Invention Grant
- Patent Title: Compression technique for deep neural network weights
-
Application No.: US17220620Application Date: 2021-04-01
-
Publication No.: US11757469B2Publication Date: 2023-09-12
- Inventor: Prajakt Kulkarni , Lakshmi Narayana Macha , Haoping Xu
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Agency: The Marbury Law Group, PLLC
- Main IPC: H03M7/30
- IPC: H03M7/30 ; G06N3/04

Abstract:
Various embodiments include methods and devices for compression and decompression of weight data sets. Some embodiments may include compressing weight data by receiving a weight data set of binary numbers representing weight values, generating a frame payload including a compressed first frame of a first subset of the weight values in the weight data set, and generating a block of compressed weight data having the frame payload. Some embodiments may include decompressing weight data by retrieving a block of compressed weight data, in which the block of compressed weight data includes a frame header associated with a frame payload, in which the frame header includes a normalization factor indicator, and in which the frame payload includes compressed weight values, and generating a first decompressed frame comprising decompressed weight values of the compressed weight values of the frame payload.
Public/Granted literature
- US20220321143A1 Compression Technique For Deep Neural Network Weights Public/Granted day:2022-10-06
Information query
IPC分类: