Scene graph generation of untagged data

Abstract

Methods for training and using a scene graph generator for transfer learning are presented. Scene graph generation techniques may decompose domain differences into various types of differences, e.g., may involve appearance, marking, and predictive differences. These differences may be reduced at least by aligning corresponding potential and output distributions using one or more gradient inversion layers (GRLs). The tagged differences may be resolved using self-pseudo statistics collected from the target data. Pseudo-statistics-based self-learning and confrontation techniques may be used to manage these differences without expensive supervision from real-world data sets.

Description

[0001] This invention patent application is a divisional application of the invention patent application filed on May 26, 2021, with application number 202180009426.1 and invention title "Generating Scene Graphs with Unlabeled Data".

[0002] Cross-reference to related applications

[0003] This PCT application claims priority to U.S. Provisional Patent Application Serial No. 63 / 030,734, filed May 27, 2020, and U.S. Patent Application No. 17 / 226,561, filed April 9, 2021, both of which are incorporated herein in their entirety for all intents and purposes. Background Technology

[0004] A growing number of applications and services rely on techniques such as object recognition and computer vision. To provide accurate results, these techniques often involve the generation of scene graphs and the learning of visual relationships between objects represented in image or video content. Traditional scene graph generation techniques depend on the availability of expensive annotations or labels. Attempting to generate scene graphs without such annotations (e.g., by using unlabeled real data) is a challenging task. Generating synthetic data is a viable alternative and has emerged as a promising direction for extending supervised learning, as the generated labels can be obtained from the data synthesis process. However, reliably performing complex tasks such as scene graph generation for networks or models trained on synthetic data remains challenging when evaluated against real data, due to issues involving performance lag or domain gaps. Attached Figure Description

[0005] Various embodiments according to this disclosure will be described with reference to the accompanying drawings, in which:

[0006] Figure 1A and Figure 1B Images that can be used to generate scene graphs according to at least one embodiment are shown;

[0007] Figure 2 A scene graph generation system according to at least one embodiment is shown;

[0008] Figure 3A and 3B Images and corresponding scene diagrams according to at least one embodiment are shown;

[0009] Figure 4A and 4B Images and corresponding scene diagrams according to at least one embodiment are shown;

[0010] Figure 5The process for training a scene graph generator according to at least one embodiment is illustrated;

[0011] Figure 6 Components of a system for generating a scene graph according to at least one embodiment are shown;

[0012] Figure 7A The inference and / or training logic according to at least one embodiment is illustrated;

[0013] Figure 7B The inference and / or training logic according to at least one embodiment is illustrated;

[0014] Figure 8 An example data center system according to at least one embodiment is shown;

[0015] Figure 9 A computer system according to at least one embodiment is shown;

[0016] Figure 10 A computer system according to at least one embodiment is shown;

[0017] Figure 11 At least a portion of a graphics processor according to one or more embodiments is shown;

[0018] Figure 12 At least a portion of a graphics processor according to one or more embodiments is shown;

[0019] Figure 13 This is an example data flow diagram of an advanced computing pipeline according to at least one embodiment;

[0020] Figure 14 This is a system diagram of an example system for training, adapting, instantiating, and deploying machine learning models in an advanced computing pipeline, according to at least one embodiment; and

[0021] Figure 15A and Figure 15B A data flow diagram of the process for training a machine learning model according to at least one embodiment is shown, along with an example illustration of a client-server architecture that leverages a pre-trained annotation model to enhance an annotation tool. Detailed Implementation

[0022] Methods according to various embodiments can provide the generation and use of scene graphs or other such data representations. Specifically, the embodiments relate to scene graph generation for transfer learning. Because conventional scene graph training methods utilize costly or difficult-to-obtain labeled data, it can be advantageous to utilize synthetic data that can provide labels at little or no additional cost. Unfortunately, models trained using synthetic data often perform poorly when running inference on real-world data, at least in part due to domain disparities. To overcome this disparity problem, scene generation techniques can be utilized that decompose domain disparities into individual types of differences, such as appearance, label, and prediction differences. This can include minimizing appearance and prediction differences by using gradient inversion layers to align the corresponding latent and output distributions. Label differences can be addressed using the principles of self-learning, but using pseudo-statistics collected from the target data and leveraging a synthetic data generator to produce accurate labels. Pseudo-statistical self-learning and adversarial techniques are used to manage these differences without the need for expensive supervision from real-world datasets.

[0023] When training a model or network to generate scene graphs, it may be desirable to generate scene graphs that correspond to inputs from different domains. In this context, a domain can refer to different settings, categories, styles, or spaces, among other such options. For example, the first set of images may include images taken at a first location (such as a metropolitan area in the United States). Figure 1A As shown in example image 100, these images may include specific types of objects of interest to a particular application, such as representations of vehicles 102 and pedestrians 104, as well as other such object types that may exist in such locations. These images may also include representations of other types of objects, including buildings, road signs, billboards, etc. For labeled data, this image may also include or have an associated set of bounding boxes that describe the approximate location or region of the image corresponding to the various instances of these object types of interest. These bounding boxes or other such location identifiers can be used to help train a model or network to recognize these types of objects in similar images. Then, when objects are surrounded by buildings and other types of objects represented in this general domain or in metropolitan areas of the United States, the network can learn to distinguish these objects with high accuracy.

[0024] However, it is possible to use such a trained model to perform similar classification or reasoning on data from different domains. This could include, for example, a domain corresponding to the European highlands, which could include, for example, domains such as... Figure 1BThe image shown is one of 150 images. As illustrated, these images can include very different types of backgrounds and other objects, such as mountains, farm animals, mountain cabins, and other objects that may have appearances very different from those present in the images from the first domain. While similar objects of interest may exist in these images from the second domain, the model or network may be less accurate in recognizing these objects and distinguishing them from surrounding image regions because the model was not trained using images with these representations. To improve the accuracy of such networks (e.g., scene graph generation networks), it may be necessary to train the network using data from both the first and second domains. However, in this example, the data from the second domain is unlabeled. As mentioned, traversing and manually annotating these images can be expensive and time-consuming, especially for the large number of images that may be needed to accurately train the model.

