Generating motion from text in content generation systems and applications

Abstract

The invention relates to generating motion from text in a content generation system and application. The methods presented herein are directed to utilizing reinforcement learning to fine-tune generative models (e.g., motion diffusion models) to achieve particular objectives, e.g., for generating representations of human motion corresponding to provided text inputs. A discriminator may be used to guide training of a generative model. In at least one embodiment, a discriminator may compare the input text and the generated motion representation (or embedding of each) to determine an alignment value or match score, e.g., which may then be used to adjust network parameters or weights of the generative model to improve alignment between the input text and the generated motion.

Description

BACKGROUND

[0001] It can be beneficial, if not necessary, to render complex three-dimensional objects in a manner that appears substantially realistic, or at least accurate or consistent, to a human viewer, in various applications such as for use in game, animation, or virtual reality content generation, for example. This can include generating realistic motion for objects or characters for use in animation or other such scenarios. In some cases, such motion can be generated based on input indicative of a type of motion, e.g., a machine learning model can take in such input and output generated motion corresponding to the input. Such model-generated motion can not always be correct or realistic, e.g., the motion differs from the motion indicated in the input, or does not represent a realistic motion of that type. To improve the performance of these generative models, various previous approaches have attempted to improve the relevant training dataset, e.g., by improving label quality or increasing the total amount of training samples. Other approaches have attempted to provide and incorporate human feedback in the training process. However, these approaches can be expensive and time-consuming, and can have inconsistencies due to differences in human perception. BRIEF DESCRIPTION OF DRAWINGS

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

[0003] Figures 1A-1D An example motion generated for text input is shown, according to at least one embodiment;

[0004] Figure 2 Components of an example system that can be used to fine-tune a model to generate motion from text are shown, according to at least one embodiment;

[0005] Figure 3A And Figure 3B An example system for training a generative model is shown, according to at least one embodiment;

[0006] Figure 3C An example system for generating motion from text is shown, according to at least one embodiment;

[0007] Figure 4A And Figure 4B Components of an example content generation system are shown, according to at least one embodiment;

[0008] Figure 5A And Figure 5B An example process for training a generative model is shown, according to at least one embodiment;

[0009] Figure 5C An example process for generating motion from text is shown, according to at least one embodiment;

[0010] Figure 6 components of a distributed system that can be used to generate and provide image content, according to at least one embodiment;

[0011] Figure 7A inference and / or training logic, according to at least one embodiment;

[0012] Figure 7B inference and / or training logic, according to at least one embodiment;

[0013] Figure 8 an example data center system, according to at least one embodiment;

[0014] Figure 9 a computer system, according to at least one embodiment;

[0015] Figure 10 a computer system, according to at least one embodiment;

[0016] Figure 11 at least portions of a graphics processor, according to one or more embodiments;

[0017] Figure 12 at least portions of a graphics processor, according to one or more embodiments;

[0018] Figure 13 is an example dataflow graph of a high-level compute pipeline, according to at least one embodiment;

[0019] Figure 14 is a system diagram of an example system for training, adapting, instantiating, and deploying machine learning models in a high-level compute pipeline, according to at least one embodiment; and

[0020] Figure 15A and Figure 15B is a dataflow graph of a process for training a machine learning model, according to at least one embodiment, and a client-server architecture that leverages a pre-trained annotation model to enhance an annotation tool. DETAILED DESCRIPTION

[0021] In the following description, various embodiments will be described. 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 one skilled in the art that the embodiments can be practiced without specific details being presented herein. In other instances, well-known features are omitted or simplified in order not to obscure the illustrative embodiments being described.

[0022] The systems and methods described herein can be used by, but are not limited to, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more advanced driver assistance systems (ADAS)), manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled with one or more trailers, aircraft, watercraft, shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, airplanes, engineering vehicles, trains, underwater vehicles, remote-controlled vehicles such as drones, and / or other vehicle types. Further, 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 twin, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, object or actor simulation and / or digital twin, data center processing, conversational AI, generative AI with large language models (LLMs) and / or visual language models (VLMs), light transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation for 3D assets, cloud computing, and / or any other suitable application.

[0023] The disclosed embodiments can be included in various 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, marine systems, smart area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twin operations, systems implemented using edge devices, systems containing one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least partially in data centers, systems for performing conversational AI operations, systems for performing generative operations using LLMs and / or VLMs, systems for performing light transport simulation, systems for performing collaborative content creation for 3D assets, systems implemented at least partially using cloud computing resources, and / or other types of systems.

[0024] Methods according to various exemplary embodiments are used to generate representations of specified motions. In particular, various embodiments are used to enable realistic generation of anthropomorphized motions based on, for example, at least textual input. A generative model (e.g., a motion diffusion model) can be trained to generate a representation of a motion of a human or other character, object, or organism given a textual (or similar) input indicative of at least a type of motion. A separate model (e.g., a discriminator) can be used to guide such training or fine-tuning of the generative model, for example, by using a reinforcement learning based approach. In at least one embodiment, a single training dataset can be used to train both the generative model and the separate discriminator model, where the discriminator model can provide an indication (e.g., an alignment value or a matching score) that is an indication of how well a generated motion representation aligns with a provided textual prompt (or speech input converted to text, etc.). In at least one embodiment, the discriminator can compare an embedding of the textual prompt and a corresponding motion representation as generated by the generative model to compute an alignment value or a matching score (or other such indicator). The alignment score can be used for reinforcement learning to further train or “fine-tune” the generative model to improve the accuracy of the generated motions from textual input. This can include, for example, performing a dot product or distance computation based in part on the embeddings. The matching score or alignment value can then be used in a loss function to generate a loss value that can be used to update appropriate network weights or parameters of the generative model during the training or fine-tuning process. In other embodiments, a motion-to-text model can be used to generate a textual description or indication of the generated motion, and a discriminator can be used to compare this textual indication to the input text, which can be trained to identify similar concepts specified differently in the text and generate an alignment value or other such matching score for adjusting the relevant network weights or parameters.

[0025] Variations of this functionality and other such functionality can also be used within the scope of the various embodiments, in accordance with the teachings and suggestions contained herein.

[0026] In at least one embodiment, a generative model (e.g., a motion diffusion model) can be trained to produce a representation of an animated anthropomorphized (or similar) motion from an instructional input (e.g., a textual input). The representation can be any appropriate representation, such as a video containing a representation of a character performing a particular motion, or a model of a character that is manipulated to perform a particular motion, among other such options. The textual input can be provided in any appropriate format, such as a textual string entered via a keyboard or a spoken instruction converted to speech using a text-to-speech converter, among other such options. The text can specify the motion in a typical human language, such as a written description of the motion in English, or can be provided in an encoded or domain-specific language, among other such options.

[0027] Figure 1AAn example text input 100, which may be provided in at least one embodiment, is illustrated. In this example, a model can be selected to generate a representation of a character performing an input movement, wherein a specific character or character identifier may be provided as a separate input, along with other information that helps generate a representation of the character performing a specific movement. In this example, the text input is "get up from the ground." Figure 1B As shown in example image 120, character 122 may currently (or initially) be represented as sitting on the ground. In other embodiments, this initial posture and / or position may be determined in part based on input text. For example, in the case of text indicating "get up from the ground," the model may reasonably infer that the character's starting point should be on the ground, and then the character will stand up from the ground. The model can be trained to understand the movement of "getting up from the ground," which in Figure 1C and Figure 1D The example images 140 and 160 shown can contain realistic motion, where the character (represented by a wireframe model in this example) can use the character's hands to help the character stand up until the character is in a standing pose.

[0028] There can be various problems or challenges in generating representations of such movements. For example, there may be many different ways to interpret the "getting up" movement, and many different ways to perform such movements. Some of these options may be suitable for a particular character, while others may not. Furthermore, some options may be realistic or consistent for a particular character, while others may not. For example, a character simply changing directly from a sitting position to a standing position without using the character's hands or kneeling first may not be realistic for a particular character. A character that should move in a realistic way should not float through such movements or otherwise perform physically impossible actions. Moreover, even if the accurate type of movement is determined, the actual animation generated by the generative model may not be realistic, for example, failing to represent appropriate weight or support, proper kinematics, realistic movement sequences, or other such aspects.

[0029] A method according to at least one embodiment can train a machine learning model capable of accurately and consistently generating representations of motion (e.g., human motion) from text, text-based input, and / or similar types of input. Machine learning models (or combinations of machine learning models) can be used to perform tasks such as text interpretation or encoding, motion generation, motion encoding and discrimination, and other such options. In at least one embodiment, a set of training data can be used to train a generator model (e.g., a motion diffusion model) to generate motion representations corresponding to input text, where the text may specify the motion (or type of motion) to be generated. In at least one embodiment, a separate encoder can be used to encode text into, for example, a latent space or feature vector, and a generative model can be trained to take the text encoding as input to generate motion representations. At least one subset of this same training dataset can also be used to train a separate machine learning model (e.g., a discriminator) to help guide the training of the generative model. In at least one embodiment, a separate discrimination model can score the alignment of a particular motion with a given text cue. This discrimination model can take the form of a contrastive model that measures the difference between the embedding of the motion and the embedding of the text, or the form of a model trained to generate text output based on input motion, and other such options. The discriminator can then provide a score reflecting the generative (e.g., text-to-motion) model's ability to generate appropriate and / or realistic motion for a given text cue. The discriminator's output can then be used to further train or fine-tune the generative model, for example, by optimizing the discriminator's score using reinforcement learning. This optimization process may subsequently help improve the generative model's text alignment.

[0030] Figure 2 Components of an example system 200, according to at least one embodiment, for training a generative model 204 to generate realistic motion from text are shown. In this example, a user can use a client device 208 to initiate a training procedure for a selected motion generator 204. This may include, for example, selecting the type of generative model or pre-trained generative model, and a set of training data to be used for training or fine-tuning. The user may also specify aspects or criteria of the training, such as one or more training termination criteria, convergence criteria, etc. The training manager 216 may be any suitable system, service, or process as discussed or suggested herein for training the motion generator 204.

[0031] During training (or updating, fine-tuning, etc.), text input 202 can be provided to motion generator 204. The text input can be any suitable text-based input sufficient to indicate or convey the type of motion to be generated. In this example, the text is input to motion generator 204 in text form, but the text can also be encoded first and then provided as input in its encoded form, such as points in a latent space, feature vectors, or another such encoding or embedding. Motion generator 204 can then take this text input and output the generated motion 212, or a representation of the motion inferred from the input text. Motion generator 204 can be any suitable type of generative model, such as a diffusion model. Any suitable type of diffusion model can also be used, such as a denoised diffusion probability model, a fractional generative model, or a stochastic differential equation model capable of modeling and generating outputs using a diffusion-based process. One or more embodiments may use alternative generative models, such as transformer-based models, variational autoencoder-based models, or generative adversarial networks. As shown in the figure, in at least one embodiment, motion generator 204 can generate motion using a specific virtual object 208, for example, which can be selected from asset repository 210 or other such sources or locations.

[0032] In this example, a second machine learning model is used to help guide the training, updating, or fine-tuning of the motion generator 204. A discriminator 214 can be used to compare the generated motion 212 with the text input 202 and generate a comparison result. The comparison can be performed in several ways to generate several types of results. In this example, a first encoder 206 is used to encode the text input 202, and a second encoder 218 is used to encode the generated motion 212. The discriminator 214 can then receive both the text embedding and the motion embedding as input. In other embodiments, a single encoder can be used for both text and generated motion, or the discriminator 214 can include encoding capabilities, among other similar options. In this example, the discriminator can receive the text embedding and the corresponding motion embedding, both of which can correspond to, for example, points in an n-dimensional latent space or an n-dimensional feature vector, where n can refer to the number of determinable features generated from the encoding process. In such an example, the discriminator can determine the distance between points in the latent space and can provide a “score” or other result based in part on the determined distance, such as a score inversely proportional to the distance. For example, points very close to each other in the latent space may result in scores close to 1 (on a scale normalized from 0 to 1), while points farther apart in the latent space may have lower scores closer to 0. In some embodiments, the discriminator may also output a confidence score of that score (or the confidence score may be reflected in the score itself). In this example, the score may be used alone or as part of a loss value determined using an appropriate loss function, for example, as guidance for further training of the motion generator 204. For example, the loss or reward value may be provided via backpropagation and used by the training manager 216 to adjust one or more network weights or parameters of the motion generator 204. Such a process may continue until training termination criteria are met, such as when it is determined that the motion generator 204 has converged, or when the discriminator's score consistently meets specified optimization criteria, and other such options.

[0033] As described, discriminators (or other such comparators) that can also analyze other forms of input can be used. For example, such as Figure 3A As shown in the example system 300, the discriminator 308 can take the text input 302 and the generated motion 306 output by the motion generator 304 and compare the text and motion directly, or based on an embedding or other form generated internally by the discriminator 308. It should be understood that reference numerals may be used interchangeably between the figures for ease of explanation, but such use should not be construed as limiting the scope of the embodiments unless explicitly stated otherwise. In another example, the text input 302 and the generated motion 306 can be generated in an encoded form, eliminating the need for separate encoding, and this encoded form can be directly input to the discriminator 308, with the score used to fine-tune the motion generator 304.

[0034] Figure 3B Another example system 330, according to at least one embodiment, is shown for use in training and / or fine-tuning generative models. In this example, a text-to-motion generator 334 can be used to infer generated motion 336 from text input 332. In another example, the same text-to-motion model 334 can be used in reverse, i.e., inputting motion to the model and then inferring text output describing that motion, and other similar options. In this example, a text-to-motion generator 338 can then be used to attempt to infer descriptive text for the generated motion 336. The inferred descriptive text can then be provided as input to a discriminator 340 for comparison along with the input text 332. A trained discriminator 340 is used for comparison in this example because there may be many different ways to describe or indicate the same motion in text, and the discriminator infers the similarity between the input text and the inferred text. For example, “get up,” “stand up,” and “stand up” are all legitimate ways to represent the same general motion, and the discriminator 340 can be trained to generate scores based on similarity. If the generated motion 336 is accurate for the input text, then the text inferred from the motion-to-text generator 338 should be very similar to the input text in the context, even if expressed using different terminology. In at least one embodiment, the text-to-motion generator 334 can run in reverse to provide text to the motion generator 338.

[0035] Once the motion generator 366 has been adequately trained and / or fine-tuned, the motion generator 336 can be used to generate motions for a variety of different purposes, such as as part of system 360, for example... Figure 3C As shown. In this example, a user can provide text input 364 using client device 362, which can be provided to a trained motion generator 366. The user (or an application running on the client device, and other similar options) can also specify other information, such as a virtual object 374 to represent the motion, which may be selected from an asset repository 372 or other such sources. In other embodiments, default or generic frame or character representations can be used to generate the generated motion 368, for example, textures and / or shapes applied in subsequent processes. The generated motion 368 can then be provided to another client device 370 (or back to the same client device 362) or other such recipients for presentation, for example, as part of a game, animation, film, or virtual reality (VR) / augmented reality (AR) / augmented reality (ER) experience.

