公开(公告)号：US12112148B2

公开(公告)日：2024-10-08

申请号：US17806056

申请日：2022-06-08

Applicant: NVIDIA Corporation

Inventor： Shaunak Gupte ,  Prashant Gaikwad ,  Chandrahas Jagadish Ramalad ,  Bhushan Rupde

IPC: G06F8/36 ,  G06F8/34 ,  G06F8/60 ,  G06N20/00

CPC classification number: G06F8/34 ,  G06F8/36 ,  G06F8/60 ,  G06N20/00

Abstract: Embodiments of the present disclosure relate to applications and platforms for configuring machine learning models for training and deployment using graphical components in a development environment. For example, systems and methods are disclosed that relate to determining one or more machine learning models and one or more processing operations corresponding to the one or more machine learning models. Further, a model component may be generated using the one or more machine learning models, the one or more processing operations, and one or more extension libraries in which the one or more extension libraries indicate one or more deployment parameters related to the one or more machine learning models. The model component may accordingly provide data that may be used to be able to use and deploy the one or more machine learning models.

公开(公告)号：US20220391176A1

公开(公告)日：2022-12-08

申请号：US17806056

申请日：2022-06-08

Applicant: NVIDIA Corporation

Inventor： Shaunak Gupte ,  Prashant Gaikwad ,  Chandrahas Jagadish Ramalad ,  Bhushan Rupde

IPC: G06F8/34 ,  G06F8/36 ,  G06F8/60

Abstract: Embodiments of the present disclosure relate to applications and platforms for configuring machine learning models for training and deployment using graphical components in a development environment. For example, systems and methods are disclosed that relate to determining one or more machine learning models and one or more processing operations corresponding to the one or more machine learning models. Further, a model component may be generated using the one or more machine learning models, the one or more processing operations, and one or more extension libraries in which the one or more extension libraries indicate one or more deployment parameters related to the one or more machine learning models. The model component may accordingly provide data that may be used to be able to use and deploy the one or more machine learning models.

公开(公告)号：US20220035684A1

公开(公告)日：2022-02-03

申请号：US17330710

申请日：2021-05-26

Applicant: NVIDIA Corporation

Inventor： Shaunak Gupte ,  Amit Kale ,  Bhushan Rupde ,  Kaustubh Purandare

IPC: G06F9/50 ,  G06F9/30 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques to balance processing load between a plurality of hardware accelerators. In at least one embodiment, operations performed on batches of frames of a video (e.g., as part of a video analytics pipeline) are distributed by a load balancer between a first hardware accelerator and a second hardware accelerator.

公开(公告)号：US20210334629A1

公开(公告)日：2021-10-28

申请号：US17116229

申请日：2020-12-09

Applicant: NVIDIA Corporation

Inventor： Wind Yuan ,  Kaustubh Purandare ,  Bhushan Rupde ,  Shaunak Gupte ,  Farzin Aghdasi

IPC: G06N3/04 ,  G06N3/10 ,  G06N3/08

Abstract: A multi-stage multimedia inferencing pipeline may be set up and executed using configuration data including information used to set up each stage by deploying the specified or desired models and/or other pipeline components into a repository (e.g., a shared folder in a repository). The configuration data may also include information a central inference server library uses to manage and set parameters for these components with respect to a variety of inference frameworks that may be incorporated into the pipeline. The configuration data can define a pipeline that encompasses stages for video decoding, video transform, cascade inferencing on different frameworks, metadata filtering and exchange between models and display. The entire pipeline can be efficiently hardware-accelerated using parallel processing circuits (e.g., one or more GPUs, CPUs, DPUs, or TPUs). Embodiments of the present disclosure can integrate an entire video/audio analytics pipeline into an embedded platform in real time.