this process can be completed at any number of facilities, so that the refined model 1512 can be further refined any number of times on new data sets to generate a more general model.

[0207] Fig. 15B is an example illustration of a client-server architecture 1532 for augmenting an annotation tool with a pre-trained annotation model according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 can be instantiated based on the client-server architecture 1532. In at least one embodiment, the AI-assisted annotation tool 1536 in an imaging application can assist radiology physicians, such as identifying organs and anomalies. In at least one embodiment, the imaging application can include a software tool that, as a non-limiting example, helps a user 1510 identify several extreme points on a specific organ of interest in an original image 1534 (e.g., in a 3D MRI or CT scan) and receive automatic annotation results for all 2D slices of the specific organ. In at least one embodiment, the results can be stored in a data store as training data 1538 and used as, for example, but not limited to, ground truth data for training. In at least one embodiment, when the computing device 1508 sends extreme points for AI-assisted annotation, for example, a deep learning model can receive the data as input and return an inference result for segmenting an organ or anomaly. In at least one embodiment, the pre-instantiated annotation tool (e.g., Fig. 15B The AI-assisted annotation tool 1536 in the example can be enhanced by making an API call (e.g., API call 1544) to a server (such as an annotation assistant server 1540), which may include a set of pre-trained models 1542 stored in, for example, an annotation model registry. In at least one embodiment, the annotation model registry can store pre-trained models 1542 (e.g., machine learning models, such as deep learning models) that are pre-trained to perform AI-assisted annotation on specific organs or abnormalities. In at least one embodiment, these models can be further updated by using a training pipeline. In at least one embodiment, the pre-installed annotation tools can be improved over time as newly labeled data is added.

[0208] Various embodiments may be described by the following terms:

[0209] 1. A computer-implemented method comprising:

[0210] Obtaining a first sequence of points representing a first shape of a first object;

[0211] generating a first reversible transformation of the first object based in part on at least a first subset of the first sequence of points;

[0212] generating a first canonical form of the first object using the first reversible transform;

[0213] Obtaining a second sequence of points representing a second shape of a second object;

[0214] generating a second reversible transformation of a second object based in part on at least a second subset of the second sequence of points;

[0215] generating a second canonical form of the second object using the second reversible transform; and

[0216] Based in part on comparing the first canonical form to the second canonical form, determining that the second object is a duplicate of the first object.

[0217] 2. The computer-implemented method of clause 1, further comprising:

[0218] determining a first vector between a selected origin and a first point in the first subset;

[0219] determining a second vector between the selected origin and a second point in the first subset, the second vector being linearly independent of the first vector;

[0220] A third vector is determined between the selected origin and a third point in the first subset, the third vector being linearly independent of the first vector and the second vector.

[0221] 3. The computer-implemented method of clause 2, wherein the first vector is perpendicular to the second vector.

[0222] 4. A computer-implemented method according to clause 3, wherein the first point is selected to provide the longest difference vector starting from the selected origin.

[0223] 5. The computer-implemented method of clause 2, wherein at least one of the selected origin, the first point, the second point, or the third point is selected pseudo-randomly.

[0224] 6. The computer-implemented method of clause 1, further comprising:

[0225] determining a first hash of the first object based at least in part on a first object topology;

[0226] determining a second hash of the second object based at least in part on a second object topology; and

[0227] Based on the first hash and the second hash, the second object is placed in a common bucket with the first object.

[0228] 7. The computer-implemented method of clause 1, further comprising:

[0229] It is determined that the first object was imported from a source that applies a point-level transformation to the first object.

[0230] 8. The computer-implemented method of clause 1, further comprising:

[0231] deleting the second object; and

[0232] The first object is replicated to provide a representation of the second object.

[0233] 9. A processor comprising:

[0234] One or more circuits for:

[0235] determining a first hash value for the first object based at least on the first object topology;

[0236] determining a set of linearly independent vectors of the first object;

[0237] determining, based at least on a second object topology, that a second hash value of a second object is within a threshold similarity of the first hash value;

[0238] comparing the first object and the second object using a transformation associated with the set of linearly independent vectors; and

[0239] It is determined that the first object and the second object are duplicates.

[0240] 10. The processor of clause 9, wherein the one or more circuits are further configured to:

[0241] A first point set of the vector set is determined from a sequence of points corresponding to the first object.

[0242] 11. A processor according to clause 9, wherein the set of vectors extends from a common origin.

[0243] 12. A processor according to clause 9, wherein the value of each angle between vectors in the vector set exceeds a threshold.

[0244] 13. The processor of clause 12, wherein the value is equal to 90 degrees.

[0245] 14. A processor according to clause 13, wherein the respective lengths of the vectors in the set of vectors are normalized to form a rigid transformation.