[0025] In some instances, synthetic images can be generated that include representations of objects of interest. Since scene graphs can be used, for example, to generate synthetic images, these synthetic images can include labels known for the types of objects included in these synthetic images. Images for specific domains, such as the European highlands, can also be synthesized. Unfortunately, this still results in different domains, as there will be images in a first domain (in this case, the synthetic domain) and images in a second domain (in this case, the "real" image domain). Thus, even if a model is trained on labeled synthetic images of the target domain, its performance may still be insufficiently accurate for real images captured or otherwise obtained for that target domain. As mentioned, this is largely due to domain disparities, which can include both content and appearance disparities. Appearance disparities can represent differences in the visual appearance between real images and synthetic images or images from different domains. Content disparities can represent differences in the placement, number, selection, and type of objects in an image, as well as other such options. In at least some embodiments, appearance disparities can be addressed by making the scene photorealistic (e.g., by using one or more image transformations, using feature alignment, or learning robust representations based on domain randomization). Methods can also be used to address content disparities in image classification.

[0026] Therefore, the methods according to various embodiments can provide scalable approaches for training scene graph generation models, networks, or other such methods to address this domain gap. These methods can further utilize both labeled synthetic data and unlabeled real data. The methods according to various embodiments can provide a tractable way to reduce appearance and content gaps that may occur between domains, such as between synthetic and real data. Such methods can also provide the learning of neural networks to generate scene graphs for unlabeled real images. This can include using synthetic data for learning to generate scene graphs (SGs) on real images or images from different domains. Such methods can utilize generation pipelines including pseudostatistics to manage domain gaps. In at least one embodiment, scene graph generation can be learned for various applications or scenarios, such as for computer vision, object recognition, or navigation assistance, and other such options. Applications can be extended to places where synthetic data can be generated using only a raw estimate of the distribution of the target dataset.

[0027] As mentioned above, scene graphs (SGs) can be used in applications such as computer vision and computer graphics to provide interpretable and structural representations of scenes. Scene graphs can be used to identify or generalize entities in a scene and the plausible relationships between or among them. Scene graphs can be presented as visual representations by inverting the graph. Scene graphs have proven beneficial for a variety of applications, including but not limited to image captioning, visual question answering, advanced reasoning tasks, image retrieval, image generation, etc. Much of the existing work on scene graph generation relies on the availability of expensive and limited labeled datasets, such as the Visual Genome and Visual Relationships Dataset (VRD). A significant limitation for at least some machine learning applications is the general lack of adequately labeled data for supervised learning tasks. Synthetic data can provide a viable alternative to this problem because annotation is essentially free as part of the synthesis process. Synthetic data has been used for a variety of tasks, such as image classification, object detection, semantic segmentation, optical flow modeling, 3D keypoint extraction, object pose estimation, and 3D reconstruction. Synthetic data has also shown effectiveness in initializing task networks and for data augmentation. Synthetic data has not yet been (at least not fully utilized) for scene graph generation and the representation of visual relationships.

[0028] In at least one embodiment, it can be assumed that gaps exist in both appearance and content, and these gaps can be extended to individual addressable sub-components. This approach can help reduce domain gaps in scene graph generation, and these techniques can also be applied to other vision-related tasks, such as image classification, image segmentation, and object detection. In at least one embodiment, a Simulation-to-Scene Graph (SimS2G) approach can be utilized, where the model learns simulation-to-real scene graph generation using labeled synthetic data and unlabeled real data. The Sim2SG approach addresses domain gaps by defining task errors (such as scene graph generation) on real data using appearance, prediction, and label (e.g., ground truth) differences between the two domains, as well as task errors on synthetic data. This approach minimizes appearance and prediction differences by aligning the corresponding latent and output distributions via one or more gradient inversion layers (GRL). In at least one embodiment, self-learning principles can be used to address labeling differences. However, pseudo-label-based self-learning can generate inaccurate labels that lead to performance problems. Therefore, the methods according to various embodiments can collect pseudo-statistics from target data and utilize a synthetic data generator to produce accurate labels.

[0029] Figure 2 An example pipeline 200 that can be used for scene graph generation is shown. As illustrated, this pipeline can receive input from at least two domains, such as a labeled synthetic image 202 and an unlabeled “real” or captured image 204. This example pipeline can operate in three stages, although other pipelines or implementations may use a single stage or other numbers of stages. In the first stage, the pipeline accepts the labeled synthetic image 202 or an image from a first domain and processes these images using an encoder 206 to determine relevant features of these images and encode those features into a latent space or representation 208. This pipeline can then process this latent space with a scene graph predictor 210 to attempt to generate an appropriate scene graph for each of those input images. In this example, both the encoder 206 and the scene graph predictor 210 can be neural networks, such as a convolutional neural network (CNN) for the encoder 206 and a generative neural network for the scene graph predictor 210. In this first state, the pipeline can learn to generate scene graphs from labeled synthetic images.

[0030] In the second stage, pipeline 200 can process the unlabeled real image 204. The unlabeled real image 204 is processed using encoder 206 to determine relevant features and encode those features into a latent space or representation, which here is a shared representation Z 208 serving as the features of both the labeled synthetic image 202 and the unlabeled real image 204. In at least one embodiment, encoder 206 maps the labeled synthetic image and the unlabeled real image to this shared representation Z 208. In at least one embodiment, the encoder may be a ResNet-101, ResNet-50, or VGGNet (e.g., VGG-16) network, and in at least some embodiments, different encoders may be used for different types or categories of input data.

[0031] In the third phase, the scene graph predictor model 210 generates one or more scene graphs from unlabeled real data in the shared latent space 208. One or more pseudo-statistics can then be computed for these scene graphs. In at least one embodiment, these pseudo-statistics may represent a high-level statistical description of the scene, which can then be fed back to the generator, in this case, the scene graph predictor 210. These pseudo-statistics can then be used to attempt to generate aligned scenes, where the synthetic data more closely simulates the real data, such as where the synthetic image has an appearance closer to that of a realistically captured image. This aligned data (e.g., may include the generated scene graph data 216) can then be fed to the renderer (for image data) and used as additional data for training the encoder 206 and the generator or scene graph predictor 210 (e.g., a graph convolutional network). This data can be used to retrain these networks for another epoch. After this additional training, the network can be used to generate another round of aligned data, and this process can continue until termination criteria are met, such as network converging, reaching a maximum number of training iterations or epochs, or all training data used for training, and other such options.