[0036] Such methods for training motion generators can help ensure alignment between input text and generated image and / or video content (or other such representations or data) across various types of motion. This not only helps ensure the correct motion is rendered but also that the representation is executed in an accurate and / or realistic manner. For example, if the input text indicates "punch," and the motion represents an outstretched hand, it might be inferred as a legitimate motion; however, if the motion is inferred to correspond to a "pointing" motion after being moved to the text model, it is unlikely to represent a realistic punch. Alternatively, a generated punch might not involve shoulder twisting or other expected related movements, which, while unrealistic, might be identified by the discriminator as not including all appropriate motions. The ability to use a guided discriminator allows for the reuse of a limited training dataset without generating additional training data, which can involve significant time and effort—for example, requiring one or more people to perform various movements using motion capture suits.

[0037] This approach also has the advantage that discriminators are easier to train accurately than generators. Therefore, a smaller dataset may be sufficient to train a discriminator, but not enough to train a generator without additional help or guidance. A discriminator can be trained to analyze the motion generated by the generative model for a given text string and provide an accurate indication or metric of similarity or correspondence. This accurate indication or metric can then be used as guidance to help train, update, or fine-tune the generative model using the same dataset, although additional or alternative training data may be used in other embodiments. As described, an example discriminator might generate a score of 100 for a perfect match between the input text string and the generated motion, and a score close to zero for a completely incorrect match or alignment, and this score can be used along with a reward function (or loss function) to train the generative model. In other approaches, incorrect matches may have negative scores, such as a score close to -100 for a nearly completely incorrect match, a score close to 0 for a partial match, and other such options. In at least some embodiments, the type of reward or penalty provided is not critical, as long as the network parameters are appropriately adjusted based on the match score, alignment value, or loss or reward derived from the score. In at least some embodiments, scores should be determined and used in such a manner as to increase the probability of generating motions with scores corresponding to correct and natural motions, and decrease the probability of generating motions with scores corresponding to incorrect (or other unnatural or undesirable) motions. Various reinforcement learning methods can be used in conjunction with these scores for training, as described and suggested herein. As an example, when using a diffusion model to guide the training of a generative model, advantage-weighted regression can be used, as the computation of the diffusion model may be particularly well-suited for such regression. On the other hand, for methods using discriminators, models such as text-to-motion retrieval (TMR) models (or other transformer-based synthetic models) may be beneficial, where both text and motion can be encoded as latent representations, and the dot product (or other function) of these latent representations can be computed to determine matching scores or other alignment values ​​for text and motion. In at least one embodiment, the TMR-based text-to-motion synthesis process may incorporate a contrastive loss to appropriately construct at least a cross-modal latent space. Such models may also include independent encoders for encoding both text and motion, where the encoded values ​​can be used in a similarity function to compare values ​​between the two different modalities. Other types of optimization and regression may also be used within the scope of various embodiments.

[0038] In at least some embodiments, a generative model can be trained to generate different types of motion for different types of characters, persons, organisms, or objects to be performed. In at least one embodiment, this can be achieved in part by providing additional, appropriately labeled instances of training data that describe the motion for a corresponding text input (or a combination of inputs including at least a certain amount of text input). For example, the text input might indicate “walk,” “walk slowly,” “walk fast,” “walk like a child,” or “walk like a monkey.” In some embodiments, the same text command “walk” might be provided, and this additional information can be provided using other inputs, such as style codes or asset indicators, and other such options. The underlying motion for each of these walking types can be different. For example, for both “walk slowly” and “walk fast” to appear realistic, they should differ in the motion used for walking, rather than simply in the speed of movement. In at least one embodiment, the training data may include different aspects or modifications of the same type of motion to generalize and enable the generation of these different motions in an accurate and realistic manner. Other types of modifiers or aspects can also be specified, such as "right punch" versus "left punch," "clockwise rotation" versus "counter-clockwise rotation," and so on. In some embodiments, the training data can also provide motion sequences, such as "right punch followed by a left hook," which would be a different motion sequence than performing a right punch, returning to a neutral position, and then performing a left hook as a separate motion. In some embodiments, the input can also specify motion rates, such as speed values, or instructions for "walking faster," etc. Generative models can be trained to produce any of these and other similar but different types of motion, for example, by using additional training data with potentially different reward functions.

[0039] In at least one embodiment, an image generated by a generative model (e.g., a motion diffusion model) can be compared with text input used to generate the motion represented in that image, for example, by using a comparator-based discriminator. Such a comparator can take various forms, such as a module capable of calculating a contrastive loss (or other perceptual realism measure) between samples generated by the diffusion model and samples corresponding to the input text (e.g., latent points). In some embodiments, this may include comparing embeddings (e.g., latent embeddings) for individual samples or instances. The determined loss value (in some embodiments, this loss value may be combined with loss values ​​for other loss terms in the loss function) can be returned to, for example, a training module or manager, which may determine, in part, new or updated network weights or parameters to be applied to the generative model based on the loss value to improve performance regarding motion generation in response to input text. In at least one embodiment, the loss function may include a term for fractional distillation sampling (SDS) loss, which is often used with the diffusion model to optimize the determined loss. Using losses such as SDS loss allows optimization of samples in an arbitrary parameter space (e.g., 3D space), where the process allows for differentiable mapping back to the image. In at least one embodiment, such a differentiable mapping can be defined using 3D scene parameterization. Backpropagation may first involve finding gradients for the generated motion representation, and SDS loss is one way to compute such gradients.

[0040] While optimizing the SDS loss alone can result in a reasonable scene appearance, in at least some embodiments, when using a neural renderer (e.g., NeRF), additional regularizers and optimization strategies can be used to improve the geometry of objects used to illustrate or otherwise represent motion. In at least one embodiment, the objects to be inserted can be explicit digital assets, which may include a 3D geometric mesh and textures projectable onto that mesh. Other types of objects can also be inserted into an image of the scene. This can include, for example, views, volumetric data representations, or other implicit representations of one or more objects. For example, such implicit representations can be generated by neural networks, such as fully connected Neural Radiation Field (NeRF) networks. Within the scope of various embodiments, there are various other ways that can be used to generate, serve, or render digital objects (or views of these objects). The trained neural renderer used herein can be consistent, with high-quality normals, surface geometry, and depth, and can be relit using, for example, a Lambertian shading model. In at least one embodiment, a lightmap or other lighting estimator can provide the neural renderer with lighting parameters or other information for applying consistent lighting effects to virtual objects to be displayed as motion.

[0041] When using diffusion models for image content generation, the models may get "stuck" in local minima in certain situations. To attempt to avoid such problems, the method proposed in this paper can use physically based rendering. This can include using ray tracing as part of the image rendering or forming process, where ray tracing is physically constrained. Additional considerations may include, for example, the dynamic characteristics of virtual objects to be inserted into the scene, and other such options. In some embodiments, the object does not have to be a virtual asset but can be generated entirely by an appropriate generative model. In at least one embodiment, a 3D model capable of performing path tracing on the scene can be used, where the object is inserted at a specified location in the scene and potentially viewed from one or more angles (including potentially novel views) while performing determined motion.

[0042] Figure 4A An example system 400 is illustrated for rendering images, video frames, or other image-related content according to at least one embodiment. Such systems may include or incorporate functionality as described herein to generate representations of motion performed by, for example, one or more virtual objects or assets. In this example, images will be rendered for a scene (or other view, portion, or region) in a virtual environment 400, although such systems may also be used to render images for semi-virtual or real environments. The virtual environment 400 may include geometry and other data representing shapes or objects in the environment, such as three-dimensional (3D) objects representing a scene occurring within the environment or to be included in a scene occurring in the environment, such as foreground objects (e.g., people or vehicles) or background objects (e.g., roads and buildings), and other such options. In at least some embodiments, at least some of the content to be inserted may be obtained from a source such as an asset repository 402 or other similar location, which may contain content (e.g., geometry, texture, and density data) that can be used to render one or more objects placed in a view of the scene. In at least some embodiments or instances, there may be a user device 404 running a content generation or management application that allows the user to select at least relevant portions of assets 402 and virtual environment 400 for rendering a composite image of the scene. User device 404 may also allow the user to control multiple aspects of the image to be rendered, such as the position or pose of objects in the scene, and the viewpoint and other parameters of the virtual camera used to render the image of virtual environment 400.

[0043] In this example, at least one computing resource 406 is used to perform rendering. This resource may correspond to one or more servers, for example, these servers may be located locally or span at least one network, and other such options. In some embodiments, rendering may instead be performed at least partially on user device 404. Computing resource 406 may acquire or receive data to be used for rendering, such as geometry, texture, and density data for virtual environments or assets, as well as information about the position and pose of these objects in the scene and parameters of a virtual camera to determine the view of the scene to be rendered. This information may be received by content application 408, which may, for example, execute on a central processing unit (CPU) 410 of the computing resource, which is responsible for tasks such as collecting data, rendering images, and performing any formatting or encoding on the resulting images, and other such options. Content applications may work in conjunction with rendering manager 412. For example, rendering manager 412 may be responsible for coordinating the operations of the rendering pipeline executed on computing resource 406, such as modules 414, 416, or processes responsible for tasks such as geometry-related tasks (including lighting and shading tasks) and rasterization, as well as other such tasks. In at least some embodiments, at least some of these rendering tasks may be executed using one or more GPUs 420A-D of computing resources and one or more processors or computing instances (physical or virtual) of one or more other computing resources. These tasks may use data stored in image database 422 or store rendered images in such image database 422, and provide rendered image content for presentation via at least one user device and / or display device 424.

[0044] Tasks such as optical transport simulations (e.g., ray tracing, path tracing, ray stepping, etc.) or volume sampling can be performed using a single processor (such as a single GPU) or can have operations distributed across multiple GPUs 420A-420D. In this example, a pool or set of GPUs 420A-420D may exist, and the resource manager 418 may be at least partially responsible for allocating GPUs to perform processing of operations. If using more than one GPU is desired or beneficial, the resource manager 418 may allocate one or more GPUs with appropriate capacity or capability. This may include the number of GPUs indicated in the allocation request, or determining the number of GPUs to be allocated in part based on that request. In some embodiments, the resource manager may also be able to monitor available bandwidth or memory to determine which and how many GPUs to allocate, such as in cases with high bandwidth capacity where operations can be distributed across a larger number of GPUs, where the impact of forwarding ray information on bandwidth is less severe, whereas a bandwidth-constrained system may cause the resource manager to attempt to allocate as few GPUs as possible to try to reduce the number of forwarded messages required.

[0045] In at least one embodiment, for example, data partitioning can be performed by the rendering manager 412, and assigning data to different processors can be performed by the system's resource manager 418. The resource manager can receive information from the rendering component and can select an appropriate processor from the pool of available processors 420 or processor capacity. In some embodiments, the rendering application can choose the partitioning, while in other embodiments the renderer may not have control over data partitioning, which can be handled by a separate management component (…). Figure 4A (Not shown in the image) to complete.

[0046] Figure 4B An example image generation pipeline 450 is shown, which can be used in system 400 (e.g., Figure 4AThe system illustrated is used to render one or more images (e.g., video frames) in a sequence. In this example, the pixel data 452 of the current frame to be rendered (which may include G-buffer data for the main surface) can be received as input to the reflection and refraction component 454 of the rendering system. The reflection and refraction component 454 can use this data to attempt to determine any determined reflection and / or refraction data in the pixel data and provide this data to the backprojection and G-buffer patching component 456, which can perform backpropagation as discussed herein to locate corresponding points for these reflections and refractions and use the data to patch the G-buffer 468, which can provide updated input for subsequent frames to be rendered. The data may then be provided to the light sample generation component 458 to perform light sampling, to the ray tracing lighting component 460 to perform ray tracing lighting, and to one or more shaders 462, which can set the pixel colors of various pixels in the frame based at least in part on determined lighting information (and other information such as color, texture, etc.). The results can be accumulated by the accumulation module 464 or components to generate an output frame 466 of the desired size, resolution, or format.

[0047] In at least one embodiment, shader 458 can perform a backprojection step. Once the backprojection pass is complete and the gradient surface parameters have been patched into the current G-buffer, the renderer can perform a lighting pass. Using information from the lighting pass and lighting results from previous frames, gradients can be computed, then filtered and used for history rejection. This approach can be used to compute robust temporal gradients between the current and previous frames in the temporal denoising unit of a ray-tracing renderer. This backprojection-based approach can also work with reflection and refraction and can work with rasterized G-buffers. Previous methods for backprojection omitted any G-buffer patching and instead relied on the original current G-buffer samples, which also led to false positive gradients. Patching the surface parameters can eliminate false positives in most cases, making the denoised image very stable while still responding quickly to lighting changes. Once the backprojection pass is complete and the gradient surface parameters have been patched into the current G-buffer, the renderer can perform a lighting pass. Using information from the lighting pass and lighting results from previous frames, gradients are computed, then filtered and used for history rejection. See reference... Figures 3A-3C The relighting and compositing of NeRF objects and non-NeRF objects discussed herein can be placed at various locations in such pipelines, such as before or after performing ray tracing lighting 460, or as part of the accumulation process 464, as well as other options discussed or suggested herein.

[0048] Figure 5AA first example process 500 for training or fine-tuning a generative model to generate motion from text (or similar input) is shown, which can be performed according to at least one embodiment. It should be understood that, for this and other processes described herein, unless explicitly stated otherwise, additional, fewer, or alternative steps may be performed, or there may be a similar or alternative order, or at least partially parallel execution, within the scope of various embodiments. Furthermore, although this example will be discussed with respect to diffusion models and text-to-motion models, other types of models (or networks), or other types of content generated, may be used within the scope of various embodiments. In this example, training of the generative model 502 is initiated, for example, by selecting an appropriate model to train (or further train or fine-tune) (e.g., a motion diffusion model) using a selected training dataset. In this example, the training data may include instances of labeled image content, such as video clips or image sequences, which include representations of a particular type of motion, wherein the labels may include one or more text labels (e.g., different text labels describing the same represented motion, such as "fast walk" and "power walk").