[0246] 15. The processor of clause 9, wherein the first object and the second object are represented by at least one of a triangle mesh, a polygon mesh, a non-uniform rational B-spline, a Bezier patch, or a subdivision surface.

[0247] 16. The processor of clause 9, wherein the processor is comprised of at least one of:

[0248] A system for performing simulation operations;

[0249] Systems for performing simulated operations to test or validate autonomous machine applications;

[0250] Systems for performing digital twin operations;

[0251] A system for performing light transport simulations;

[0252] Systems for rendering graphical output;

[0253] Systems for performing deep learning operations;

[0254] Systems implemented using edge devices;

[0255] Systems for generating or presenting virtual reality (VR) content;

[0256] Systems for generating or presenting augmented reality (AR) content;

[0257] Systems for generating or presenting mixed reality (MR) content;

[0258] A system comprising one or more virtual machines (VMs);

[0259] Systems for performing operations of conversational AI applications;

[0260] A system for performing operations of a generative AI application;

[0261] A system for performing operations using a language model;

[0262] A system for performing one or more generative content operations using a large language model (LLM);

[0263] A system implemented at least in part in a data center;

[0264] A system for performing hardware testing using simulation;

[0265] A system for performing one or more generative content operations using a language model;

[0266] Systems for synthetic data generation;

[0267] A collaborative content creation platform for 3D assets; or

[0268] A system implemented at least in part using cloud computing resources.

[0269] 17. A system comprising:

[0270] One or more processors for determining a similarity between the first object and the second object based at least on mapping a second canonical form of the second object to a first canonical form of the first object, the respective canonical forms being determined by ordered tuples of points forming at least three linearly independent vectors.

[0271] 18. The system of clause 17, wherein the at least three linearly independent vectors extend from a common origin.

[0272] 19. The system of clause 17, wherein the second canonical form and the first canonical form are associated with a transformation of the first object and a transformation of the second object, respectively.

[0273] 20. The system of clause 17, wherein the ordered tuple comprises at least four points selected pseudo-randomly.

[0274] 21. The system of clause 17, wherein the one or more processors are further configured to delete the second object when the second object is sufficiently similar to the first object.

[0275] 22. The system of clause 17, wherein the system is one of:

[0276] A system for performing simulation operations;

[0277] Systems for performing simulated operations to test or validate autonomous machine applications;

[0278] Systems for performing digital twin operations;

[0279] A system for performing light transport simulations;

[0280] Systems for rendering graphics output;

[0281] Systems for performing deep learning operations;

[0282] Systems implemented using edge devices;

[0283] Systems for generating or presenting virtual reality (VR) content;

[0284] Systems for generating or presenting augmented reality (AR) content;

[0285] Systems for generating or presenting mixed reality (MR) content;

[0286] A system comprising one or more virtual machines (VMs);

[0287] Systems for performing operations of conversational AI applications;

[0288] A system for performing operations of a generative AI application;

[0289] A system for performing operations using a language model;

[0290] A system for performing one or more generative content operations using a large language model (LLM);

[0291] A system implemented at least in part in a data center;

[0292] A system for performing hardware testing using simulation;

[0293] A system for performing one or more generative content operations using a language model;

[0294] Systems for synthetic data generation;

[0295] A collaborative content creation platform for 3D assets; or

[0296] A system implemented at least in part using cloud computing resources.

[0297] Other variations are within the spirit of the present disclosure. Thus, while the disclosed technology is susceptible to various modifications and alternative constructions, certain illustrated embodiments thereof are shown in the drawings and have been described in detail above. However, it should be understood that there is no intention to limit the disclosure to one or more specific forms disclosed, but on the contrary, it is intended to cover all modifications, alternative constructions, and equivalents that fall within the spirit and scope of the present disclosure as defined by the appended claims.

[0298] Unless otherwise noted or clearly contradictory to the context, in the context of describing the disclosed embodiments (particularly in the context of the appended claims), the use of the terms "one" and "an" and "the" and similar references should be interpreted as covering the singular and plural, rather than as definitions of terms. Unless otherwise noted, the terms "include", "have", "include" and "contain" should be interpreted as open terms (meaning "including but not limited to") unless otherwise noted. The term "connected" (which refers to a physical connection when unmodified) should be interpreted as partially or completely included, attached to or connected together, even if there are some interventions. Unless otherwise noted herein, references to numerical ranges herein are intended only to be used as a shorthand method of referring to each individual value falling within the range, respectively, and each individual value is incorporated into the specification as if it were individually described herein. Unless otherwise noted or contradictory to the context, the use of the term "set" (e.g., "item set") or "subset" should be interpreted as a non-empty set including one or more members. Furthermore, unless otherwise indicated or contradicted by context, the term "subset" of a corresponding set does not necessarily mean a proper subset of the corresponding set, but rather a subset and a corresponding set may be equivalent.