[0032] In this process, a scene graph prediction network P can be trained on a shared representation Z using synthetic data. Domain disparities can be bridged by aligning features in the representation space Z (for appearance disparities) using the first gradient inversion layer (GRL) 212 and features in the output space (for content disparities) using the second GRL 214, together with a domain discriminator. Using pseudo-statistical self-learning, the labeled disparities (for content disparities) can be aligned between the two domains. Note that the arrows in the figure correspond to the flow of synthetic data, real data, and / or backpropagation. The GRL can be a feature layer preceding the final scene graph prediction layer, where the type of discriminator will attempt to determine the domain of the features, such as whether they correspond to the real or synthetic domain.

[0033] Such methods can be beneficial, at least because initial scene graph predictions based on synthetic pre-training will not be accurate, and this inaccuracy is at least partly due to domain disparities. After the initial scene graph predictions, pseudostatistics can be identified, such as the number or layout of objects in the scene, and this can be used to help generate slightly more aligned data in the next iteration or epoch. Better aligned data helps improve the performance of the synthetic prediction network, as well as the performance of predicting or obtaining pseudostatistics from the real data. Over time, this self-learning-based approach can predict data that is increasingly aligned with the real data, causing the network to converge and the synthetic data to be a very accurate representation of the real data.

[0034] As mentioned, in the third state, this synthetic data, which now accurately resembles the real data, can have appearance and predictive features aligned between the two domains. A GRL can be used for both appearance and prediction losses, and the distribution of features is matched at the encoder level and at the output level. Using such a process, appearance alignment will effectively generate features that are either invariant or appearance-invariant in both domains. The prediction loss can also be used to teach the network to be consistent in both domains. Once trained, a set of features classified as "chair" in domain A should also be classified as "chair" in domain B, which helps to align with the prediction loss.

[0035] In at least one embodiment, the SG predictor module can be trained using labels from the source domain. In at least one embodiment, the scene graph can be effectively a set of bounding boxes used as nodes of a graph, where the edges of the graph represent relationships between those objects. The scene graph of a given image I can be labeled as a graph G with nodes o and edges r. Nodes can be bounding boxes b. i ={xmin i ,ymin i ,w i ,h i} and category c i tuple o i = i ,c i >. Relation r is <o i ,p,o j The triple of >, where p is the predicate. In at least one embodiment, scene graph prediction has at least two key components, including an extractor. P-plot predictor and extractor The input space x is mapped to the latent space z, and the predictor P is mapped from the latent space z to the output space y(G). The predicted SG is Networks such as Resnet-101 can be used to implement Furthermore, architectures such as GraphRCNN are used to implement P. These networks can be trained using the following task losses. ​And P: Cross-entropy loss for object classification and relation classification, and L1 loss for bounding boxes, as shown in... Figure 2 As discussed. In at least some embodiments, relationships between objects in a scene are predicted, but their attributes are not.

[0036] In at least one embodiment, the domain gap between the source and target domains can be analyzed to formulate the task error on the real domain (e.g., for SG generation) as a function of the task error on the synthetic domain, as well as the appearance and content gaps between the domains. Each sub-component of the domain gap can then be resolved.

[0037] In the example representing the domain difference, two domains will be discussed, including the synthetic domain. <x s ,y s ~p(x,y) and the real domain <x r ,y r >~q(x,y). In this example, y r It is unknown. This example also assumes that the synthetic domain and the real domain contain objects of the same class. The two domains also share similar scenarios (e.g., both have driving scenarios). However, the joint distribution of scenarios (e.g., images) is different in the two domains (i.e., p(x) ≠ q(x)). The distribution of labels (e.g., truth values) is also different in the two domains (i.e., p(y) ≠ q(y)). The task (e.g., SG generation) error can then be represented in the synthetic domain as a function of the latent space z:

[0038]

[0039] Among them, e s It is defined as e s =|p(y|z)–y s |The risk. Here, p(z) represents the distribution of features, p(y) is the distribution of labels, and p(y|z) is the output distribution. Since labels y are accessible... s Therefore, task errors can be minimized. However, the label distribution q(y) of the real domain may not be accessible. Therefore, task errors or risks can be addressed in the real domain through easily tractable components such as... Binding in the middle:

[0040]

[0041] Using the simplifications in the above equations, we can show that the task error in the real domain is a function of three terms: the task error in the synthetic domain. Feature differences between two domains and the risk differences between domains For the sake of simplicity, terminology P will be discarded from the continued discussion. Since features often consider appearance, feature differences ∈ a This can be termed the appearance difference and is empirically demonstrated through ablation. Similarly, the risk difference ∈ c Ablation can be related to content gaps. Nevertheless, a method according to at least one embodiment can attempt to make ∈ s ,∈ a and ∈ c Minimize to reduce task errors in the real domain. If the error ∈ r If the reduction to zero over the target domain is achieved, then the method has effectively closed the domain gap. The first term ∈ s It can be direct to minimize what is discussed here.

[0042] Regarding the second term, appearance gap refers to the difference in appearance between two domains. This can include, for example, differences in the texture, color, lighting, and reflectivity of objects in a scene. To address appearance gap, one approach attempts to avoid photorealistic representations in synthetic data, as this may require high-quality assets and significant effort from artists. Therefore, appearance-invariant representations z can be learned to avoid appearance biases in the model. However, feature z: It has both content and appearance components, and aligning these features can be detrimental. To overcome this challenge, only when aligning the content gap between these two domains ∈ c Only then can the appearance difference be aligned. a As discussed here, this appearance difference can be made ∈ by aligning the feature distributions p(z) and q(z) as follows. a Minimize:

[0043] θ * =arg θ min∫(q(z)-p(z))e s dz

[0044] This utilizes the fact that p(z) ≡ q(z) is such that ∈ a The sufficient condition for the value to be zero. Gradient inversion layers (GRL) can be used to align distributions p(z) and q(z) together with a domain classifier D to classify them. The loss on D can be minimized with respect to its own parameters, while also minimizing the loss with respect to the network parameters. Maximize. This can be done using a GRL, which acts as an identity function during forward propagation and from D to... The sign of the gradient is flipped during backpropagation.

[0045] Regarding the third point, content gap refers to the difference between two domains, including differences in the number of objects and their classes, layouts, poses, and distributions of extensions. This can lead to issues with token offsets or truth value distributions. It is expected that this content gap will be understood in at least some embodiments. Since minimizing ∈ in the current form... c It is unmanageable, therefore the risk difference (e) r -e s It can be reduced as follows:

[0046] arg θ min∈ c =arg θ min∫q(z)(y s -y r )dz+∫q(z)(q(y|z)-p(y|z))dz

[0047] =arg θ min∈ c,label +∈ c,pred

[0048] We can assume that the risk is positive, and that risk dependence is further divided into labeled differences ∈ c,pred .

[0049] To address the prediction discrepancy ∈ c,pred The output distributions can be aligned for latent codes belonging to the same visual category. This is reasonable because the outputs of scene graph generation models should be identical for the same category in different domains. Terms ∈ can be handled by aligning the output distributions p(y|z) and q(y|z) using the same GRL-based technique discussed earlier. c,pred .

[0050] On the other hand, minimizing ∈ c,label It can be challenging because there may not be a label for the target (e.g., the real) domain (y). r Access to ) . In at least one embodiment, self-learning using pseudostatistics can be used to obtain an estimate of the label distribution for obtaining real data. Pseudo-label-based self-learning may produce inaccurate labels due to prediction inaccuracies when evaluated across different domains. However, the method proposed herein can use a synthetic data generator to produce accurate labels. It can be noted that pseudostatistical methods can be orthogonal to pseudo-label-based self-learning, and the latter can potentially be combined with it.

[0051] In at least one embodiment, the marker alignment ∈ c,label At least in part by targeting the target domain All N scenarios (x r It generates N scene graphs (SGs) to work. For each predicted SG... Where k∈{1,...,N}, pseudostatistics ps can be extracted. k Statistics on ps k Including objects {o1, o2, ..., o j A list of {r1, r2, ..., r} and the relationships between them. j ...}. Each object o j With bounding box b j and its associated category c j And each relation triple r j It has two objects and a predicate as described in this article. This pseudo-statistic can then be used to create a scene using a synthetic data generator. It can be based on the category c of the first object. j From ps k Select the first object. Then, assets can be randomly selected from that category, and their 2D bounding boxes can be set using camera parameters. j Project it onto the 3D scene. If available, camera parameters from the target data can be used, or careful assumptions related to height or pitch can be made.

[0052] The pose can be chosen intelligently or randomly. For example, in a driving simulation environment, the bounding box of the car... j The aspect ratio can be used to align it with the lane (0° or 180° rotation) or rotate it 90°. The same steps can be repeated for each object in the scene. These relationships can then be used for fine-tuning and correcting the object's position and pose.

[0053] For example, in a restaurant simulation environment, there may be different objects visible in the scene, such as table 302, chairs 304, 306, 308, and laptops 310 and 312 visible in image 300, such as... Figure 3A As shown. In at least one embodiment, the "on..." relation can be used to specify that a laptop computer is placed on a table. Different assumptions can be made, such as a flat ground plane, all objects remaining on the ground, minimal background (e.g., walls, ground, road, or other objects), and a real-world scale. The view of the 3D scene can then be rendered using a compositing data generator to obtain a composite image 300 and a ground truth x. s y s It can provide all statistical ps k Synthetic data is generated to train the encoding and generative networks in the next epoch. This can be called self-learning because predictions of unlabeled targets are used to generate synthetic data similar to the targets, and the model is trained with new data in the next epoch. Figure 3BAn exemplary scene diagram 350 is shown that can be used to generate such a scene, indicating the positional relationship between the chair and the laptop computer and the table 302. Various other scene diagrams can also be generated for such scenes within the scope of the various embodiments.

[0054] Figure 4A and 4B Another example image and scene diagram, which can be generated according to various embodiments, are shown respectively. Figure 4A In example image 400, there are three objects represented: a cylinder 402, a cube 404, and a sphere 406. For example... Figure 4B As shown, the exemplary scene graph 450 corresponding to this scene may include positional relationship information for each pair of objects in the scene, rather than relative to a single object in the scene. Such a scene graph may contain redundant information, such as a cylinder to the right of a cube and a cube to the left of a cylinder, but such a method can provide many paths that can be used to generate and examine the relationships used to generate the scene from the scene graph.

[0055] In at least one embodiment, the process for training one or more networks (e.g., as part of the SimS2G pipeline) may assume the availability of an encoder and scene graph predictor, as well as synthetic images, synthetic tags, a data generator, and real images. For a given number of iterations or epochs, an attempt can be made to minimize a loss function that includes appearance gaps, content prediction gaps, and a loss term for the scene graph generation task. After appropriate network parameters have been tuned to minimize the loss, suitable pseudo-statistics can be extracted from the predictions, and synthetic data can be generated using tags aligned with the real data.

[0056] Figure 5An example process 500 for training a scene graph generation model according to at least one embodiment is illustrated. This process may utilize a loss function for terms having the appearance, content, and SG generation terms described above. In this example, a set of labeled synthetic data and a set of unlabeled "real" or non-synthetic data are obtained 502. This data may be input to at least one encoder network that extracts features from these datasets and encodes them 504 into shared representations, such as a shared latent space. This latent space may be provided as input 506 to train a scene graph prediction network that predicts scene graphs based on features from the latent space. In this example, the features in this latent space may be aligned with the output space of the scene graph prediction network. This can result in alignment of real and synthetic features, making the synthetic data (e.g., images) generated using inference from the scene graphs indistinguishable from the real data. As mentioned above, this can also be used to minimize gaps between other domains. The labels of objects in these scene graphs may also be aligned 510 using pseudo-statistical self-learning as discussed herein, such that synthetic data with labels aligned with the labels of the real data can be produced. A 512-scene graph generation model can be trained until termination criteria are met, such as network fusion or a training process for a defined number of epochs (e.g., three epochs). Once trained, the pipeline can be used for various purposes, such as generating synthetic data for simulation or other similar purposes. This approach can also be used to generate scene graphs from unlabeled data from different domains. Given data on a real-world scene without data labels, labeled versions of the scene graph can be generated that can be used to synthesize that scene.

[0057] Such a method can be beneficial for any content creation application, such as online games, where generating realistic synthetic data may be desired. This method can also be used to automatically build simulated environments, which could be useful for robotics or navigation simulations. The methods according to the various embodiments are not limited to scene graphs but can be used with any relevant representations of two or more domains, especially where labeled training data is insufficient for one of the domains. Applications that can benefit from such capabilities include area / room scanning, security, spatial analysis, anomaly detection, and realistic simulation, among many others.

