SYSTEM AND METHOD FOR IMAGE PROCESSING USING MIXED INFERENCE PRECISION

    公开(公告)号:US20240386704A1

    公开(公告)日:2024-11-21

    申请号:US18833782

    申请日:2023-03-31

    Abstract: Systems and techniques are provided for processing image data. For example, a process can include generating one or more object detection outputs based on an input image. A plurality of image patches can be determined for the input image. Based on the object detection outputs, a first subset of the image patches can be determined as associated with a first inference precision level and a second subset of the image patches can be determined as associated with a second inference precision level different from the first inference precision level. A processed image patch can be generated for each image patch of the first subset using an image processing machine learning model quantized to the first inference precision level. A processed image patch can be generated for each image patch of the second subset using an image processing machine learning model quantized to the second inference precision level.

    NETWORK SLICING ENHANCEMENT
    2.
    发明公开

    公开(公告)号:US20230353456A1

    公开(公告)日:2023-11-02

    申请号:US17997813

    申请日:2020-06-28

    Inventor: Zhiguo LI Nan ZHANG

    CPC classification number: H04L41/0895 H04L41/0803 H04W84/042

    Abstract: Aspects of the present disclosure relate to wireless communications, and more particularly, to network slicing enhancements with randomly generated application identifiers. For example, by handling requests of an application, a user equipment (UE) may be able to forward such requests to a network entity to receive an encoded random number token corresponding to the application to provide for improved indexing of applications on the UE.

    DECREASED QUANTIZATION LATENCY
    3.
    发明公开

    公开(公告)号:US20230410255A1

    公开(公告)日:2023-12-21

    申请号:US18251220

    申请日:2021-01-22

    CPC classification number: G06T3/4046 G06F9/5027

    Abstract: Systems and techniques are described herein for decreasing quantization latency. In some aspects, a process includes determining a first integer data type of data at least one layer of a neural network is configured to process, and determining a second integer data type of data received for processing by the neural network. The second integer data type can be different than the first integer data type. The process further includes determining a ratio between a first size of the first integer data type and a second size of the second integer data type, and scaling parameters of the at least one layer of the neural network using a scaling factor corresponding to the ratio. The process further includes quantize the scaled parameters of the neural network, and inputting the received data to the neural network with the quantized and scaled parameters.

    TECHNIQUES FOR ACCELERATING DATA RECOVERY FROM OUT OF SERVICE

    公开(公告)号:US20230180310A1

    公开(公告)日:2023-06-08

    申请号:US17997474

    申请日:2020-07-02

    CPC classification number: H04W76/10 H04W40/22 H04W60/04 H04W48/18

    Abstract: Methods, systems, and devices for wireless communications are described. In some systems, a user equipment (UE) may attempt to establish a data session with a base station. The UE may transmit one or more session request messages including one or more route selection descriptors (RSDs) to the base station, and the UE may determine a successful RSD that may be compatible with the network based on a session accept message received from the base station. The UE may store the successful RSD at a location in memory for use in future session establishment procedures. For example, the UE may go out of service, and may re-acquire service with the same network. In such cases, the UE may transmit a session request message including the previously-accepted RSD to re-establish a data session with the base station.

    ADAPTIVE SCHEDULING FOR EXECUTING MACHINE LEARNING OPERATIONS IN A MULTIPROCESSOR COMPUTING DEVICE

    公开(公告)号:US20250028576A1

    公开(公告)日:2025-01-23

    申请号:US18714036

    申请日:2022-02-28

    Abstract: Certain aspects of the present disclosure provide techniques and apparatus for scheduling execution of machine learning model operations on a multiprocessor computing device. The method generally includes during execution of operations in a first portion of a machine learning model on a first processing unit of the computing device, measuring a temperature for each of a plurality of locations on the computing device. It is determined that a temperature measured for the first processing unit exceeds a threshold temperature. Based on one or more operating parameters for the computing device, a second processing unit of the computing device is selected to use in executing operations in a second portion of the machine learning model. Execution of operations in the second portion of the machine learning model on the second processing unit is scheduled.

    DUAL AUDIO CHANNELS OVER DUAL QUALITY OF SERVICE FLOWS

    公开(公告)号:US20230319637A1

    公开(公告)日:2023-10-05

    申请号:US18041754

    申请日:2020-10-06

    CPC classification number: H04W28/0967 H04W28/10 H04W76/15

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive an indication that dual audio channels are to be established over dual quality of service (QoS) flows. The UE may establish a first audio channel of the dual audio channels over a first QoS flow and a second audio channel of the dual audio channels over a second QoS flow based at least in part on receiving the indication. Numerous other aspects are provided.

Patent Agency Ranking