[0049] During training, text (or text acquired, identified, or selected in other ways) can be received for each of several training iterations, wherein in at least one embodiment, the text may correspond to labels from the training dataset (or labels from other training data previously used to train the generative model). The text can be provided as input to the generative model, either as text or in an encoded form, among other such options. Then, generated image content can be received as output to the generative model, wherein the image content may include a generated representation of motion indicated by the input text, at least to the extent that the generative model understands it. In this example, if the encoding of the input text and image content (e.g., feature vectors or points in the latent space) is not yet available, encoding of the input text and image content (e.g., feature vectors or points in the latent space) can be generated, at least ... The encoding can be generated using one or more dedicated encoders, or it can be generated using a portion of the same model or network used to perform discrimination (e.g., a motion embedding network that may be part of the discriminator model), among other such options. In this example, a discriminator (e.g., a CLIP-based discriminator) can be used to analyze the 512 (i.e., compare or contrast) text and image encodings to determine a matching score (or other such measure or metric of the quality / alignment of the generated motion representation relative to the input text). In at least one embodiment, this can be generated by performing a dot product on the text and image / motion embeddings (or, for example, performing distance calculations in an n-dimensional latent space) to produce a metric of similarity or difference. The matching score can be used in a loss function to determine the loss value to be provided to the training module or manager via backpropagation; for example, the training module or manager can adjust one or more parameters of the 514 generative model in part based on the matching score and / or the loss value. As described, the loss function used to determine the loss value can include one or more terms for the quality of image content generated by the generative model using ground truth data from the training set. The training process 500 can continue until at least one training termination criterion 516 is met, such as network convergence, reaching the maximum number of training iterations, or using all training data. If such termination criteria are not met, the process can continue for the next text input. If such criteria are met, the training process can be completed or terminated, and a trained generative model 518 can be provided to generate motion representations at least in part based on the text input and / or other relevant inputs.As described, such processes can use reinforcement learning to fine-tune the motion diffusion model for a specific target (e.g., text-to-motion alignment).

[0050] Figure 5BA second example process 530, which can be performed according to at least one embodiment, is illustrated for training, updating, or fine-tuning a generative model to generate motion from text (or similar input). In this example, training of the generative model (e.g., a text-to-motion diffusion model) is initiated, for example by selecting a suitable model and training dataset. In one or more (e.g., each time) of several training iterations, text indicating at least one type of motion may be received 534 (or otherwise acquired, identified, or selected). This text may be provided as input to the generative model (e.g., text or encoded form) 536. Then, generated image content may be received 538 as output of the generative model, wherein the image content may include a representation of the generated motion indicated by the input text, at least to the extent that the generative model understands. In this example, a text descriptor 540 corresponding to the motion represented in the generated image content may be generated. This may include, for example, using a motion-to-text model or running the generative model in reverse, and other such options. If the generated motion is an accurate representation of the input text, then the text descriptor should at least match the input text in context, or describe the same type of motion as the input text. A discriminator can be used to compare (or contrast) text input and text descriptors to determine a matching score (or other similarity, dissimilarity, or alignment metric). In some embodiments, encodings can be generated for the text input and text descriptors first, and these encodings (e.g., feature vectors or latent embeddings) can be used for comparison, as described elsewhere in this document. In at least one embodiment, this can be generated by performing a dot product (or, for example, distance calculation in an n-dimensional latent space) on the text and image / motion embeddings to generate a measure of similarity or dissimilarity. The matching score can be used in a loss function to determine the loss value to be provided to the training module or manager via backpropagation; for example, the training module or manager can adjust one or more parameters of the generative model in part based on the matching score and / or the loss value. As described, the loss function used to determine the loss value can include one or more terms for the quality of image content generated by the generative model using ground truth data from the training set. This training process 530 can continue until it is determined 546 that at least one training termination criterion is met. If such a termination criterion is not met, the process can continue for the next text input. If this criterion is met, the training process can be completed or terminated, and 548 trained generative models can be provided to generate motion representations at least in part based on text input and / or other relevant inputs. As described, this process can use reinforcement learning to fine-tune the motion diffusion model for a specific objective (e.g., text-to-motion alignment).

[0051] Figure 5CAn example process 560 for generating image content containing motion representations, which can be performed according to at least one embodiment, is shown. In this example, receiving 562 indicates text indicating the motion to be presented. For example, this could include text input provided by a user via a client device, indicating the type of motion a character in the generated animated content is to perform. This text may potentially be provided as input 564 to a trained generative model, such as a trained motion diffusion model, along with other textual and / or non-textual instructions. As described, in at least one embodiment, the generative model may have been fine-tuned using a discriminator and reinforcement learning, for example, referencing... Figure 5A and / or Figure 5B As described, 566 image contents (or other such data that can be used to generate visual representations) can be received as the output of a generative model, wherein the image contents may include a generated representation of the indicated motion. Multiple aspects of the motion, such as velocity or direction, may be included in the representation, as discussed elsewhere herein. 568 generated image contents can then be provided in response to received text.

[0052] In at least one embodiment, the generated content is not necessarily image content, but may include (or correspond to) different types of motion representations. For example, the generated content may include deformation or manipulation of line models or geometries, which may be textured or shading applied during the rendering process. The generated representation may also be 2D, 3D, or other dimensions, and may be used for various operations, including but not limited to operations related to games, animation, simulation, autonomous navigation, or virtual reality (VR) / augmented reality (AR) / augmented reality (ER) applications, and other such options.

[0053] Several aspects of the various methods proposed herein can be lightweight enough to be executed in real time at various locations, such as on devices (e.g., client devices including personal computers or game consoles). This processing can be performed on content generated on the client device, content received by the client device, or content received from an external source, or such processing can be performed on content generated on the client device, content received by the client device, or content received from an external source, such as streaming data or other content received via at least one network from a cloud server 620 or a third-party service 660, and other such options. In some cases, at least a portion of the processing, generation, synthesis, 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 another such recipient) for presentation or another such purpose.

[0054] 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, client device 602 can use components of content application 604 on client device 602 and data locally stored on the client device to generate or receive data for a session. In at least one embodiment, content application 624 executing on server 620 (e.g., cloud server or edge server) can initiate a session associated with at least one client device 602 (e.g., utilizing a session manager and user data stored in user database 636), and content manager 626 can determine content from asset repository 634, such as one or more digital assets (e.g., implicit and / or explicit object representations). Content manager 626 can work in conjunction with rendering module 628 to generate or select objects, digital assets, or other such content to be placed in a scene or other virtual environment. Views of these objects can be rendered by rendering module 628, for example, by interpolation into an input scene image, and provided for presentation via client device 602. In at least one embodiment, the rendering module 628 may work in conjunction with the content generator 630 to achieve a representation to be applied to one or more objects or assets. As described, the training module 632 or manager may train the content generator 630 to accurately infer motion representations based on, for example, text input. At least a portion of the rendered content may be transmitted to the client device 602 using a suitable transmission manager 622 for delivery via download, streaming, or another such transmission channel. An encoder may be used to encode and / or compress at least some of the data before transmission to the client device 602. In at least one embodiment, the client device 602 receiving such content may provide the content to a corresponding content application 604, which may also or alternatively include a graphical user interface 610, a content manager 612, and a rendering module 614 for providing, compositing, rendering, combining, modifying, or using the content to be presented on or by the client device 602 (or for other purposes). The decoder can also be used to decode data received via one or more networks 640 for presentation via client device 602, such as presenting image or video content via display 606, and presenting audio (such as sound and music) via at least one audio playback device 608 (such as a speaker or headphones). In at least one embodiment, at least some of the content may already be stored on, rendered on, or accessible to client device 602, such that at least that portion of the content does not need to be transmitted via network 640, such as in cases where the content may have been previously downloaded or stored locally on a hard drive or optical disc.In at least one embodiment, a transport mechanism (such as data streaming) may be used to transfer the content from server 620 or user database 636 to 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 (such as third-party service 660 or other client device 650), which may also include a content application 662 for generating, enhancing, or providing the content. In at least one embodiment, multiple computing devices or multiple processors within one or more computing devices (such as a combination of multiple CPUs and multiple GPUs) may be used to perform multiple portions of this function.

[0055] In this example, these client devices can include any suitable computing device, such as desktop computers, laptops, set-top boxes, streaming devices, game consoles, smartphones, tablets, VR headsets, AR goggles, wearable computers, or smart TVs. Each client device can submit requests via at least one wired or wireless network, which can include the Internet, Ethernet, a local area network (LAN), or a cellular network, among other such options. In this example, these requests can be submitted to an address associated with a cloud provider that operates or controls one or more electronic resources within a cloud provider environment, such as a data center or server cluster. In at least one embodiment, the request can be received or processed by at least one edge server located at the network edge and outside at least one security layer associated with the cloud provider environment. In this way, latency can be reduced by enabling client devices to interact with servers in closer proximity, while also improving the security of resources within the cloud provider environment.

[0056] 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 providing image or video content to test or validate autonomous machine applications, or for performing deep learning operations. In at least one embodiment, such a system can be implemented using edge devices, or can be combined with one or more virtual machines (VMs). In at least one embodiment, such a system can be implemented at least partially in a data center or at least partially using cloud computing resources.

[0057] Reasoning and training logic

[0058] Figure 7A Inference and / or training logic 715 is shown for performing inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Provide details about reasoning and / or training logic 715.

[0059] In at least one embodiment, inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701 for storing forward and / or output weights and / or input / output data, and / or other parameters configuring neurons or layers of a neural network trained for and / or used for inference in one or more embodiments. In at least one embodiment, training logic 715 may include or be coupled to code and / or data storage 701 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic, including integer and / or floating-point units (collectively, arithmetic logic units (ALUs)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, code and / or data storage 701 stores weight parameters and / or input / output data of each layer of a neural network trained or used in one or more embodiments during forward propagation of input / output data and / or weight parameters during training and / or inference using one or more embodiments. In at least one embodiment, any portion of the code and / or data storage 701 may be included within other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0060] In at least one embodiment, any portion of the code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 701 may be a cache memory, dynamic random access memory (“DRAM”), static random access memory (“SRAM”), non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether the code and / or data storage 701 is internal or external to the processor, for example, or composed of DRAM, SRAM, flash memory, or some other storage type, may depend on the available on-chip or off-chip storage space, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in the inference and / or training of the neural network, or some combination of these factors.

[0061] In at least one embodiment, inference and / or training logic 715 may include, but is not limited to, code and / or data storage 705 for storing backpropagation and / or output weights and / or input / output data corresponding to neurons or layers of a neural network trained and / or used for inference in one or more embodiments. In at least one embodiment, during training and / or inference using one or more embodiments, code and / or data storage 705 stores weight parameters and / or input / output data for each layer of a neural network trained or used in one or more embodiments during backpropagation of input / output data and / or weight parameters. In at least one embodiment, training logic 715 may include or be coupled to code and / or data storage 705 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic including integer and / or floating-point units (collectively, an arithmetic logic unit (ALU)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of the code and / or data storage 705 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. In at least one embodiment, any portion of the code and / or data storage 705 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 705 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice between the code and / or data storage 705 being internal or external to the processor, for example, whether it consists of DRAM, SRAM, flash memory, or some other type of storage, depends on whether the available storage is on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the data batch size used in the inference and / or training of the neural network, or some combination of these factors.

[0062] In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be separate storage structures. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be the same storage structure. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be partially identical and partially separate storage structures. In at least one embodiment, any portion of code and / or data storage 701 and code and / or data storage 705 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0063] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, one or more arithmetic logic units (“ALUs”) 710 (including integer and / or floating-point units) for performing logical and / or mathematical operations at least in part based on or instructed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from layers or neurons within a neural network) stored in activation storage 720, which are functions of input / output and / or weight parameter data stored in code and / or data storage 701 and / or code and / or data storage 705. In at least one embodiment, activation is activated in response to execution instructions or other code, and linear algebraic and / or matrix-based mathematical generation performed by ALU 710 is stored in activation storage 720, wherein weight values ​​stored in code and / or data storage 705 and / or code and / or data storage 701 are used as operands with other values, such as bias values, gradient information, momentum values, or other parameters or hyperparameters, and any or all of these can be stored in code and / or data storage 705 or code and / or data storage 701 or other on-chip or off-chip storage.

[0064] In at least one embodiment, one or more processors or other hardware logic devices or circuits include one or more ALUs 710, while in another embodiment, one or more ALUs 710 may be located outside the processor or other hardware logic device or the circuitry using 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 the execution unit of the processor, which may be within the same processor or distributed among different processors of different types (e.g., a central processing unit, a graphics processing unit, a fixed-function unit, etc.). In at least one embodiment, code and / or data storage 701, code and / or data storage 705, and activation storage 720 may be on the same processor or other hardware logic device or circuitry, while in another embodiment, they may be on different processors or other hardware logic devices or circuitries, or in some combination of the same and different processors or other hardware logic devices or circuitries. In at least one embodiment, any portion of activation storage 720 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Furthermore, inference and / or training code may be stored together with other code accessible to the processor or other hardware logic or circuitry, and may be retrieved and / or processed using the processor’s fetch, decode, schedule, execute, exit, and / or other logic circuitry.

[0065] In at least one embodiment, the active memory 720 may be a cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other memory. In at least one embodiment, the active memory 720 may be wholly or partially located inside or outside one or more processors or other logic circuits. In at least one embodiment, the choice of whether the active memory 720 is internal to or external to the processor may depend on the available on-chip or off-chip storage, the latency requirements for training and / or inference functions, the batch size of data used in inference and / or training the neural network, or some combination of these factors. For example, it may include DRAM, SRAM, flash memory, or other memory types. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (“ASIC”), such as those from Google. Processing unit, from Graphcore TM Inference processing unit (IPU) or from Intel Corp. (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as field programmable gate array (“FPGA”)

[0066] Figure 7B Inference and / or training logic 715 according to at least one or more embodiments is illustrated. In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, hardware logic, wherein computational resources are dedicated or otherwise uniquely used in conjunction with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (ASIC), such as those from Google. Processing unit, from Graphcore TM Inference processing unit (IPU) or from Intel Corp. (e.g., "LakeCrest") processor. In at least one embodiment, Figure 7BThe inference and / or training logic 715 shown can be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware (e.g., field-programmable gate array (FPGA)). In at least one embodiment, the inference and / or training logic 715 includes, but is not limited to, code and / or data storage 701 and code and / or data storage 705, which can be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, momentum values, and / or other parameter or hyperparameter information. Figure 7B In at least one embodiment shown, each of code and / or data storage 701 and code and / or data storage 705 is associated with dedicated computing resources (e.g., computing hardware 702 and computing hardware 706), respectively. In at least one embodiment, each of computing hardware 702 and computing hardware 706 includes one or more ALUs that perform mathematical functions (e.g., linear algebraic functions) only on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of the function execution are stored in activation storage 720.