[0058] As an example, Figure 6An example network configuration 600 that can be used to provide or generate content is shown. In at least one embodiment, client device 602 can generate session content using components of content application 604 on client device 602 and data locally stored on the client device. In at least one embodiment, content application 624 (e.g., image generation or editing application) executing on content server 620 (e.g., cloud server or edge server) can initiate a session associated with at least client device 602, such as by utilizing a session manager and user data stored in user database 634, and content 632 can be determined by content manager 626, rendered using a rendering engine (if required by this type of content or platform), and sent to client device 602 using appropriate transport manager 622 for transmission via download, streaming, or other such transport channels. In at least one embodiment, the content 632 may include assets that a rendering engine can use to render a scene based on a determined scene graph. Content server 620 may also include one or more training modules 630 for training scene graph generation components, networks, or pipelines 628. In at least one embodiment, the client device 602 receiving the content may provide the content to a corresponding content application 604, which may also include, or alternatively include, a rendering engine (if desired) for rendering at least some of the content for presentation via the client device 602, such as image or video content via display 606 and audio, such as sound and music, via at least one audio playback device 608 (such as a speaker or headphones). For example, such a rendering engine may not be necessary for real-time video content captured by one or more cameras unless it is used to enhance the video content in some way.

[0059] In at least one embodiment, at least some of the content may have already been stored on, rendered on, or made accessible to the client device 602, such that at least that portion of the content does not require transmission over network 640, as in cases where the content may have previously been downloaded or locally stored on a hard drive or optical disc. In at least one embodiment, a transmission mechanism such as data streaming may be used to transfer the content from content server 620 or content database 634 to client device 602. In at least one embodiment, at least a portion of the content may be obtained from or streamed from another source, such as a third-party content service 660, which may also include a content application 662 for generating or providing the content. In at least one embodiment, a portion of the functionality may be performed using multiple computing devices or multiple processors within one or more computing devices, such as a combination of CPU and GPU.

[0060] In at least one embodiment, content application 624 includes content manager 626, which can determine or analyze content before transmitting it to client device 602. In at least one embodiment, content manager 626 may also include or work with other components capable of generating, modifying, or enhancing the content to be provided. In at least one embodiment, this may include a rendering engine for rendering image or video content. In at least one embodiment, image, video, or scene graph generation component 628 may be used to generate scene graphs, which may be used by content application 624 on the server or content application 604 on the client device to generate image, video, or other media content. In at least one embodiment, enhancement component 630 (which may also include a neural network) may perform one or more enhancements on the content, as discussed and suggested herein. In at least one embodiment, content manager 626 may enable the content to be transmitted to client device 602. In at least one embodiment, content application 604 on client device 602 may also include components such as a rendering engine, scene graph generator 612, and content generation module, such that any or all of these functions may be additionally or alternatively executed on client device 602. In at least one embodiment, the content application 662 on the third-party content service system 660 may also include such functionality. In at least one embodiment, the location where at least some of this functionality is performed may be configurable or may depend on factors such as the type of client device 602 or the availability of a network connection with appropriate bandwidth. In at least one embodiment, the system for content generation may include any suitable combination of hardware and software in one or more locations. In at least one embodiment, the generated image or video content at one or more resolutions may also be provided to or made available to other client devices 650, such as for downloading or streaming from a media source storing a copy of the image or video content. In at least one embodiment, this may include transmitting images of game content for a multiplayer game, wherein different client devices may display the content at different resolutions, including one or more super-resolutions.

[0061] In this example, these client devices can include any suitable computing device, such as desktop computers, laptops, edge devices, set-top boxes, streaming devices, game consoles, smartphones, tablets, VR headsets, AR goggles, wearable computers, or smart TVs. Each client device can submit requests across at least one wired or wireless network, such as the Internet, Ethernet, a local area network (LAN), or a cellular network, among other such options. In this example, these requests can be submitted to an address associated with a cloud provider, which can operate or control one or more electronic resources within the cloud provider's environment, such as data centers or server clusters. 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's 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's environment.

[0062] 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.

[0063] Reasoning and training logic

[0064] 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.

[0065] 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.

[0066] 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-addressable memory (“DRAM”), static random-addressable memory (“SRAM”), non-transitory 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. In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, the code and / or data storage 705 to store inverse and / or output weights and / or input / output data neural networks corresponding to neurons or layers of a neural network trained and / or used for inference in aspects of one or more embodiments. In at least one embodiment, during training and / or inference using aspects of one or more embodiments, code and / or data storage 705 is stored in the weight parameters and / or input / output data of each layer of the neural network trained or used in conjunction with the input / output data and / or weight parameters during backpropagation of the neural network using one or more embodiments. 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 referred to as Arithmetic Logic Units (ALUs)).

[0067] In at least one embodiment, code (such as graph code) loads weights or other parameter information into the processor ALU based on the architecture of the neural network corresponding to the code. 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-transitory 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.

[0068] 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.

[0069] 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.

[0070] In at least one embodiment, one or more ALUs 710 are included in one or more processors or other hardware logic devices or circuits, while in another embodiment, one or more ALUs 710 may be located outside the processor or other hardware logic device or the circuitry that uses them (e.g., a coprocessor). In at least one embodiment, 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 in different processors or other hardware logic devices or circuitries, or in some combination of the same and different processors or other hardware logic devices or circuitries. In at least one embodiment, any portion of activation storage 720 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Furthermore, the inference and / or training code may be stored alongside 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. In at least one embodiment, the active memory 720 may be a cache memory, DRAM, SRAM, non-transitory memory (e.g., flash memory), or other storage. In at least one embodiment, the active memory 720 may be wholly or partially located within or outside one or more processors or other logic circuitry. 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 availability of 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, or may include DRAM, SRAM, flash memory, or other storage types.

[0071] 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 7AThe 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”)

[0072] 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 7B 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 (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.

[0073] 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.

[0074] Data Center

[0075] 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.

[0076] In at least one embodiment, such as Figure 8 As shown, the data center infrastructure layer 810 may include a resource coordinator 812, packet 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.

[0077] In at least one embodiment, the grouped computing resource 814 may include individual groups (not shown) of node CRs housed within one or more racks, or a plurality of racks (also not shown) housed within data centers in various geographic locations. The individual groups of node CRs within the grouped computing resource 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.

[0078] 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.

[0079] In at least one embodiment, such as Figure 8 As 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, which can utilize distributed file system 828 for large-scale data processing (e.g., "big data"). TM(Hereinafter referred to as "Spark"). In at least one embodiment, the job scheduler 832 may include a Spark driver to facilitate the scheduling of workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be able to configure different layers, such as the software layer 830 and the framework layer 820, which includes Spark and a distributed file system 828 for supporting large-scale data processing. In at least one embodiment, the resource manager 826 is able to manage cluster or group computing resources mapped to or allocated to support the distributed file system 828 and the job scheduler 822. In at least one embodiment, the cluster or group computing resources may include group computing resources 814 on the data center infrastructure layer 810. In at least one embodiment, the resource manager 826 may coordinate with the resource coordinator 812 to manage these mapped or allocated computing resources.