[0299] Unless expressly indicated otherwise or clearly contradicted by context, conjunctions such as phrases of the form "at least one of A, B, and C" or "at least one of A, B and C" are understood in context to be generally used to refer to an item, clause, or the like that may be A or B or C, or any non-empty subset of the set A and B and C. For example, in the illustrative example of a set having three members, the conjunction 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}. Thus, such conjunction language is not generally intended to imply that certain embodiments require the presence of at least one of A, at least one of B, and at least one of C. In addition, unless expressly indicated otherwise or contradicted by context, the term "plurality" refers to a plural state (e.g., "plurality of items" means a plurality of items). The number of items in a plurality of items is at least two, but may be more if expressly indicated or indicated by context. Further, the phrase "based on" means "based at least in part on" rather than "based solely on" unless otherwise specified or clear from context.

[0300] Unless otherwise indicated herein or clearly contradictory to 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 and / or combinations thereof) are performed 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 applications) that are jointly executed on one or more processors by hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium in the form of, for example, a computer program that includes a plurality of instructions that can be executed 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., propagated transient electrical or electromagnetic transmissions), but includes non-transitory data storage circuits (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on a set of 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 being executed), causes the computer system to perform the operations described herein. In at least one embodiment, a set of non-transitory computer-readable storage media includes a plurality of non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media in the plurality of non-transitory computer-readable storage media lacks all the code, but the plurality of non-transitory computer-readable storage media stores all the code together. In at least one embodiment, the executable instructions are executed so that different instructions are executed by different processors, for example, a non-transitory computer-readable storage medium stores instructions, and a main central processing unit ("CPU") executes some instructions, while a graphics processing unit ("GPU") executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and different processors execute different subsets of instructions.

[0301] Thus, in at least one embodiment, a computer system is configured to implement one or more services that individually or collectively perform the operations of the processes described herein, and such a computer system is configured with applicable hardware and / or software that enables the implementation of the operations. In addition, a computer system that implements at least one embodiment of the present disclosure is a single device, and in another embodiment is a distributed computer system that includes multiple devices that operate in different ways, so that the distributed computer system performs the operations described herein, and so that a single device does not perform all operations.

[0302] The use of any and all examples or exemplary language (e.g., "such as") provided herein is intended only to better illustrate embodiments of the present disclosure and does not limit the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any non-claimed element is essential to practicing the disclosure.

[0303] All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.

[0304] In the specification and claims, the terms "coupled" and "connected," as well as their derivatives, may be used. It should be understood that these terms may not be intended as synonyms for each other. On the contrary, in specific 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.

[0305] Unless explicitly stated otherwise, it is to be understood that throughout the specification, terms such as “processing”, “computing”, “calculating”, “determining” and the like refer to the actions and / or processes of a computer or computing system or similar electronic computing device that processes and / or converts data represented as physical quantities (e.g., electronic) in registers and / or memories of the computing system into other data similarly represented as physical quantities in the memories, registers or other such information storage, transmission or display devices of the computing system.

[0306] In a similar manner, the term "processor" may refer to any device or part of a memory that processes electronic data from registers and / or memory and converts the electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" may be a CPU or a GPU. A "computing platform" may include one or more processors. As used herein, a "software" process may include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process may refer to multiple processes to execute instructions sequentially or in parallel, continuously or intermittently. The terms "system" and "method" may be used interchangeably herein, as long as a system may embody one or more methods, and a method may be considered a system.

[0307] In this document, reference may be made to obtaining, acquiring, receiving or inputting analog or digital data into a subsystem, a computer system or a computer-implemented machine. It is possible to obtain, acquire, receive or input analog and digital data in a variety of ways, such as by receiving data as a parameter of a function call or a call to an application programming interface. In some implementations, the process of obtaining, acquiring, 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 obtaining, acquiring, 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. It is also possible to reference 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 accomplished by transmitting data as an input or output parameter of a function call, an application programming interface or an interprocess communication mechanism.

[0308] Although the above discussion sets forth example implementations of the described techniques, other architectures may be used to implement the described functionality and are intended to fall within the scope of the present disclosure. In addition, although specific responsibilities are defined above for discussion purposes, various functions and responsibilities may be allocated and divided in different ways, depending on the circumstances.

[0309] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as exemplary forms of implementing the claims.

Claims

1. A computer-implemented method comprising: Obtaining a first sequence of points representing a first shape of a first object; generating a first reversible transformation of the first object based in part on at least a first subset of the first sequence of points; generating a first canonical form of the first object using the first reversible transform; Obtaining a second sequence of points representing a second shape of a second object; generating a second reversible transformation of a second object based in part on at least a second subset of the second sequence of points; generating a second canonical form of the second object using the second reversible transform; as well as Based in part on comparing the first canonical form to the second canonical form, determining that the second object is a duplicate of the first object.