[0067] In at least one embodiment, each of the code and / or data storage 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activation obtained from one “store / computation pair 701 / 702” of the code and / or data storage 701 and computing hardware 702 provides input as input to the next “store / computation pair 705 / 706” of the code and / or data storage 705 and computing hardware 706, in order to reflect the conceptual organization of the neural network. In at least one embodiment, each store / computation pair 701 / 702 and 705 / 706 may correspond to more than one neural network layer. In at least one embodiment, additional store / computation pairs (not shown) may be included in the inference and / or training logic 715 after or in parallel with the store / computation pairs 701 / 702 and 705 / 706.

[0068] Data Center

[0069] Figure 8 An example data center 800 that can be used with at least one embodiment is shown. In at least one embodiment, the data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0070] In at least one embodiment, such as Figure 8As shown, the data center infrastructure layer 810 may include a resource coordinator 812, grouped computing resources 814, and node computing resources (“nodes CR”) 816(1)-816(N), where “N” represents any positive integer. In at least one embodiment, nodes CR 816(1)-816(N) may include, but are not limited to, any number of central processing units (“CPUs”) or other processors (including accelerators, field-programmable gate arrays (FPGAs), graphics processors, etc.), memory devices (e.g., dynamic read-only memory), storage devices (e.g., solid-state drives or disk drives), network input / output (“NWI / O”) devices, network switches, virtual machines (“VMs”), power modules, and cooling modules, etc. In at least one embodiment, one or more nodes CR 816(1)-816(N) may be servers having one or more of the aforementioned computing resources.

[0071] In at least one embodiment, the grouped computing resources 814 may include individual groups (not shown) of node CRs housed in one or more racks, or a plurality of racks (also not shown) housed in data centers in various geographic locations. Individual groups of node CRs within the grouped computing resources 814 may include computing, networking, memory, or storage resources that can be configured or allocated to support groups of one or more workloads. In at least one embodiment, several node CRs, including CPUs or processors, may be grouped within one or more racks to provide computing resources to support one or more workloads. In at least one embodiment, the one or more racks may also include any number of power modules, cooling modules, and network switches, in any combination.

[0072] In at least one embodiment, resource coordinator 812 may configure or otherwise control one or more nodes CR816(1)-816(N) and / or grouped computing resources 814. In at least one embodiment, resource coordinator 812 may include a Software Design Infrastructure (“SDI”) management entity for data center 800. In at least one embodiment, resource coordinator 108 may include hardware, software, or some combination thereof.

[0073] In at least one embodiment, such as Figure 8As shown, framework layer 820 includes a job scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, framework layer 820 may include a framework of software 832 supporting software layer 830 and / or one or more applications 842 supporting application layer 840. In at least one embodiment, software 832 or application 842 may respectively include web-based service software or applications, such as services or applications provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, framework layer 820 may be, but is not limited to, a free and open-source software web application framework, such as Apache Spark™ (hereinafter referred to as "Spark") which can leverage distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, job scheduler 832 may include Spark drivers to facilitate the scheduling of workloads supported by the various layers of data center 800. In at least one embodiment, configuration manager 824 may be able to configure different layers, such as software layer 830 and framework layer 820 including Spark and distributed file system 828 for supporting large-scale data processing. In at least one embodiment, resource manager 826 is capable of managing cluster or group computing resources mapped to or allocated to support distributed file system 828 and job scheduler 822. In at least one embodiment, cluster or group computing resources may include group computing resources 814 on data center infrastructure layer 810. In at least one embodiment, resource manager 826 may coordinate with resource coordinator 812 to manage these mapped or allocated computing resources.

[0074] In at least one embodiment, the software 832 included in the software layer 830 may include software used by at least a portion of the nodes CR816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of software may include, but are not limited to, Internet web page search software, email virus scanning software, database software, and streaming video content software.

[0075] In at least one embodiment, the application layer 840 may include one or more applications 842 that can be used by at least a portion of nodes CR816(1)-816(N), grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. The one or more types of applications may include, but are not limited to, any number of genomics applications, cognitive computing and machine learning applications, including training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in conjunction with one or more embodiments.

[0076] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can perform any number and type of self-modification actions based on any amount and type of data acquired in any technically feasible manner. In at least one embodiment, self-modification actions can mitigate potentially poor configuration decisions by data center operators of data center 800 and can prevent underutilization and / or poor performance of the data center.

[0077] In at least one embodiment, data center 800 may include tools, services, software, or other resources to train one or more machine learning models or to use one or more machine learning models to predict or infer information according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model can be trained by calculating weight parameters based on a neural network architecture using the software and computing resources described above with respect to data center 800. In at least one embodiment, information can be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to data center 800 by using weight parameters calculated through one or more training techniques described herein.

[0078] In at least one embodiment, the data center may use a CPU, application-specific integrated circuit (ASIC), GPU, FPGA, or other hardware to utilize the aforementioned resources to perform training and / or inference. Furthermore, one or more of the aforementioned software and / or hardware resources may be configured as a service to allow a user to train or perform information inference, such as image recognition, speech recognition, or other artificial intelligence services.

[0079] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7BDetails are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be implemented in the system. Figure 8 Used in systems for reasoning or predicting operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0080] Such components can be used to render different types of objects, determine consistent secondary lighting effects for these objects, and then use these secondary lighting effects to composite the objects to generate a composite image.

[0081] Computer System

[0082] Figure 9 This is a block diagram illustrating an exemplary computer system according to at least one embodiment. The exemplary computer system may be a system of interconnected devices and components, a system-on-a-chip (SoC), or some combination thereof formed with a processor, which may include an execution unit to execute instructions. In at least one embodiment, according to this disclosure, such as the embodiments described herein, computer system 900 may include, but is not limited to, components such as processor 902, whose execution unit includes logic to execute algorithms for process data. In at least one embodiment, computer system 900 may include a processor, such as those available from Intel Corporation of Santa Clara, California. Processor family, Xeon™ XScale™ and / or StrongARM™ Core TM or Nervana TM A microprocessor may be used, although other systems (including PCs, engineering workstations, set-top boxes, etc.) with other microprocessors may also be used. In at least one embodiment, computer system 900 may execute a version of the Windows operating system available from Microsoft Corporation of Redmond, Washington, although other operating systems (such as UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0083] The embodiments can be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol (IP) devices, digital cameras, personal digital assistants (“PDAs”), and handheld PCs. In at least one embodiment, the embedded application may include a microcontroller, a digital signal processor (“DSP”), a system-on-a-chip (SoC), a network computer (“NetPC”), a set-top box, a network hub, a wide area network (“WAN”) switch, or any other system that can execute one or more instructions according to at least one embodiment.

[0084] In at least one embodiment, the computer system 900 may include, but is not limited to, a processor 902, which may include, but is not limited to, one or more execution units 908, to perform machine learning model training and / or inference according to the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, but in another embodiment, the computer system 900 may be a multiprocessor system. In at least one embodiment, the processor 902 may include, but is not limited to, a Complex Instruction Set Computing (“CISC”) microprocessor, a Reduced Instruction Set Computing (“RISC”) microprocessor, a Very Long Instruction Word (“VLIW”) microprocessor, a processor implementing instruction set combination, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which can transmit data signals between the processor 902 and other components in the computer system 900.

[0085] In at least one embodiment, processor 902 may include, but is not limited to, a Level 1 (“L1”) internal cache memory (“cache”) 904. In at least one embodiment, processor 902 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory may reside external to processor 902. Depending on specific implementation and requirements, other embodiments may also include a combination of internal and external caches. In at least one embodiment, register file 906 may store different types of data in various registers, including but not limited to integer registers, floating-point registers, status registers, and instruction pointer registers.

[0086] In at least one embodiment, a logic execution unit 908, including but not limited to performing integer and floating-point operations, is also located within the processor 902. In at least one embodiment, the processor 902 may further include a microcode (“ucode”) read-only memory (“ROM”) for storing microcode of certain macro instructions. In at least one embodiment, the execution unit 908 may include logic for processing a packaged instruction set 909. In at least one embodiment, by including the packaged instruction set 909 in the instruction set of a general-purpose processor, along with the associated circuitry for executing the instructions, the packaged data in the processor 902 can be used to perform operations used by numerous multimedia applications. In one or more embodiments, the execution of numerous multimedia applications can be accelerated and performed more efficiently by using the full width of the processor’s data bus to perform operations on the packaged data, which may eliminate the need to transfer smaller data units on the processor’s data bus to perform one or more operations on one data element at a time.

[0087] In at least one embodiment, the execution unit 908 may also be used in a microcontroller, embedded processor, graphics device, DSP, and other types of logic circuitry. In at least one embodiment, the computer system 900 may include, but is not limited to, memory 920. In at least one embodiment, memory 920 may be implemented as a dynamic random access memory (“DRAM”) device, a static random access memory (“SRAM”) device, a flash memory device, or other storage device. In at least one embodiment, memory 920 may store instructions 919 and / or data 921 represented by data signals that can be executed by processor 902.

[0088] In at least one embodiment, the system logic chip may be coupled to the processor bus 910 and the memory 920. In at least one embodiment, the system logic chip may include, but is not limited to, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage, as well as for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 may initiate data signals between the processor 902, the memory 920, and other components in the computer system 900, and bridge data signals between the processor bus 910, the memory 920, and the system I / O 922. In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 may be coupled to the memory 920 via the high-bandwidth memory path 918, and the graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port (“AGP”) interconnect 914.

[0089] In at least one embodiment, computer system 900 may use system I / O 922, which is a proprietary hub interface bus, to couple MCH 916 to I / O controller hub (“ICH”) 930. In at least one embodiment, ICH 930 may provide direct connectivity to certain I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, but is not limited to, a high-speed I / O bus for connecting peripheral devices to memory 920, chipset, and processor 902. Examples may include, but are not limited to, audio controller 929, firmware hub (“FlashBIOS”) 928, wireless transceiver 926, data storage 924, a conventional I / O controller 923 including user input and keyboard interfaces, serial expansion port 927 (e.g., a Universal Serial Bus (USB) port), and network controller 934. Data storage 924 may include hard disk drives, floppy disk drives, CD-ROM devices, flash memory devices, or other mass storage devices.

[0090] In at least one embodiment, Figure 9 A system including interconnected hardware devices or "chips" is shown, while in other embodiments, Figure 9An exemplary system-on-a-chip (SoC) may be illustrated. In at least one embodiment, the device may be interconnected with a proprietary interconnect, a standardized interconnect (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of the computer system 900 are interconnected using a compute fast link (CXL) interconnect.

[0091] The inference and / or training logic 715 is used to perform inference and / or training operations related to one or more embodiments. (The following is in conjunction with...) Figure 7A and / or Figure 7B Details are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be... Figure 9 Used in systems for reasoning or predicting operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0092] Such components can be used to render different types of objects, determine consistent secondary lighting effects for these objects, and then use these secondary lighting effects to composite the objects to generate a composite image.

[0093] Figure 10 This 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 laptop computer, tower server, rack server, blade server, desktop computer, tablet computer, mobile device, telephone, embedded computer, or any other suitable electronic device.

[0094] In at least one embodiment, the electronic device 1000 may, but is not limited to, a processor 1010 communicatively coupled to any suitable number or type of components, peripherals, modules, or devices. In at least one embodiment, the processor 1010 uses a bus or interface coupling, such as an I2C 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 accessory (“SATA”) bus, a universal serial bus (“USB”) (versions 1, 2, and 3), or a universal asynchronous receiver / transmitter (“UART”) bus. In at least one embodiment, Figure 10 The system shown includes interconnected hardware devices or "chips," while in other embodiments, Figure 10 An exemplary system-on-a-chip (SoC) can be illustrated. In at least one embodiment, Figure 10 The device shown can be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, Figure 10One or more components are interconnected using Computational Fast Link (CXL) interconnects.

[0095] In at least one embodiment, Figure 10 It may include a display 1024, a touch screen 1025, a touchpad 1030, a near field communication unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, a fast chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash (“BIOS, FWFlash”) 1022, a DSP 1060, a drive 1020 (e.g., a solid-state drive (“SSD”) or a hard disk drive (“HDD”)), a wireless local area network unit (“WLAN”) 1050, a Bluetooth unit 1052, a wireless wide area network unit (“WWAN”) 1056, a global positioning system (GPS) 1055, a camera (“USB 3.0 camera”) 1054 (e.g., a USB 3.0 camera) and / or a low-power double data rate (“LPDDR”) memory unit (“LPDDR3”) 1015 implemented in, for example, the LPDDR3 standard. These components can each be implemented in any suitable way.

[0096] In at least one embodiment, other components may be communicatively coupled to processor 1010 via the components described above. In at least one embodiment, accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to sensor hub 1040. In at least one embodiment, thermal sensor 1039, fan 1037, keyboard 1036, and touchpad 1030 may be communicatively coupled to EC 1035. In at least one embodiment, speaker 1063, earphone 1064, and microphone (“mic”) 1065 may be communicatively coupled to audio unit (“audio codec and Class D amplifier”) 1062, which in turn may be communicatively coupled to DSP 1060. In at least one embodiment, audio unit 1062 may include, for example, but not limited to, audio encoder / decoder (“codec”) and Class D amplifier. In at least one embodiment, SIM card (“SIM”) 1057 may be communicatively coupled to WWAN unit 1056. In at least one embodiment, components such as WLAN unit 1050, Bluetooth unit 1052, and WWAN unit 1056 can be implemented as next-generation form factor (NGFF).

[0097] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7BDetails are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be... Figure 10 The system is used to infer or predict operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0098] Such components can be used to render different types of objects, determine consistent secondary lighting effects for these objects, and then use these secondary lighting effects to composite the objects to generate a composite image.

[0099] Figure 11 This is a block diagram of a processing system according to at least one embodiment. In at least one embodiment, system 1100 includes one or more processors 1102 and one or more graphics processors 1108, and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a large number of processors 1102 or processor cores 1107. In at least one embodiment, system 1100 is a processing platform incorporated within a system-on-a-chip (SoC) integrated circuit for use in mobile, handheld, or embedded devices.

[0100] In at least one embodiment, system 1100 may include or be integrated into a server-based gaming platform, including a game console, mobile game console, handheld game console, or online game console, which are game and media consoles. In at least one embodiment, system 1100 is a mobile phone, smartphone, tablet computing device, or mobile internet device. In at least one embodiment, processing system 1100 may also include components coupled to or integrated into a wearable device, such as a smartwatch, smart glasses, augmented reality, or virtual reality device. In at least one embodiment, processing system 1100 is a television or set-top box device having one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0101] In at least one embodiment, one or more processors 1102 each include one or more processor cores 1107 for processing instructions that, when executed, perform operations against the system and user software. In at least one embodiment, each of the one or more processor cores 1107 is configured to process a specific instruction set 1109. In at least one embodiment, the instruction set 1109 may facilitate Complex Instruction Set Computing (CISC), Reduced Instruction Set Computing (RISC), or computation via Very Long Instruction Word (VLIW). In at least one embodiment, the processor cores 1107 may each process different instruction sets 1109, which may include instructions that facilitate the emulation of other instruction sets. In at least one embodiment, the processor cores 1107 may also include other processing devices, such as digital signal processors (DSPs).