[0080] 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.

[0081] In at least one embodiment, one or more applications 842 included in application layer 840 may include one or more types of applications used by at least a portion of nodes CR816(1)-816(N), grouped computing resources 814, and / or the distributed file system 828 of framework layer 820. 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. This document combines... 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 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.

[0086] Such components can be used to train one or more generative models to generate scene graphs for unlabeled data, as well as to generate scenes based on scene graphs that are indistinguishable from real-world scenes.

[0087] Computer System

[0088] Figure 9This 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 one available from Intel Corporation of Santa Clara, California. Processor family, Xeon TM , XScale TM and / or StrongARM TM , 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.

[0089] 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.

[0090] In at least one embodiment, the computer system 900 may include, but is not limited to, a processor 902, which may include, but is not limited to, one or more execution units 908, to perform machine learning model training and / or inference according to the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, but in another embodiment, the computer system 900 may be a multiprocessor system. In at least one embodiment, the processor 902 may include, but is not limited to, a Complex Instruction Set Computer (“CISC”) microprocessor, a Reduced Instruction Set Computing (“RISC”) microprocessor, a Very Long Instruction Word (“VLIW”) microprocessor, a processor implementing instruction set combination, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which can transmit data signals between the processor 902 and other components in the computer system 900.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] In at least one embodiment, Figure 9 A system including interconnected hardware devices or "chips" is shown, while in other embodiments, Figure 9 An 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.

[0097] 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.

[0098] Such components can be used to train one or more generative models to generate scene graphs for unlabeled data, as well as to generate scenes based on scene graphs that are indistinguishable from real-world scenes.

[0099] Figure 10This 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.

[0100] In at least one embodiment, system 1000 may include, but is not limited to, processor 1010 communicatively coupled to any suitable number or type of components, peripherals, modules, or devices. In at least one embodiment, processor 1010 uses a bus or interface coupling, such as an I2C bus, system management bus (“SMBus”), low pin count (LPC) bus, serial peripheral interface (“SPI”), high-definition audio (“HDA”) bus, serial advanced technology accessory (“SATA”) bus, universal serial bus (“USB”) (versions 1, 2, and 3), or universal asynchronous receiver / transmitter (“UART”) bus. In at least one embodiment, Figure 10 The system shown includes interconnected hardware devices or "chips," while in other embodiments, Figure 10 An exemplary system-on-a-chip (SoC) can be illustrated. In at least one embodiment, Figure 10 The device shown can be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, Figure 10 One or more components are interconnected using Computational Fast Link (CXL) interconnects.

[0101] 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.

[0102] 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).

[0103] 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 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.

[0104] Such components can be used to train one or more generative models to generate scene graphs for unlabeled data, as well as to generate scenes based on scene graphs that are indistinguishable from real-world scenes.

[0105] 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.

[0106] 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.

[0107] In at least one embodiment, each of the one or more processors 1102 includes 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 particular set of instructions 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, each processor core 1107 may process a different set of instructions 1109, which may include instructions that facilitate emulation of other instruction sets. In at least one embodiment, the processor core 1107 may also include other processing devices, such as a digital signal processor (DSP).

[0108] 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.

[0109] 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 input / output (I / O) devices via a local I / O bus.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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 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 of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0114] Such components can be used to train one or more generative models to generate scene graphs for unlabeled data, as well as to generate scenes based on scene graphs that are indistinguishable from real-world scenes.

[0115] 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.

[0116] In at least one embodiment, internal cache units 1204A-1204N and shared cache unit 1206 represent a cache memory hierarchy within processor 1200. In at least one embodiment, cache memory units 1204A-1204N may include at least one level of instruction and data cache within each processor core and one or more levels of cache in a shared intermediate cache, such as Level 2 (L2), Level 3 (L3), Level 4 (L4), or other levels of cache, wherein the highest level of cache preceding external memory is classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between the various cache units 1206 and 1204A-1204N.

[0117] 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).

[0118] In at least one embodiment, one or more processor cores 1202A-1202N include support for multi-threaded concurrent processing. In at least one embodiment, system agent core 1210 includes components for coordinating and operating cores 1202A-1202N during multi-threaded processing. In at least one embodiment, system agent core 1210 may additionally include a power control unit (PCU) including logic and components for regulating one or more power states of processor cores 1202A-1202N and graphics processor 1208.

[0119] 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.

[0120] In at least one embodiment, ring-based interconnect unit 1212 is used to couple internal components of processor 1200. In at least one embodiment, alternative interconnect units, such as point-to-point interconnects, switched interconnects, or other technologies, may be used. In at least one embodiment, graphics processor 1208 is coupled to ring interconnect 1212 via I / O link 1213.

[0121] 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.

[0122] 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.

[0123] 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 1512, graphics core 1202A-1202N, or other components are used. Furthermore, in at least one embodiment, the inference and / or training operations described herein can use, except... Figure 7A or Figure 7B The logic is performed using logic other than that shown. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALU of the graphics processor 1200 to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0124] Such components can be used to train one or more generative models to generate scene graphs for unlabeled data, as well as to generate scenes based on scene graphs that are indistinguishable from real-world scenes.

[0125] Virtualization computing platform

[0126] 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.

[0127] 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.

[0128] In at least one embodiment, the model registry 1324 may be supported by an object storage system that supports version control and object metadata. In at least one embodiment, it may be available from within a cloud platform via, for example, cloud storage (e.g., Figure 14 The system uses a cloud-compatible application programming interface (API) to access object storage. In at least one embodiment, machine learning models within the model registry 1324 can be uploaded, listed, modified, or deleted by the developer or partner of the system interacting with the API. In at least one embodiment, the API can provide access to methods that allow users with appropriate credentials to associate models with applications, enabling the models to be executed as part of the containerized instantiation of the application.

