公开(公告)号：US20230410255A1

公开(公告)日：2023-12-21

申请号：US18251220

申请日：2021-01-22

Applicant: QUALCOMM Incorporated

Inventor： Wenhao ZHANG ,  Zhiguo LI ,  Ronghui LIN ,  Zhiping PANG

IPC: G06T3/40 ,  G06F9/50

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.

公开(公告)号：US20240386704A1

公开(公告)日：2024-11-21

申请号：US18833782

申请日：2023-03-31

Applicant: QUALCOMM Incorporated

Inventor： Wenhao ZHANG ,  Zhiguo LI ,  Shaochun LV

IPC: G06V10/77 ,  G06T3/40 ,  G06V10/22 ,  G06V10/26 ,  G06V10/764 ,  G06V10/82

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.