[0102] In at least one embodiment, processor 1102 includes cache memory 1104. In at least one embodiment, processor 1102 may have a single internal cache or multiple levels of internal caches. In at least one embodiment, the cache memory is shared among various components of processor 1102. In at least one embodiment, processor 1102 also uses an external cache (e.g., a Level 3 (L3) cache or a last-level cache (LLC)) (not shown), which can be shared among processor cores 1107 using known cache coherence techniques. In at least one embodiment, processor 1102 further includes a register file 1106, which may include different types of registers for storing different types of data (e.g., integer registers, floating-point registers, status registers, and instruction pointer registers). In at least one embodiment, register file 1106 may include general-purpose registers or other registers.

[0103] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 to transmit communication signals, such as address, data, or control signals, between the processors 1102 and other components in the system 1100. In at least one embodiment, the interface bus 1110 may be a processor bus, such as a version of the Direct Media Interface (DMI) bus. In at least one embodiment, the interface bus 1110 is not limited to the DMI bus and may include one or more peripheral component interconnect buses (e.g., PCI, PCI Express), memory buses, or other types of interface buses. In at least one embodiment, the processor 1102 includes an integrated memory controller 1116 and a platform controller hub 1130. In at least one embodiment, the memory controller 1116 facilitates communication between memory devices and other components of the processing system 1100, while the platform controller hub (PCH) 1130 provides connectivity to I / O devices via a local I / O bus.

[0104] In at least one embodiment, memory device 1120 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase-change memory device, or a device with suitable performance for use as processor memory. In at least one embodiment, memory device 1120 may be used as system memory of processing system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process. In at least one embodiment, memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 of processor 1102 to perform graphics and media operations. In at least one embodiment, display device 1111 may be connected to processor 1102. In at least one embodiment, display device 1111 may include one or more internal display devices, such as in mobile electronic devices or laptop devices, or external display devices connected via a display interface (e.g., DisplayPort). In at least one embodiment, the display device 1111 may include a head-mounted display (HMD), such as a stereoscopic display device for virtual reality (VR) or augmented reality (AR) applications.

[0105] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to connect to the storage device 1120 and the processor 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripheral devices include, but are not limited to, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, a touch sensor 1125, and a data storage device 1124 (e.g., a hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 may be connected via a storage interface (e.g., SATA) or via a peripheral bus, such as a peripheral component interconnect bus (e.g., PCI, PCIe). In at least one embodiment, the touch sensor 1125 may include a touchscreen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 may be a Wi-Fi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or LTE transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and may be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, network controller 1134 may enable network connectivity to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to interface bus 1110. In at least one embodiment, audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, processing system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to system 1100. In at least one embodiment, platform controller hub 1130 may also be connected to one or more Universal Serial Bus (USB) controllers 1142 that connect input devices, such as a keyboard and mouse combination 1143, a camera 1144, or other USB input devices.

[0106] In at least one embodiment, instances of the memory controller 1116 and platform controller hub 1130 may be integrated into a discrete external graphics processor, such as external graphics processor 1112. In at least one embodiment, the platform controller hub 1130 and / or the memory controller 1116 may be external to one or more processors 1102. For example, in at least one embodiment, system 1100 may include external memory controller 1116 and platform controller hub 1130, which may be configured as a memory controller hub and peripheral controller hub in a system chipset communicating with processor 1102.

[0107] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7BDetails regarding the inference and / or training logic 715 are provided. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the graphics processor 1100. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs embodied in the graphics processor. Furthermore, in at least one embodiment, the inference and / or training operations described herein may use, in addition to Figure 7A and / or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0108] Such components can be used to render different types of objects, determine consistent secondary lighting effects for these objects, and then use these secondary lighting effects to composite the objects to generate a composite image.

[0109] Figure 12 This is a block diagram of a processor 1200 having one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208 according to at least one embodiment. In at least one embodiment, the processor 1200 may include additional cores, up to and including additional cores 1202N indicated by dashed boxes. In at least one embodiment, each processor core 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core may also access one or more shared cache units 1206.

[0110] In at least one embodiment, internal cache units 1204A-1204N and shared cache unit 1206 represent a cache memory hierarchy within processor 1200. In at least one embodiment, cache units 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of cache in a shared intermediate cache, such as Level 2 (L2), Level 3 (L3), Level 4 (L4), or other levels of cache, wherein the highest level of cache preceding external memory is classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0111] In at least one embodiment, the processor 1200 may further include a set of one or more bus controller units 1216 and a system agent core 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCIe buses. In at least one embodiment, the system agent core 1210 provides management functions for various processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 to manage access to various external memory devices (not shown).

[0112] In at least one embodiment, one or more processor cores 1202A-1202N include support for concurrent multithreading. In at least one embodiment, system agent core 1210 includes components for coordinating processor cores 1202A-1202N during multithreaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) including logic and components for regulating one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0113] In at least one embodiment, processor 1200 further includes a graphics processor 1208 for performing graph processing operations. In at least one embodiment, graphics processor 1208 is coupled to a shared cache unit 1206 and a system proxy core 1210 including one or more integrated memory controllers 1214. In at least one embodiment, system proxy core 1210 further includes a display controller 1211 for driving graphics processor outputs to one or more coupled displays. In at least one embodiment, display controller 1211 may also be a separate module coupled to graphics processor 1208 via at least one interconnect, or it may be integrated within graphics processor 1208.

[0114] In at least one embodiment, the ring-based interconnect unit 1212 is used to couple internal components of the processor 1200. In at least one embodiment, alternative interconnect units, such as point-to-point interconnects, switched interconnects, or other technologies, may be used. In at least one embodiment, the graphics processor 1208 is coupled to the ring-based interconnect unit 1212 via I / O link 1213.

[0115] In at least one embodiment, I / O link 1213 represents at least one of a variety of I / O interconnects, including packaged I / O interconnects that facilitate communication between various processor components and high-performance embedded memory module 1218 (e.g., eDRAM module). In at least one embodiment, each of processor cores 1202A-1202N and graphics processor 1208 uses embedded memory module 1218 as a shared last-level cache.

[0116] In at least one embodiment, processor cores 1202A-1202N are homogeneous cores executing a common instruction set architecture. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), with one or more processor cores 1202A-1202N executing a common instruction set, while one or more other processor cores 1202A-1202N execute a subset of the common instruction set or a different instruction set. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, with one or more cores having relatively high power consumption coupled to one or more power cores having lower power consumption. In at least one embodiment, processor 1200 may be implemented on one or more chips or implemented as a SoC integrated circuit.

[0117] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7B Details regarding the inference and / or training logic 715 are provided. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the processor 1200. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs embodied in... Figure 12 The graphics processor 1208, graphics core 1202A-1202N, or other components are used. Furthermore, in at least one embodiment, the inference and / or training operations described herein can use, except... Figure 7A and / or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor 1200 to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0118] Such components can be used to render different types of objects, determine consistent secondary lighting effects for these objects, and then use these secondary lighting effects to composite the objects to generate a composite image.

[0119] Virtualization computing platform

[0120] Figure 13 This is an example data flow diagram of process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, process 1300 may be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. Process 1300 may be executed within training system 1304 and / or deployment system 1306. In at least one embodiment, training system 1304 may be used to train, deploy, and implement machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use in deployment system 1306. In at least one embodiment, deployment system 1306 may be configured to offload processing and computing resources in a distributed computing environment to reduce the infrastructure requirements of facility 1302. In at least one embodiment, one or more applications in the pipeline may use or invoke services of deployment system 1306 (e.g., inference, visualization, computation, AI, etc.) during application execution.

[0121] In at least one embodiment, some applications used in the advanced processing and inference pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, a machine learning model may be trained at facility 1302 using data 1308 (e.g., imaging data) generated at facility 1302 (and stored on one or more Picture Archiving and Communication System (PACS) servers at facility 1302), imaging or sequencing data 1308 from another or more facilities, or a combination thereof. In at least one embodiment, training system 1304 may be used to provide applications, services, and / or other resources to generate a deployable machine learning model for the work of deploying system 1306.

[0122] In at least one embodiment, the model registry 1324 may be supported by an object storage system that supports version control and object metadata. In at least one embodiment, the object storage may be accessed from within a cloud platform via, for example, a cloud storage-compatible application programming interface (API). In at least one embodiment, machine learning models within the model registry 1324 may be uploaded, listed, modified, or deleted by the developer or partner of a system interacting with the API. In at least one embodiment, the API may provide access to methods that allow users with appropriate credentials to associate models with applications, enabling the models to be executed as part of the containerized instantiation of the application.

[0123] In at least one embodiment, training system 1304 (Figure 13 This can include situations where facility 1302 is training its own machine learning model or has an existing machine learning model that needs optimization or updating. In at least one embodiment, imaging data 1308 generated by imaging equipment, sequencing equipment, and / or other types of equipment can be received. In at least one embodiment, once the imaging data 1308 is received, AI-assisted annotation 1310 can be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for machine learning models. In at least one embodiment, AI-assisted annotation 1310 can include one or more machine learning models (e.g., convolutional neural networks (CNNs)) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain equipment). In at least one embodiment, AI-assisted annotation 1310 can then be used directly or adjusted or fine-tuned using annotation tools to generate ground-based data. In at least one embodiment, AI-assisted annotation 1310, labeled data 1312, or a combination thereof can be used as ground-based data for training machine learning models. In at least one embodiment, the trained machine learning model may be referred to as output model 1316 and may be used by deployment system 1306 as described herein.

[0124] In at least one embodiment, the training pipeline may include a scenario where facility 1302 requires a machine learning model to perform one or more processing tasks for deploying one or more applications in system 1306, but facility 1302 may not currently have such a machine learning model (or may not have a model optimized, efficient, or effective for this purpose). In at least one embodiment, an existing machine learning model may be selected from model registry 1324. In at least one embodiment, model registry 1324 may include machine learning models trained to perform various inference tasks on imaging data. In at least one embodiment, the machine learning model in model registry 1324 may be trained on imaging data from a different facility (e.g., a remote facility) instead of facility 1302. In at least one embodiment, the machine learning model may have already been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training on imaging data from a specific location, training may be performed at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts the off-site transfer of the imaging data. In at least one embodiment, once a model has been trained or partially trained at one location, a machine learning model can be added to model registry 1324. In at least one embodiment, the machine learning model can then be retrained or updated at any number of other facilities, and the retrained or updated model can be used in model registry 1324. In at least one embodiment, a machine learning model (referred to as output model 1316) can then be selected from model registry 1324, and can be used in deployment system 1306 to perform one or more processing tasks for one or more applications of the deployment system.

[0125] In at least one embodiment, the scenario may include facility 1302, which requires a machine learning model to perform one or more processing tasks for deploying one or more applications in system 1306, but facility 1302 may not currently have such a machine learning model (or may not have an optimized, efficient, or effective model). In at least one embodiment, the machine learning model selected from model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at facility 1302 due to population variability, robustness, anomalous diversity of training data, and / or other problems with the training data used to train the machine learning model. In at least one embodiment, AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for training or updating the machine learning model. In at least one embodiment, labeled data 1312 may be used as ground-based data for training the machine learning model. In at least one embodiment, retraining or updating the machine learning model may be referred to as model training 1314. In at least one embodiment, model training 1314 (e.g., AI-assisted annotation 1310, labeled clinical data 1312, or a combination thereof) can be used as ground-based data to retrain or update the machine learning model. In at least one embodiment, the trained machine learning model can be referred to as output model 1316 and can be used by deployment system 1306, as described herein.

[0126] In at least one embodiment, deployment system 1306 may include software 1318, service 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, deployment system 1306 may include a software "stack" such that software 1318 can be built on top of service 1320 and can be used to perform some or all of the processing tasks, and service 1320 and software 1318 can be built on top of hardware 1322 and use hardware 1322 to perform the deployment system's processing, storage, and / or other computational tasks. In at least one embodiment, software 1318 may include any number of different containers, each of which can perform an instantiation of an application. In at least one embodiment, each application can perform one or more processing tasks (e.g., inference, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in a high-level processing and inference pipeline. In at least one embodiment, in addition to receiving and configuring imaging data for use by each container and / or by facility 1302 after processing through the pipeline, advanced processing and inference pipelines (e.g., to convert output back to available data types) can be defined based on the selection of different containers desired or required for processing imaging data 1308. In at least one embodiment, a combination of containers within software 1318 (e.g., constituting a pipeline) may be referred to as a virtual instrument (as described in more detail herein), and the virtual instrument may utilize service 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated within the container.

[0127] In at least one embodiment, the data processing pipeline may receive input data (e.g., imaging data 1308) in a specific format in response to an inference request (e.g., a request from a user of deployment system 1306). In at least one embodiment, the input data may represent one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data may be preprocessed as part of the data processing pipeline to prepare it for processing by one or more applications. In at least one embodiment, post-processing may be performed on the output of one or more inference tasks or other processing tasks of the pipeline to prepare output data for the next application and / or to prepare output data for user transmission and / or use (e.g., as a response to an inference request). In at least one embodiment, the inference task may be performed by one or more machine learning models, such as trained or deployed neural networks, which may include the output model 1316 of training system 1304.

[0128] In at least one embodiment, the tasks of the data processing pipeline can be encapsulated in containers, each container representing a discrete, fully functional instantiation of an application and a virtualized computing environment capable of referencing a machine learning model. In at least one embodiment, containers or applications can be published to a private (e.g., limited access) area of ​​a container registry (described in more detail herein), and trained or deployed models can be stored in a model registry 1324 and associated with one or more applications. In at least one embodiment, an image of an application (e.g., a container image) can be used in the container registry, and once a user selects an image from the container registry for deployment in the pipeline, that image can be used to generate containers for instantiation of the application for use by the user's system.

[0129] In at least one embodiment, a developer (e.g., a software developer, clinician, physician, etc.) can develop, publish, and store an application (e.g., as a container) for performing image processing and / or inference on provided data. In at least one embodiment, a software development kit (SDK) associated with the system can be used to perform development, publication, and / or storage (e.g., to ensure that the developed application and / or container conforms to or is compatible with the system). In at least one embodiment, the developed application can be tested locally using the SDK (e.g., at a first facility, testing data from a first facility), the SDK serving as a system (e.g., Figure 12 System 1200 may support at least some services 1320. In at least one embodiment, since DICOM objects may contain one to hundreds of images or other data types, and due to variations in the data, the developer may be responsible for managing (e.g., setting up constructs for preprocessing built into the application, etc.) the extraction and preparation of incoming data. In at least one embodiment, once verified by process 1300 (e.g., for accuracy), the application becomes available in the container registry for user selection and / or implementation to perform one or more processing tasks on data at the user's facility (e.g., a second facility).

