Abstract: Disclosed are apparatuses, systems, and techniques that improve memory and computational efficiency of remote direct memory accesses into a memory of a graphics processing unit. The techniques include but are not limited to receiving packets with video frame data, storing the plurality of packets in a memory of a network controller, processing the packets to obtain unit(s) of the video frame, storing the unit(s) representative of the video frame in a memory of a graphics processing unit (GPU), and extracting the data of the video frame from the units representative of the video frame, stored in the memory of the GPU, to render the video frame.

Abstract: Apparatuses, systems, and techniques for continuous training of an object detection and/or classification model. A first image including a depiction of an environment based on a first set of conditions is identified. Object data associated with an object detected in the first image is obtained based on one or more outputs of a machine learning model. A determination is made of whether a level of confidence that an object corresponds to an object class satisfies a level of confidence criterion. If so, a first set of conditions corresponding to the environment depicted in the first image. One or more noise characteristics associated with a second image including a depiction of the environment is determined based on a difference between the first set of conditions and a second set of conditions of the second image. The first image is augmented based on the one or more determined noise characteristics to generate a third image.

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.

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.

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.