2. The computer-implemented method of claim 1 , further comprising: determining a first vector between a selected origin and a first point in the first subset; determining a second vector between the selected origin and a second point in the first subset, the second vector being linearly independent of the first vector; A third vector is determined between the selected origin and a third point in the first subset, the third vector being linearly independent of the first vector and the second vector. 3 . The computer-implemented method of claim 2 , wherein the first vector is perpendicular to the second vector. 4 . The computer-implemented method of claim 3 , wherein the first point is selected to provide a longest difference vector starting from the selected origin.

5. The computer-implemented method of claim 2, wherein at least one of the selected origin, the first point, the second point, or the third point is pseudo-randomly selected.

6. The computer-implemented method of claim 1 , further comprising: determining a first hash of the first object based at least in part on a first object topology; determining a second hash of the second object based at least in part on a second object topology; as well as Based on the first hash and the second hash, the second object is placed in a common bucket with the first object.

7. The computer-implemented method of claim 1 , further comprising: It is determined that the first object was imported from a source that applies a point-level transformation to the first object.

8. The computer-implemented method of claim 1 , further comprising: deleting the second object; and The first object is replicated to provide a representation of the second object.

9. A processor comprising: One or more circuits for: determining a first hash value for the first object based at least on the first object topology; determining a set of linearly independent vectors of the first object; determining, based at least on a second object topology, that a second hash value of a second object is within a threshold similarity of the first hash value; comparing the first object and the second object using a transformation associated with the set of linearly independent vectors; and It is determined that the first object and the second object are duplicates.

10. The processor of claim 9, wherein the one or more circuits are further configured to: A first point set of the vector set is determined from a sequence of points corresponding to the first object.

11. The processor of claim 9, wherein the set of vectors extend from a common origin. 12 . The processor of claim 9 , wherein a value of each angle between vectors in the vector set exceeds a threshold value.

13. The processor of claim 12, wherein the value is equal to 90 degrees.

14. The processor of claim 13, wherein respective lengths of vectors in the set of vectors are normalized to form a rigid transformation.

15. The processor of claim 9, wherein the first object and the second object are represented by at least one of a triangle mesh, a polygon mesh, a non-uniform rational B-spline, a Bezier patch, or a subdivision surface.

16. The processor of claim 9, wherein the processor is included in at least one of the following: A system for performing simulation operations; Systems for performing simulated operations to test or validate autonomous machine applications; Systems for performing digital twin operations; A system for performing light transport simulations; Systems for rendering graphical output; Systems for performing deep learning operations; Systems implemented using edge devices; Systems for generating or presenting virtual reality (VR) content; Systems for generating or presenting augmented reality (AR) content; Systems for generating or presenting mixed reality (MR) content; A system comprising one or more virtual machines VM; Systems for performing operations of conversational AI applications; A system for performing operations of a generative AI application; A system for performing operations using a language model; A system for performing one or more generative content operations using a large language model (LLM); A system implemented at least in part in a data center; A system for performing hardware testing using simulation; A system for performing one or more generative content operations using a language model; Systems for synthetic data generation; A collaborative content creation platform for 3D assets; or A system implemented at least in part using cloud computing resources.

17. A system comprising: One or more processors for determining a similarity between the first object and the second object based at least on mapping a second canonical form of the second object to a first canonical form of the first object, the respective canonical forms being determined by ordered tuples of points forming at least three linearly independent vectors.

18. The system of claim 17, wherein the at least three linearly independent vectors extend from a common origin.

19. The system of claim 17, wherein the second canonical form and the first canonical form are associated with a transformation of the first object and a transformation of the second object, respectively.

20. The system of claim 17, wherein the ordered tuple comprises at least four points selected pseudo-randomly.

21. The system of claim 17, wherein the one or more processors are further configured to delete the second object when the second object is sufficiently similar to the first object.

22. The system of claim 17, wherein the system is one of: A system for performing simulation operations; Systems for performing simulated operations to test or validate autonomous machine applications; Systems for performing digital twin operations; A system for performing light transport simulations; Systems for rendering graphical output; Systems for performing deep learning operations; Systems implemented using edge devices; Systems for generating or presenting virtual reality (VR) content; Systems for generating or presenting augmented reality (AR) content; Systems for generating or presenting mixed reality (MR) content; A system comprising one or more virtual machines VM; Systems for performing operations of conversational AI applications; A system for performing operations of a generative AI application; A system for performing operations using a language model; A system for performing one or more generative content operations using a large language model (LLM); A system implemented at least in part in a data center; A system for performing hardware testing using simulation; A system for performing one or more generative content operations using a language model; Systems for synthetic data generation; A collaborative content creation platform for 3D assets; or A system implemented at least in part using cloud computing resources.

Images