[0130] In at least one embodiment, the developer can then share the application or container over a network for the system (e.g., Figure 13The system 1300 allows for user access and use. In at least one embodiment, completed and validated applications or containers may be stored in a container registry, and associated machine learning models may be stored in a model registry 1324. In at least one embodiment, a requesting entity (which provides an inference or image processing request) may browse the container registry and / or model registry 1324 to obtain applications, containers, datasets, machine learning models, etc., select desired combinations of elements to include in the data processing pipeline, and submit an image processing request. In at least one embodiment, the request may include input data necessary to execute the request (and, in some examples, patient-related data), and / or may include selections of applications and / or machine learning models to be executed when processing the request. In at least one embodiment, the request may then be passed to one or more components of the deployment system 1306 (e.g., the cloud) to perform processing in the data processing pipeline. In at least one embodiment, processing performed by the deployment system 1306 may include referencing elements (e.g., applications, containers, models, etc.) selected from the container registry and / or model registry 1324. In at least one embodiment, once the results are generated through the pipeline, the results can be returned to the user for reference (e.g., for viewing in a suite of viewing applications executed locally, on a local workstation, or on a terminal).

[0131] In at least one embodiment, service 1320 may be utilized to assist in processing or executing applications or containers in the pipeline. In at least one embodiment, service 1320 may include computing services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, service 1320 may provide functionality common to one or more applications in software 1318, thus abstracting functionality into services that can be invoked or utilized by applications. In at least one embodiment, the functionality provided by service 1320 can operate dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using...). Figure 12The parallel computing platform 1230 in the system can be scaled well. In at least one embodiment, it is not required that each application providing the same functionality as the shared service 1320 must have a corresponding instance of the service 1320, but 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, which can provide the ability to train and / or retrain machine learning models. In at least one embodiment, a data augmentation service may be further included, which can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, conforming to REST, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used, which can add image rendering effects (e.g., ray tracing, rasterization, denoising, sharpening, etc.) to add realism to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, a virtual instrument service may be included, which provides beamforming, segmentation, inference, imaging, and / or support for other applications within the virtual instrument pipeline.

[0132] In at least one embodiment, where service 1320 includes an AI service (e.g., an inference service), as part of application execution, one or more machine learning models can be executed by invoking (e.g., as an API call) the inference service (e.g., an inference server) to execute one or more machine learning models or their processing. In at least one embodiment, where another application includes one or more machine learning models for a segmentation task, the application can invoke the inference service to execute the machine learning models for performing one or more processing operations associated with the segmentation task. In at least one embodiment, software 1318 implementing advanced processing and inference pipelines, including a segmentation application and an anomaly detection application, can be pipelined because each application can invoke the same inference service to execute one or more inference tasks.

[0133] In at least one embodiment, hardware 1322 may include a GPU, CPU, graphics card, AI / deep learning system (e.g., an AI supercomputer, such as NVIDIA's DGX), cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, specially built support for software 1318 and services 1320 in deployment system 1306. In at least one embodiment, GPU processing may be used to perform local processing (e.g., at facility 1302) within the AI / deep learning system, in the cloud system, and / or other processing components of deployment system 1306 to improve the efficiency, accuracy, and performance of image processing and generation. In at least one embodiment, as a non-limiting example, software 1318 and / or services 1320 may be optimized for GPU processing in relation to deep learning, machine learning, and / or high-performance computing. In at least one embodiment, at least some of the computing environment of deployment system 1306 and / or training system 1304 may be executed in a data center, one or more supercomputers, or high-performance computing systems with GPU-optimized software (e.g., a hardware and software combination of an NVIDIA DGX system). In at least one embodiment, as described herein, hardware 1322 may include any number of GPUs that can be invoked to perform data processing in parallel. In at least one embodiment, the cloud platform may also include GPU-optimized execution for deep learning tasks, GPU processing for machine learning tasks, or other computational tasks. In at least one embodiment, an AI / deep learning supercomputer and / or GPU-optimized software (e.g., as provided on NVIDIA's DGX systems) may be used as a hardware abstraction and scaling platform to execute the cloud platform (e.g., NVIDIA's NGC). In at least one embodiment, the cloud platform may integrate application container cluster systems or coordination systems (e.g., Kubernetes) across multiple GPUs to achieve seamless scaling and load balancing.

[0134] Figure 14 This is a system diagram of an example system 1400 for generating and deploying an imaging deployment pipeline according to at least one embodiment. In at least one embodiment, system 1400 can be used to implement Figure 13 The process 1300 and / or other processes include advanced processing and inference pipelines. In at least one embodiment, system 1400 may include training system 1304 and deployment system 1306. In at least one embodiment, training system 1304 and deployment system 1306 may be implemented using software 1318, service 1320 and / or hardware 1322, as described herein.

[0135] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) may be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 may be implemented locally (in relation to a healthcare facility) or as a combination of cloud computing resources and local computing resources. In at least one embodiment, access to the API in cloud 1426 may be restricted to authorized users by establishing security measures or protocols. In at least one embodiment, the security protocol may include a network token, which may be signed by an authentication service (e.g., AuthN, AuthZ, Gluecon, etc.) and may carry appropriate authorization. In at least one embodiment, the API of the virtual instrument (described herein) or other instances of system 1400 may be restricted to a set of public IPs that have been audited or authorized for interaction.

[0136] In at least one embodiment, the various components of system 1400 may communicate with each other using any of a variety of different network types, including but not limited to local area networks (LANs) and / or wide area networks (WANs) via wired and / or wireless communication protocols. In at least one embodiment, communication between facilities and components of system 1400 (e.g., for sending inference requests, for receiving the results of inference requests, etc.) may be transmitted via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet), etc.

[0137] In at least one embodiment, similar to the description herein. Figure 13 As described, training system 1304 can execute training pipeline 1404. In at least one embodiment, where deployment system 1306 uses one or more machine learning models in deployment pipeline 1410, training pipeline 1404 can be used to train or retrain one or more (e.g., pre-trained) models, and / or implement one or more pre-trained models 1406 (e.g., without retraining or updating). In at least one embodiment, as a result of training pipeline 1404, output model 1316 can be generated. In at least one embodiment, training pipeline 1404 can include any number of processing steps, such as, but not limited to, transformation or adaptation of imaging data (or other input data). In at least one embodiment, different training pipelines 1404 can be used for different machine learning models used by deployment system 1306. In at least one embodiment, similar to the description of... Figure 13 The training pipeline 1404 described in the first example can be used for the first machine learning model, similar to the one described above. Figure 13 The training pipeline 1404 described in the second example can be used for a second machine learning model, similar to the one described above. Figure 13The training pipeline 1404 of the third example described can be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 can be used according to the requirements of each corresponding machine learning model. In at least one embodiment, one or more machine learning models may have already been trained and are ready for deployment, so the training system 1304 may not perform any processing on the machine learning models, and one or more machine learning models may be implemented by the deployment system 1306.

[0138] In at least one embodiment, depending on the implementation or embodiment, the output model 1316 and / or the pre-trained model 1406 may include any type of machine learning model. In at least one embodiment, and not limited thereto, the machine learning model used by system 1400 may include models using linear regression, logistic regression, decision trees, support vector machines (SVM), Naive Bayes, k-nearest neighbors (Knn), k-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutions, recursion, perceptrons, long / short-term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid state machines, etc.), and / or other types of machine learning models.

[0139] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotations, as described herein regarding at least Figure 14More specifically, in at least one embodiment, labeled clinical data 1312 can be generated using any number of techniques (e.g., conventional annotation). In at least one embodiment, in some examples, labels or other annotations can be generated by drawing programs (e.g., annotation programs), computer-aided design (CAD) programs, tagging programs, another type of application suitable for generating annotations or labels for ground reality, and / or can be hand-drawn. In at least one embodiment, ground reality data can be synthetically generated (e.g., generated from computer models or renderings), realistically generated (e.g., designed and generated from real-world data), machine-generated (e.g., extracting features from data using feature analysis and learning, and then generating labels), human-annotated (e.g., taggers or annotation experts, defining the placement of labels), and / or combinations thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by machine learning models), there may be corresponding ground reality data generated by training system 1304. In at least one embodiment, AI-assisted annotation can be performed as part of deployment pipeline 1410; supplementing or replacing AI-assisted annotation included in training pipeline 1404. In at least one embodiment, system 1400 may include a multi-layer platform, which may include a software layer (e.g., software 1318) of a diagnostic application (or other application type) capable of performing one or more medical imaging and diagnostic functions. In at least one embodiment, system 1400 may be communicatively coupled (e.g., via an encrypted link) to a network of PACS servers in one or more facilities. In at least one embodiment, system 1400 may be configured to access and reference data from PACS servers to perform operations such as training machine learning models, deploying machine learning models, image processing, inference, and / or other operations.

[0140] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or certified API that can invoke (e.g., call) an application or container from an external environment (e.g., facility 1302). In at least one embodiment, the application may then invoke or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with their respective applications, and the software 1318 and / or services 1320 may utilize the hardware 1322 to perform processing tasks efficiently and effectively. In at least one embodiment, communication sent to or received by the training system 1304 and deployment system 1306 may occur using a pair of DICOM adapters 1402A, 1402B.

[0141] In at least one embodiment, deployment system 1306 may execute deployment pipeline 1410. In at least one embodiment, deployment pipeline 1410 may include any number of applications, which may be sequential, non-sequential, or otherwise applied to imaging data (and / or other data types) – including AI-assisted annotation, the imaging data being generated by imaging devices, sequencing devices, genomics devices, etc., as described above. In at least one embodiment, as described herein, deployment pipeline 1410 for an individual device may be referred to as a virtual instrument for the device (e.g., a virtual ultrasound instrument, a virtual CT scanner, a virtual sequencing instrument, etc.). In at least one embodiment, for a single device, more than one deployment pipeline 1410 may exist, depending on the desired information from the data generated from the device. In at least one embodiment, a first deployment pipeline 1410 may exist if it is desired to detect an anomaly from an MRI machine, and a second deployment pipeline 1410 may exist if it is desired to perform image enhancement from the output of the MRI machine.

[0142] In at least one embodiment, the image generation application may include processing tasks that utilize machine learning models. In at least one embodiment, a user may wish to use their own machine learning model or select a machine learning model from the model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to be included in the application performing the processing tasks. In at least one embodiment, the application may be optional and customizable, and by defining the application's construction, the deployment and implementation of the application for a specific user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of system 1400 (e.g., service 1320 and hardware 1322), the deployment pipeline 1410 can be more user-friendly, provide easier integration, and produce more accurate, efficient, and timely results.

[0143] In at least one embodiment, deployment system 1306 may include a user interface (UI) 1414 (e.g., a graphical user interface, a web interface, etc.) that can be used to select applications to be included in deployment pipeline 1410, deploy applications, modify or change applications or their parameters or configurations, use and interact with deployment pipeline 1410 during setup and / or deployment, and / or otherwise interact with deployment system 1306. In at least one embodiment, although not shown with respect to training system 1304, UI 1414 (or different user interfaces) can be used to select models to be used in deployment system 1306, to select models to be trained or retrained in training system 1304, and / or to otherwise interact with training system 1304.

[0144] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may be used to manage interactions between applications or containers deployed through the pipeline 1410 and services 1320 and / or hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate interactions from application to application, from application to service 1320, and / or from application or service to hardware 1322. In at least one embodiment, although shown as included in software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in service 1320. In at least one embodiment, the application coordination system 1428 (e.g., Kubernetes, DOCKER, etc.) may include a container coordination system that can group applications into containers as logical units for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from the deployment pipeline 1410 (e.g., rebuilding applications, splitting applications, etc.) with individual containers, each application can execute in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0145] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed independently (e.g., a first user or developer can develop, modify, and deploy a first application, and a second user or developer can develop, modify, and deploy a second application separate from the first user or developer). This allows focus on the tasks of a single application and / or container without being hindered by the tasks of another application or container. In at least one embodiment, the pipeline manager 1412 and the application coordination system 1428 can facilitate communication and collaboration between different containers or applications. In at least one embodiment, the application coordination system 1428 and / or the pipeline manager 1412 can facilitate communication and resource sharing between and within each application or container, provided that the expected inputs and / or outputs of each container or application are known to the system (e.g., based on the construction of the application or container). In at least one embodiment, since one or more applications or containers in the deployment pipeline 1410 can share the same services and resources, the application coordination system 1428 can coordinate, load balance, and determine the sharing of services or resources between and within the various applications or containers. In at least one embodiment, the scheduler can be used to track the resource requirements of applications or containers, the current or planned use of these resources, and resource availability. Therefore, in at least one embodiment, the scheduler can allocate resources to different applications and distribute resources between and among applications, taking into account the system's needs and availability. In some examples, the scheduler (and / or other components of the application coordination system 1428) can determine resource availability and distribution based on constraints imposed on the system (e.g., user constraints), such as Quality of Service (QoS), the urgency of data output (e.g., to determine whether to perform real-time processing or delayed processing), etc.

[0146] In at least one embodiment, service 1320, utilized and shared by applications or containers in deployment system 1306, may include computing service 1416, AI service 1418, visualization service 1420, and / or other service types. In at least one embodiment, an application may invoke (e.g., execute) one or more services 1320 to perform processing operations for the application. In at least one embodiment, an application may utilize computing service 1416 to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, one or more computing services 1416 may be utilized to perform parallel processing (e.g., using parallel computing platform 1430) to process data substantially simultaneously through one or more applications and / or one or more tasks of a single application. In at least one embodiment, parallel computing platform 1430 (e.g., NVIDIA's CUDA) may implement general-purpose computing on a GPU (GPGPU) (e.g., GPU / graphics 1422). In at least one embodiment, the software layer of parallel computing platform 1430 may provide access to the GPU's virtual instruction set and parallel computing elements to execute computing kernels. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, memory may be shared between and within multiple containers, and / or between and within different processing tasks within a single container. In at least one embodiment, inter-process communication (IPC) calls may be generated for multiple containers and / or multiple processes within containers to enable the use of the same data (e.g., multiple different stages of one or more applications processing the same information) from a shared memory segment of the parallel computing platform 1430. In at least one embodiment, instead of copying data and moving it to different locations in memory (e.g., read / write operations), the same data in the same memory location can be used for any number of processing tasks (e.g., at the same time, at different times, etc.). In at least one embodiment, this information about the new location of the data can be stored and shared between applications because the resulting data from processing is used to generate new data. In at least one embodiment, the location of the data, and the location of the updated or modified data, may be part of the definition of how the payload in the container is understood.

