- Patent Title: High level syntax for compressed representation of neural networks
-
Application No.: US17140512Application Date: 2021-01-04
-
Publication No.: US11412266B2Publication Date: 2022-08-09
- Inventor: Emre Baris Aksu , Miska Matias Hannuksela , Hamed Rezazadegan Tavakoli , Francesco Cricri
- Applicant: Nokia Technologies Oy
- Applicant Address: FI Espoo
- Assignee: Nokia Technologies Oy
- Current Assignee: Nokia Technologies Oy
- Current Assignee Address: FI Espoo
- Agency: Harrington & Smith
- Agent Joseph C. Drish
- Main IPC: H04N19/70
- IPC: H04N19/70 ; H04N19/61 ; H04N19/46 ; G06N3/04

Abstract:
An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit having metadata or compressed neural network data of a portion of the at least one neural network; and wherein a serialized bitstream comprises one or more of the at least one information unit.
Public/Granted literature
- US20210211733A1 High Level Syntax for Compressed Representation of Neural Networks Public/Granted day:2021-07-08
Information query