[0129] In at least one embodiment, training pipeline 1404 ( Figure 14 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 devices, sequencing devices, and / or other types of devices can be received. In at least one embodiment, once the imaging data 1308 is received, AI-assisted annotation 1310 can be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for the machine learning model. In at least one embodiment, AI-assisted annotation 1310 can include one or more machine learning models (e.g., convolutional neural networks (CNNs)) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, AI-assisted annotation 1310 can then be used directly or adjusted or fine-tuned using annotation tools to generate ground-based data. In at least one embodiment, AI-assisted annotation 1310, labeled clinical data 1312, or a combination thereof can be used as ground-based data for training the machine learning model. In at least one embodiment, the trained machine learning model may be referred to as output model 1316 and may be used by deployment system 1306 as described herein.

[0130] In at least one embodiment, training pipeline 1404 ( Figure 14This may include situations 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 transfer of the imaging data from off-site locations. In at least one embodiment, once a model has been trained or partially trained at a location, a machine learning model may 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 (and referred to as output model 1316) can then be selected from model registry 1324, and can be executed in deployment system 1306 for one or more processing tasks for one or more applications of the deployment system.

[0131] In at least one embodiment, in training pipeline 1404 ( Figure 14In this scenario, 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 clinical 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 14 System 1400 may support at least some services 1320. In at least one embodiment, since DICOM objects may contain one to hundreds of images or other data types, and due to variations in the data, the developer may be responsible for managing (e.g., setting up constructs for preprocessing built into the application, etc.) the extraction and preparation of incoming data. In at least one embodiment, once verified by system 1400 (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).

[0136] In at least one embodiment, the developer can then share the application or container over a network for the system (e.g., Figure 14The system 1400 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 the request is processed. 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).

[0137] 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 14The parallel computing platform 1430 in the system can be well scaled. In at least one embodiment, it is not required that every application providing the same functionality as service 1320 must have a corresponding instance of service 1320, but 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 also be 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.

[0138] 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. 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.

[0139] 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 further 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 system) may be used as a hardware abstraction and extension 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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 respective 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.

[0144] 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.

[0145] 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 using drawing programs (e.g., annotation programs), computer-aided design (CAD) programs, labeling 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., labelers or annotation experts, defining the location 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), corresponding ground reality data generated by training system 1304 may exist. 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.

[0146] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or certified API that can invoke (e.g., call) an application or container from an external environment (e.g., facility 1302). In at least one embodiment, the application may then invoke or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with their respective applications, and the software 1318 and / or service 1320 may utilize the hardware 1322 to perform processing tasks efficiently and effectively.

[0147] 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.

[0148] 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.

[0149] In at least one embodiment, deployment system 1306 may include user interface 1414 (e.g., graphical user interface, web interface, etc.) which may be used to select applications to be included in deployment pipeline 1410, deploy applications, modify or change applications or their parameters or configurations, use and interact with deployment pipeline 1410 during setup and / or deployment, and / or otherwise interact with deployment system 1306. In at least one embodiment, although not shown with respect to training system 1304, user interface 1414 (or different user interfaces) may 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.

[0150] In at least one embodiment, in addition to the application coordination system 1428, a pipeline manager 1412 may also be used to manage interactions between applications or containers deploying 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 (e.g., as...) Figure 13 and Figure 14 As shown, pipeline manager 1412 may be included in service 1320. In at least one embodiment, application coordination system 1428 (e.g., Kubernetes, DOCKER, etc.) may include 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 (e.g., rebuilding applications, splitting applications, etc.) from deployment pipeline 1410 with individual containers, each application can execute in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0151] 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.

[0152] 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 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 use the same data from a shared memory segment of the parallel computing platform 1430 (e.g., where multiple different stages of one or more applications are processing the same information). 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.

[0153] 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 from 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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 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.).

[0159] In at least one embodiment, hardware 1322 may include GPU 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 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 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 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.

[0160] 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 GPU-optimized software (e.g., a software stack) that can be executed using multiple GPUs 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.

[0161] 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 extension 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.

[0162] 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 14System 1400 executes process 1500. In at least one embodiment, process 1500 may utilize services 1320 and / or hardware 1322 of system 1400, as described herein. In at least one embodiment, the refined model 1512 generated by process 1500 may be executed by deployment system 1306 for one or more containerized applications in deployment pipeline 1410.

[0163] In at least one embodiment, model training 1314 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 finely tuned parameters (e.g., weights and / or biases) retained from previous training, so training or retraining 1314 may not require as much time or processing as training the model from scratch. In at least one embodiment, during model training 1314, by resetting or replacing the output or loss layer of the initial model 1504, on a new customer dataset 1506 (e.g., new input data, such as customer dataset 1506, and / or new ground reality data associated with the input data), the initial model 1504 may be retrained or updated. Figure 13 When generating predictions on image data (1308), the parameters of the new dataset can be updated and readjusted based on the loss calculation associated with the accuracy of the output or loss layer.

[0164] In at least one embodiment, the pre-trained model 1406 may be stored in a data storage or registry (e.g., Figure 13(Model registry 1324). In at least one embodiment, the pre-trained model 1406 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 1406 may have been trained locally using locally generated customer or patient data. In at least one embodiment, the pre-trained model 1406 may be trained using cloud 1426 and / or other hardware 1322, but confidential, privacy-protected patient data may not be transferred to, used by, or accessed by any component of cloud 1426 (or other non-local hardware). In at least one embodiment, if the pre-trained model 1406 is trained using patient data from more than one facility, the pre-trained model 1406 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 1406 locally and / or externally, such as in a data center or other cloud computing infrastructure.

[0165] In at least one embodiment, when selecting an application for use in deployment pipeline 1410, 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 1406 to use with the application. In at least one embodiment, the pre-trained model 1406 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 1406 may be updated, retrained, and / or fine-tuned for use at various facilities before being deployed to deployment pipeline 1410 for use with one or more applications.

[0166] In at least one embodiment, a user may select a pre-trained model 1406 to be updated, retrained, and / or fine-tuned, and the pre-trained model 1406 may be referred to as the initial model 1504 of the training system 1304 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 1314 (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, ground-based data (e.g., such as...) may be generated at the facility at least in part by clinicians, scientists, physicians, practitioners, etc. Figure 13 Clinical data marked in 1312).

[0167] In at least one embodiment, AI-assisted annotation 1310 may be used in some examples to generate ground reality data. In at least one embodiment, AI-assisted annotation 1310 (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted ground reality data for a customer dataset. In at least one embodiment, user 1510 may use the annotation tool within a user interface (graphical user interface (GUI)) on computing device 1508.

[0168] 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.

[0169] 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 1314. 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 within one or more deployment pipelines 1410 at the facility to perform one or more processing tasks related to medical imaging data.