[0147] In at least one embodiment, AI service 1418 may be used to perform an inference service for executing a machine learning model associated with the application (e.g., a task to perform one or more processing tasks of the application). In at least one embodiment, AI service 1418 may utilize AI system 1424 to execute a machine learning model (e.g., a neural network such as a CNN) for segmentation, reconstruction, object detection, feature detection, classification, and / or other inference tasks. In at least one embodiment, the application deploying pipeline 1410 may use one or more output models 1316 of self-training system 1304 and / or other models of the application to perform inference on imaging data. In at least one embodiment, two or more examples of using application coordination system 1428 (e.g., a scheduler) for inference may be available. In at least one embodiment, a first category may include a high-priority / low-latency path that can implement a higher service level protocol, such as for performing inference on urgent requests in emergency situations or for radiologists during diagnostic procedures. In at least one embodiment, a second category may include a standard priority path that can be used for requests that may not be urgent or for situations where analysis can be performed at a later time. In at least one embodiment, the application coordination system 1428 may allocate resources (e.g., services 1320 and / or hardware 1322) based on priority paths for different inference tasks of the AI ​​service 1418.

[0148] In at least one embodiment, shared memory may be installed into AI service 1418 in system 1400. In at least one embodiment, shared memory may operate as a cache (or other storage device type) and may be used to process inference requests from applications. In at least one embodiment, when an inference request is submitted, a set of API instances of deployment system 1306 may receive the request and may select one or more instances (e.g., for best fit, for load balancing, etc.) to process the request. In at least one embodiment, to process the request, the request may be fed into a database, and if not already in the cache, a machine learning model may be located from model registry 1324. A verification step may ensure that an appropriate machine learning model is loaded into the cache (e.g., shared memory), and / or a copy of the model may be saved to the cache. In at least one embodiment, if the application is not already running or there are not enough instances of the application, a scheduler (e.g., the scheduler of pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if an inference server has not yet been started to execute the model, an inference server may be started. Any number of inference servers may be started for each model. In at least one embodiment, in a pull model that clusters inference servers, the model can be cached whenever load balancing is favorable. In at least one embodiment, the inference servers can be statically loaded into the corresponding distributed servers.

[0149] In at least one embodiment, an inference server running in a container can be used to perform inference. In at least one embodiment, an instance of the inference server can be associated with a model (and optionally multiple versions of the model). In at least one embodiment, if an instance of the inference server does not exist when a request to perform inference on the model is received, a new instance can be loaded. In at least one embodiment, when the inference server is started, a model can be passed to the inference server, allowing the same container to be used to serve different models, as long as the inference server runs as different instances.

[0150] In at least one embodiment, during application execution, an inference request for a given application can be received, and a container (e.g., an instance of a hosted inference server) can be loaded (if not already loaded), and a launcher can be invoked. In at least one embodiment, preprocessing logic within the container can (e.g., using a CPU and / or GPU) load, decode, and / or perform any additional preprocessing on the incoming data. In at least one embodiment, once the data is ready for inference, the container can infer the data as needed. In at least one embodiment, this can include a single inference call for an image (e.g., a hand X-ray) or can request inference for hundreds of images (e.g., a chest CT scan). In at least one embodiment, the application can summarize the results before completion, which may include, but is not limited to, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating visualizations, or generating text to summarize the results. In at least one embodiment, different priorities can be assigned to different models or applications. For example, some models may have a real-time (TAT less than 1 minute) priority, while other models may have a lower priority (e.g., TAT less than 10 minutes). In at least one embodiment, model execution time can be measured from the requesting agency or entity, and may include cooperative network traversal time and inference service execution time.

[0151] In at least one embodiment, the transfer of requests between service 1320 and the inference application can be hidden behind a software development kit (SDK) and robust transfer can be provided via queues. In at least one embodiment, requests are placed in queues via an API for individual application / tenant ID combinations, and the SDK pulls requests from the queues and provides them to the application. In at least one embodiment, the name of the queue can be provided in the environment where the SDK picks up the queue. In at least one embodiment, asynchronous communication via queues may be useful because it allows any instance of the application to pick up work when it becomes available. Results can be sent back via queues to ensure no data loss. In at least one embodiment, queues can also provide the ability to partition work, as the highest priority work can go into a queue connected to a majority of instances of the application, while the lowest priority work can go into a queue connected to a single instance that processes tasks in the order they are received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in cloud 1426, and the inference service can perform inference on the GPU.

[0152] In at least one embodiment, visualization service 1420 can be used to generate visualizations for viewing the output of application and / or deployment pipeline 1410. In at least one embodiment, visualization service 1420 can utilize GPU / graphics 1422 to generate visualizations. In at least one embodiment, visualization service 1420 can implement rendering effects such as ray tracing to generate higher quality visualizations. In at least one embodiment, visualizations can include, but are not limited to, 2D image rendering, 3D volume rendering, 3D volume reconstruction, 2D tomographic slicing, virtual reality display, augmented reality display, etc. In at least one embodiment, a virtualized environment can be used to generate virtual interactive displays or environments (e.g., virtual environments) for system users (e.g., doctors, nurses, radiologists, etc.) to interact with. In at least one embodiment, visualization service 1420 can include an internal visualizer, cinematic and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0153] In at least one embodiment, hardware 1322 may include GPU / graphics 1422, AI system 1424, cloud 1426, and / or any other hardware for performing training system 1304 and / or deployment system 1306. In at least one embodiment, GPU / graphics 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs that can be used to perform processing tasks for any feature or function of computing service 1416, AI service 1418, visualization service 1420, other services, and / or software 1318. For example, for AI service 1418, GPU / graphics 1422 may be used to perform preprocessing on imaging data (or other data types used by machine learning models), postprocessing on the output of machine learning models, and / or inference (e.g., to execute machine learning models). In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may use GPU / graphics 1422. In at least one embodiment, cloud 1426 may include a GPU-optimized platform for deep learning tasks. In at least one embodiment, AI system 1424 may use a GPU, and one or more AI systems 1424 may be used to perform cloud 1426 (or at least part of a task for deep learning or inference). Similarly, although hardware 1322 is shown as a discrete component, this is not intended to be limiting, and any component of hardware 1322 may be combined with or utilized by any other component of hardware 1322.

[0154] In at least one embodiment, AI system 1424 may include a specially built computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, in addition to CPU, RAM, memory, and / or other components, features, or functions, AI system 1424 (e.g., NVIDIA's DGX) may also include software (e.g., a software stack) that can be used to perform GPU-optimized tasks using multiple GPUs / graphics 1422. In at least one embodiment, one or more AI systems 1424 may be implemented in a cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of system 1400.

[0155] In at least one embodiment, cloud 1426 may include GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that can provide a GPU-optimized platform for performing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include AI system 1424 for performing one or more AI-based tasks of system 1400 (e.g., as a hardware abstraction and scaling platform). In at least one embodiment, cloud 1426 may be integrated with application coordination system 1428 utilizing multiple GPUs to achieve seamless scaling and load balancing between and within applications and services 1320. In at least one embodiment, as described herein, cloud 1426 may be responsible for performing at least some of the services 1320 of system 1400, including computing service 1416, AI service 1418, and / or visualization service 1420. In at least one embodiment, cloud 1426 may perform large and small batch inference (e.g., perform NVIDIA's TENSORRT), provide accelerated parallel computing APIs and platform 1430 (e.g., NVIDIA's CUDA), perform application coordination system 1428 (e.g., KUBERNETES), provide graphics rendering APIs and platform (e.g., for ray tracing, 2D graphics, 3D graphics and / or other rendering techniques to produce higher quality cinematic effects), and / or provide other functionalities for system 1400.

[0156] Figure 15A A data flow diagram of a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment is shown. In at least one embodiment, a non-limiting example can be used. Figure 14 The system 1400 executes the process 1500. In at least one embodiment, the process 1500 may utilize services and / or hardware, as described herein. In at least one embodiment, the refined model 1512 generated by the process 1500 may be executed by a deployment system for one or more containerized applications in the deployment pipeline.

[0157] In at least one embodiment, model training 1514 may include retraining or updating the initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data, such as customer dataset 1506, and / or new ground reality data associated with the input data). In at least one embodiment, to retrain or update the initial model 1504, the output or loss layer of the initial model 1504 may be reset or deleted, and / or replaced with an updated or new output or loss layer. In at least one embodiment, the initial model 1504 may have previously fine-tuned parameters (e.g., weights and / or biases) retained from previous training, so training or retraining 1514 may not require as much time or processing as training the model from scratch. In at least one embodiment, during model training 1514, when generating predictions on the new customer dataset 1506 by resetting or replacing the output or loss layer of the initial model 1504, the parameters of the new dataset may be updated and readjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0158] In at least one embodiment, the pre-trained model 1506 may be stored in a data store or registry. In at least one embodiment, the pre-trained model 1506 may have been trained at least partially at one or more facilities other than the facility executing process 1500. In at least one embodiment, to protect the privacy and rights of patients, subjects, or customers at different facilities, the pre-trained model 1506 may have been trained locally using locally generated customer or patient data. In at least one embodiment, the pre-trained model 1506 may be trained using cloud and / or other hardware, but confidential, privacy-protected patient data may not be transferred to, used by, or accessed by any component of the cloud (or other non-local hardware). In at least one embodiment, if the pre-trained model 1506 is trained using patient data from more than one facility, the pre-trained model 1506 may have been trained separately for each facility before training on patient or customer data from another facility. In at least one embodiment, such as when customer or patient data has been published for privacy reasons (e.g., by abandonment, for experimental purposes, etc.), or where customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train a pre-trained model 1506 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0159] In at least one embodiment, when selecting an application for use in the deployment pipeline, the user may also select a machine learning model for a specific application. In at least one embodiment, the user may not have a model available, so the user may select a pre-trained model to use with the application. In at least one embodiment, the pre-trained model may not be optimized to generate accurate results on the user facility's customer dataset 1506 (e.g., based on patient diversity, demographics, type of medical imaging equipment used, etc.). In at least one embodiment, the pre-trained model may be updated, retrained, and / or fine-tuned for use at various facilities before being deployed into the deployment pipeline for use with one or more applications.

[0160] In at least one embodiment, a user may select a pre-trained model to update, retrain, and / or fine-tune, and this pre-trained model may be referred to as the initial model 1504 of the training system in process 1500. In at least one embodiment, a client dataset 1506 (e.g., imaging data, genomic data, sequencing data, or other data types generated by equipment at the facility) may be used to perform model training (which may include, but is not limited to, transfer learning) on ​​the initial model 1504 to generate a refined model 1512. In at least one embodiment, ground-based data corresponding to the client dataset 1506 may be generated by the training system 1304. In at least one embodiment, the ground-based data may be generated at the facility, at least in part, by clinicians, scientists, physicians, or practitioners.

[0161] In at least one embodiment, AI-assisted annotation may be used to generate ground-based data in some examples. In at least one embodiment, AI-assisted annotation (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted ground-based data for a customer dataset. In at least one embodiment, a user may use the annotation tool within a user interface (graphical user interface (GUI)) on a computing device.

[0162] In at least one embodiment, user 1510 can interact with the GUI via computing device 1508 to edit or fine-tune annotations or automatic annotations. In at least one embodiment, polygon editing features can be used to move the vertices of a polygon to more precise or fine-tuned positions.

[0163] In at least one embodiment, once the customer dataset 1506 has associated ground-based data, the ground-based data (e.g., from AI-assisted annotations, manual labeling, etc.) can be used to generate a refined model 1512 during model training. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 an arbitrary number of times, and the ground-based data can be used to update the parameters of the initial model 1504 until an acceptable level of accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 is generated, it can be deployed in one or more deployment pipelines at the facility to perform one or more processing tasks related to medical imaging data.

[0164] In at least one embodiment, the refined model 1512 can be uploaded to a pre-trained model registry for selection by another facility. In at least one embodiment, this process can be performed at any number of facilities, allowing the refined model 1512 to be further refined an arbitrary number of times on a new dataset to generate a more general model.

[0165] Figure 15B This is an example illustration of a client-server architecture 1532 for enhancing an annotation tool using a pre-trained annotation model, according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 may be instantiated based on the client-server architecture 1532. In at least one embodiment, the AI-assisted annotation tool 1536 in an imaging application can assist radiologists, for example, in identifying organs and abnormalities. In at least one embodiment, the imaging application may include software tools, as a non-limiting example, that help user 1510 identify several extreme points on a specific organ of interest in a raw image 1534 (e.g., in a 3D MRI or CT scan) and receive automatic annotation results for all 2D slices of that specific organ. In at least one embodiment, the results may be stored in a data store as training data 1538 and used as (e.g., but not limited to) ground-based data for training. In at least one embodiment, when computing device 1508 sends extreme points for AI-assisted annotation, for example, a deep learning model may receive this data as input and return inference results for segmenting organs or abnormalities. In at least one embodiment, a pre-instantiated annotation tool (e.g., Figure 15BThe AI-assisted annotation tool 1536 can be enhanced by making API calls (e.g., API call 1544) to a server (such as annotation assistant server 1540), which may include a set of pre-trained models 1542 stored, for example, in an annotation model registry. In at least one embodiment, the annotation model registry may store the pre-trained models 1542 (e.g., machine learning models, such as deep learning models) pre-trained to perform AI-assisted annotation on specific organs or anomalies. In at least one embodiment, these models can be further updated using a training pipeline. In at least one embodiment, the pre-installed annotation tool can be improved over time as new labeled data is added.

[0166] The various embodiments can be described by the following terms:

[0167] 1. A computer-implemented method, comprising:

[0168] Using a generative model and based on the input text, generate a representation of the motion specified by the text;

[0169] Using a discriminator, the representations of the text and motion are compared to calculate an alignment value; and

[0170] One or more network parameters used in the generative model are updated in part based on the alignment value.

[0171] 2. The computer-implemented method according to Clause 1, wherein the discriminator includes a first network for generating text embeddings for received text and a second network for generating motion embeddings for the representation of motion.

[0172] 3. The computer-implemented method according to Clause 2, wherein the discriminator is used to calculate the alignment value in part based on the dot product of the text embedding and the motion embedding.

[0173] 4. The computer-implemented method according to Clause 1, wherein advantage-weighted regression is used to calculate one or more updates for the one or more network parameters.

[0174] 5. The computer-implemented method according to Clause 1, wherein the generative model is at least one of a diffusion model, a transformer-based model, a variational autoencoder-based model, or a generative adversarial network.

[0175] 6. The computer-implemented method according to Clause 5, wherein the representation is one of virtual manipulation of an image sequence, a video clip, or a three-dimensional model.

[0176] 7. The computer-implemented method according to Clause 1 further comprises:

[0177] Using a loss function with a loss term corresponding to the alignment value, calculate the loss value for the representation of the generated motion; and

[0178] One or more updates to the one or more network parameters are determined in part based on the loss value.

[0179] 8. The computer-implemented method according to Clause 1, wherein the text further includes at least one qualifier indicating the type, style, or rate of execution of the movement.

[0180] 9. The computer-implemented method according to Clause 1, wherein the discriminator is a discriminator based on a contrastive language-image pre-trained CLIP.

[0181] 10. A processor comprising:

[0182] One or more circuits are used for:

[0183] Generative models are used to generate anthropomorphic motion representations associated with the input text;

[0184] The text and motion representations are compared using a discriminator; and

[0185] One or more network parameters used in the generative model are updated in part based on the results of the comparison.

[0186] 11. The processor according to Clause 10, wherein the one or more network parameters are updated as part of a reinforcement learning-based training process to fine-tune the generative model.

[0187] 12. The processor according to Clause 10, wherein the generative model is a motion diffusion model.

[0188] 13. The processor according to Clause 10, wherein the discriminator includes a first network for generating text embeddings for received text and a second network for generating motion embeddings for the representation of motion.

[0189] 14. The processor according to Clause 13, wherein the discriminator is configured to compute the alignment value in part based on the dot product of the text embedding and the motion embedding.

[0190] 15. The processor according to Clause 10, wherein the processor is included in at least one of the following:

[0191] A system used to perform simulation operations;

[0192] A system used to perform simulations to test or validate autonomous machine applications;

[0193] Systems used to perform digital twin operations;

[0194] A system for performing optical transmission simulation;

[0195] A system used for rendering graphics output;

[0196] A system used to perform deep learning operations;

[0197] Systems implemented using edge devices;

[0198] Systems used to generate or present virtual reality (VR) content;

[0199] A system for generating or presenting augmented reality (AR) content;

[0200] A system for generating or presenting mixed reality (MR) content;

[0201] A system containing one or more virtual machines (VMs);

[0202] A system that is at least partially implemented in a data center;

[0203] A system for performing hardware tests using simulation;

[0204] Systems for generating synthetic data;

[0205] A system for performing generative operations using large language model LLM;

[0206] A system for performing generative operations using a visual language model (VLM);

[0207] A collaborative content creation platform for 3D assets; or

[0208] A system that utilizes cloud computing resources at least in part.

[0209] 16. A system comprising:

[0210] One or more processors are configured to use a motion diffusion model to generate a representation of anthropomorphic motion corresponding to text input, and to update the motion diffusion model using a discriminator that computes an alignment value between the text input and the representation of human motion, the alignment value being used to determine updates to one or more network parameters for the motion diffusion model.

[0211] 17. The system according to Clause 16, wherein the one or more network parameters are updated as part of a reinforcement learning-based training process to fine-tune the motion diffusion model.

[0212] 18. The system according to Clause 16, wherein the alignment value is calculated in part based on a first code generated for the text input and a second code generated for the representation of human motion.

[0213] 19. The system according to Clause 16, wherein the text further includes at least one qualifier indicating the type, style, or rate of execution of the movement.

[0214] 20. The system according to Clause 16, wherein the system comprises at least one of the following:

[0215] A system used to perform simulation operations;

[0216] A system used to perform simulations to test or validate autonomous machine applications;

[0217] Systems used to perform digital twin operations;

[0218] A system for performing optical transmission simulation;

[0219] A system used for rendering graphics output;

[0220] A system used to perform deep learning operations;

[0221] A system for performing generative operations using large language model LLM;

[0222] A system for performing generative operations using a visual language model (VLM);

[0223] Systems implemented using edge devices;

[0224] Systems used to generate or present virtual reality (VR) content;

[0225] A system for generating or presenting augmented reality (AR) content;

[0226] A system for generating or presenting mixed reality (MR) content;

[0227] A system containing one or more virtual machines (VMs);

[0228] A system that is at least partially implemented in a data center;

[0229] A system for performing hardware tests using simulation;

[0230] Systems for generating synthetic data;

[0231] A collaborative content creation platform for 3D assets; or

[0232] A system that utilizes cloud computing resources at least in part.

[0233] Other variations are within the spirit of this disclosure. Therefore, while the disclosed technology is readily adaptable to various modifications and alternative constructions, certain embodiments thereof are illustrated in the accompanying drawings and have been described in detail above. However, it should be understood that the disclosure is not intended to be limited to one or more specific forms disclosed, but rather, it is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of this disclosure as defined in the appended claims.

[0234] Unless otherwise stated or obviously contradicted by the context, the terms “a,” “an,” and “the,” and similar references, used in the context of describing the disclosed embodiments (particularly in the context of the appended claims), should be interpreted as encompassing both singular and plural forms, rather than as definitions of the terms. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” should be interpreted as open-ended terms (meaning “including, but not limited to”). The term “connection” (referring to a physical connection where not modified) should be interpreted as partially or wholly contained, attached to, or joined together, even with some intervention. Unless otherwise indicated herein, references to numerical ranges herein are intended only as a way of abbreviating each individual value falling within that range, and each individual value is incorporated into the specification as if it were separately described herein. Unless otherwise indicated or contradicted by the context, the use of the terms “set” (e.g., “item set”) or “subset” should be interpreted as a non-empty set comprising one or more members. Furthermore, unless otherwise indicated or contradicted by the context, the term "subset" of a corresponding set does not necessarily refer to an appropriate subset of the corresponding set, but rather the subset and the corresponding set can be equal.

[0235] Unless otherwise explicitly stated or clearly contradicted by the context, connective phrases such as “at least one of A, B, and C” or “at least one of A, B, and C” are understood in the context to generally refer to items, terms, etc., which can be A or B or C, or any non-empty subset of the set A, B, and C. For example, in an illustrative example of a set with three members, the connective phrases “at least one of A, B, and C” and “at least one of A, B, and C” refer to any of the following sets: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Therefore, such connective language is generally not intended to imply that some embodiments require the presence of at least one of A, at least one of B, and at least one of C. Additionally, unless otherwise stated or contradicted by the context, the term “multiple” indicates a plural state (e.g., “multiple items” means multiple items). The number of items in a multiple item is at least two, but may be more if explicitly indicated or indicated by the context. Furthermore, unless otherwise stated or clearly understood from the context, the phrase “based on” means “at least partially based on” rather than “based on only”.

[0236] Unless otherwise indicated herein or clearly contradicted by the context, the operations of the processes described herein may be performed in any suitable order. In at least one embodiment, processes such as those described herein (or variations thereof and / or combinations thereof) are executed under the control of one or more computer systems configured with executable instructions and are implemented as code (e.g., executable instructions, one or more computer programs, or one or more application programs) that is executed jointly on one or more processors via hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors. In at least one embodiment, the computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagating transient electrical or electromagnetic transmissions) but includes non-transitory data storage circuitry (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on one or more non-transitory computer-readable storage media (or other memory for storing executable instructions) on which executable instructions are stored, which, when executed by one or more processors of a computer system (i.e., as a result of execution), cause the computer system to perform the operations described herein. In at least one embodiment, the set of non-transitory computer-readable storage media comprises multiple non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media lack all the code, but the multiple non-transitory computer-readable storage media collectively store all the code. In at least one embodiment, the executable instructions are executed such that different instructions are executed by different processors; for example, the non-transitory computer-readable storage media store the instructions, and the main central processing unit (“CPU”) executes some instructions while the graphics processing unit (“GPU”) executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and the different processors execute different subsets of the instructions.

[0237] Therefore, in at least one embodiment, the computer system is configured to implement one or more services that perform the operations of the processes described herein, either individually or collectively, and such a computer system is configured with suitable hardware and / or software to enable the implementation of the operations. Furthermore, the computer system implementing at least one embodiment of this disclosure is a single device, and in another embodiment it is a distributed computer system comprising multiple devices operating in different ways, such that the distributed computer system performs the operations described herein, and that a single device does not perform all the operations.

[0238] The use of any and all examples or exemplary language (e.g., “such as”) provided herein is intended only to better illustrate embodiments of this disclosure and does not constitute a limitation on the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any unclaimed element is essential to the practice of the disclosure.

[0239] All references cited in this article, including publications, patent applications and patents, are incorporated herein by reference as if each reference were individually and specifically indicated to be incorporated herein by reference and the entire contents of which are described herein.

[0240] The terms “coupled” and “connected”, and their derivatives, may be used in the specification and claims. It should be understood that these terms may not be intended to be synonyms with each other. Rather, in certain examples, “connected” or “coupled” may be used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. “Coupled” may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0241] Unless otherwise expressly stated, it will be understood that throughout this specification, terms such as “processing,” “computing,” “determining,” etc., refer to the actions and / or processes of a computer or computing system or similar electronic computing device that process and / or convert data represented as physical quantities (e.g., electrons) in the registers and / or memory of the computing system into other data represented as physical quantities in the memory, registers, or other such information storage, transmission, or display devices of the computing system.

[0242] In a similar manner, the term "processor" can refer to any device or part of memory that processes electronic data from registers and / or memory and converts that electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" can be a CPU or a GPU. A "computing platform" can include one or more processors. As used herein, a "software" process can include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process can refer to multiple processes that execute instructions sequentially or intermittently, sequentially, or in parallel. The terms "system" and "method" are used interchangeably herein, provided that a system can embody one or more methods, and a method can be considered a system.

[0243] This document refers to the process of acquiring, obtaining, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine. Analog and digital data can be acquired, obtained, received, or input in various ways, such as by receiving data as a parameter to a function call or a call to an application programming interface (API). In some implementations, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data via a serial or parallel interface. In another implementation, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data from a providing entity to an acquiring entity via a computer network. Reference can also be made to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data can be implemented by transmitting data as an input or output parameter to a function call, an API, or an inter-process communication mechanism.

[0244] While the discussion above illustrates example implementations of the described technologies, other architectures can be used to implement the described functionality and are intended to fall within the scope of this disclosure. Furthermore, although specific assignments of responsibilities have been defined above for discussion purposes, various functions and responsibilities can be assigned and divided in different ways depending on the circumstances.

[0245] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or actions described. Rather, specific features and actions are disclosed as exemplary forms for implementing the claims.

Claims

1. A computer-implemented method comprising: generating, using a generative model and based on input text, a representation of a motion specified by the text; comparing, using a discriminator, the text and the representation of the motion to compute an alignment value; and updating, based in part on the alignment value, one or more network parameters for the generative model.

2. The computer-implemented method of claim 1, wherein, the discriminator comprises a first network to generate a text embedding for a received text and a second network to generate a motion embedding for the representation of the motion.

3. The computer-implemented method of claim 2, wherein, the discriminator is to compute the alignment value based in part on a dot product of the text embedding and the motion embedding.

4. The computer-implemented method of claim 1, wherein, computing one or more updates to the one or more network parameters using advantage weighted regression.

5. The computer-implemented method of claim 1, wherein, the generative model is at least one of a diffusion model, a transformer-based model, a variational autoencoder-based model, or a generative adversarial network.

6. The computer-implemented method of claim 5, wherein, the representation is one of a sequence of images, a video clip, or a virtual manipulation of a three-dimensional model.

7. The computer-implemented method of claim 1, further comprising: computing, using a loss function having a loss term corresponding to the alignment value, a loss value for the generated representation of the motion; and determining, based in part on the loss value, one or more updates to the one or more network parameters.

8. The computer-implemented method of claim 1, wherein, the text further comprises at least one qualifier indicative of a type, style, or rate of performance of the motion.

9. The computer-implemented method of claim 1, wherein, the discriminator is a discriminator based on contrastive language-image pre-training (CLIP).

10. A processor comprising: one or more circuits to: generate, using a generative model, a representation of anthropomorphized motion associated with input text; perform a comparison, using a discriminator, of the text and the representation of the motion; and update, based in part on a result of the comparison, one or more network parameters for the generative model.

11. The processor of claim 10, wherein, the one or more network parameters are updated as part of a reinforcement learning-based training process to fine-tune the generative model.

12. The processor of claim 10, wherein, the generative model is a motion diffusion model.

13. The processor of claim 10, wherein, the discriminator comprises a first network to generate a text embedding for a received text and a second network to generate a motion embedding for the representation of the motion.

14. The processor of claim 13, wherein, the discriminator is to compute the alignment value based in part on a dot product of the text embedding and the motion embedding.

15. The processor of claim 10, wherein, the processor is comprised in at least one of: a system to perform simulation operations; a system to perform simulation operations to test or validate autonomous machine applications; a system to perform digital twin operations; a system to perform optical transport simulations; a system to render graphical output; a system to perform deep learning operations; a system implemented using edge devices; a system to generate or present virtual reality (VR) content; a system to generate or present augmented reality (AR) content; a system to generate or present mixed reality (MR) content; a system comprising one or more virtual machines (VMs); a system implemented at least partially in a data center; a system to perform hardware testing using simulations; a system to generate synthetic data; a system to perform generative operations using large language models (LLMs); A system for performing generative operations using a visual language model (VLM); A collaborative content creation platform for 3D assets; or A system implemented at least in part using cloud computing resources.

16. A system comprising: one or more processors to use a motion diffusion model to generate a representation of anthropomorphic motion corresponding to a text input, the motion diffusion model being updated using a discriminator that computes an alignment value between the text input and the representation of human motion, the alignment value to be used to determine an update to one or more network parameters for the motion diffusion model.

17. The system of claim 16, wherein, The one or more network parameters are updated as part of a reinforcement learning based training process to fine-tune the motion diffusion model.

18. The system of claim 16, wherein, The alignment value is computed based in part on a first encoding generated for the text input and a second encoding generated for the representation of human motion.

19. The system of claim 16, wherein, The text further includes at least one qualifier that indicates a type, style, or rate of performance of the motion.

20. The system of claim 16, wherein, The system comprises at least one of: a system for performing simulation operations; a system for performing simulation operations to test or validate autonomous machine applications; a system for performing digital twin operations; a system for performing optical transport simulation; a system for rendering graphical output; a system for performing deep learning operations; a system for performing generative operations using a large language model (LLM); a system for performing generative operations using a visual language model (VLM); a system implemented using edge devices; a system for generating or presenting virtual reality (VR) content; a system for generating or presenting augmented reality (AR) content; a system for generating or presenting mixed reality (MR) content; a system comprising one or more virtual machines (VMs); a system implemented at least in part in a data center; a system for performing hardware testing using simulation; a system 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