[0170] In at least one embodiment, the refined model 1512 can be uploaded to the pre-trained model 1406 in the model registry 1324 for selection by another facility. In at least one embodiment, this process can be completed at any number of facilities, allowing the refined model 1512 to be further refined any number of times on a new dataset to generate a more general model.

[0171] Figure 15B This is an example illustration of a client-server architecture 1532 for enhancing an annotation tool using a pre-trained annotation model, according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 may be instantiated based on the client-server architecture 1532. In at least one embodiment, the annotation tool 1536 in an imaging application can assist 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 1310, 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 15B The AI-assisted annotation tool 1536B can be enhanced by making API calls (e.g., API call 1544) to a server (such as annotation assistant server 1540), which may include a set of pre-trained models 1542 stored, for example, in an annotation model registry. In at least one embodiment, the annotation model registry may store pre-trained models 1542 (e.g., machine learning models, such as deep learning models) that have been pre-trained to perform AI-assisted annotation on specific organs or abnormalities. In at least one embodiment, these models can be further updated using a training pipeline 1404. In at least one embodiment, the pre-installed annotation tool can be improved over time as new labeled clinical data 1312 is added.

[0172] Such components can be used to train one or more generative models to generate scene graphs for unlabeled data, as well as to generate scenes based on scene graphs that are indistinguishable from real-world scenes.

[0173] Other variations are within the spirit of this disclosure. Therefore, although the disclosed technology is readily adaptable to various modifications and alternative constructions, certain embodiments thereof are illustrated in the accompanying drawings and have been described in detail above. However, it should be understood that the disclosure is not intended to be limited to one or more specific forms disclosed, but rather, it is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of this disclosure as defined in the appended claims.

[0174] 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 the corresponding set does not necessarily mean an appropriate subset of the corresponding set, but rather that the subset and the corresponding set can be equal.

[0175] 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”.

[0176] 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 are 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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: Receive the unlabeled real data corresponding to the first field; The scene graph prediction network is used to generate labeled synthetic data corresponding to the first domain, wherein the scene graph prediction network is updated at least using labeled synthetic data corresponding to the second domain; as well as One or more synthetic images are generated based on at least the generated labeled synthetic data corresponding to the first domain.

2. The computer-implemented method according to claim 1 further includes: A scene graph is generated by aligning one or more features in the latent space with one or more features in the output space corresponding to the scene graph prediction network using at least one of the following: one or more gradient inversion layers (GRL) or a domain discriminator; as well as The one or more synthetic images are generated based on at least the generated scene graph.

3. The computer-implemented method as described in claim 1, wherein, Generating one or more synthetic images based at least on the labeled synthetic data corresponding to the first domain reduces one or more differences in at least one of the following: the appearance or content between the labeled synthetic data corresponding to the first domain and the unlabeled real data.

4. The computer-implemented method as described in claim 1, wherein, The generation of the one or more synthetic images is also based on self-learning using pseudo-statistics to align the labels between the unlabeled real data and the labeled synthetic data corresponding to the first domain.

5. The computer-implemented method as described in claim 1, further comprising: Receive image; as well as The scene graph prediction network is used to generate a scene graph of the image.

6. The computer-implemented method as described in claim 1, wherein, The simulation environment is constructed using one or more synthetic images.

7. The computer-implemented method as described in claim 1, further comprising: The scene graph prediction network is used to generate scene graphs; as well as One or more composite images are generated based on the generated scene graph.

8. The computer-implemented method as described in claim 1, further comprising: Render the one or more composite images into a three-dimensional scene view.

9. The computer-implemented method as described in claim 2, wherein, Aligning one or more features reduces the appearance difference between the labeled synthetic data and the unlabeled real data.

10. A processor, comprising: One or more circuits are used for: Receive the unlabeled real data corresponding to the first field; The scene graph prediction network generates labeled synthetic data corresponding to the first domain, wherein the scene graph prediction network is trained using labeled synthetic data corresponding to the second domain. as well as One or more synthetic images are generated based on at least the generated labeled synthetic data corresponding to the first domain.

11. The processor of claim 10, wherein, At least one of the one or more circuits is configured to: A scene graph is generated by aligning one or more features in the latent space with one or more features in the output space of the scene graph prediction network using at least one of the following: one or more gradient inversion layers (GRL) or a domain discriminator; as well as The one or more synthetic images are generated based on at least the generated scene graph.

12. The processor of claim 10, wherein, Generating one or more synthetic images based at least on the labeled synthetic data corresponding to the first domain reduces one or more differences in appearance and content between the labeled synthetic data corresponding to the first domain and the unlabeled real data.

13. The processor of claim 10, wherein, The generation of the one or more synthetic images is also based on self-learning using pseudo-statistics to align the labels between the unlabeled real data and the labeled synthetic data corresponding to the first domain.

14. The processor of claim 10, wherein, At least one of the one or more circuits is configured to: Receive unlabeled images; and A trained scene graph prediction network is used to generate scene graphs for the unlabeled images.

15. A system comprising: Memory; as well as One or more processors are configured to generate one or more synthetic images based at least on labeled synthetic data corresponding to a first domain, wherein the labeled synthetic data corresponding to the first domain is generated using a scene graph prediction network, the scene graph prediction network being trained using labeled synthetic data corresponding to a second domain different from the first domain.

16. The system of claim 15, wherein, The one or more processors are also used for: A scene graph is generated by aligning one or more features in the latent space with one or more features in the output space of the scene graph prediction network using at least one of the following: a gradient inversion layer (GRL) or a domain discriminator; and The one or more synthetic images are generated based on at least the generated scene graph.

17. The system of claim 15, wherein, Generating one or more synthetic images based at least on the labeled synthetic data corresponding to the first domain reduces one or more differences in appearance and content between the labeled synthetic dataset corresponding to the first domain and the unlabeled real data.

18. The system of claim 15, wherein, The generation of the one or more synthetic images is also based on self-learning using pseudo-statistics to align the labels between unlabeled real data and labeled synthetic data corresponding to the first domain.

19. The system of claim 15, wherein, The system includes at least one of the following: A system used to perform graphics rendering operations; A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; A system used to perform deep learning operations; Systems implemented using edge devices; A system that merges one or more virtual machines (VMs); A system that is at least partially implemented in a data center; or A system that utilizes cloud computing resources at least in part.

20. The system of claim 15, wherein, The one or more processors are also used for: Receive unlabeled images; and A trained scene graph prediction network is used to generate scene graphs for the unlabeled images.

Images