Invention Application
- Patent Title: APPARATUS AND METHOD FOR CONVERTING NEURAL NETWORK
-
Application No.: US17485322Application Date: 2021-09-24
-
Publication No.: US20220245458A1Publication Date: 2022-08-04
- Inventor: Jae-Bok PARK
- Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
- Applicant Address: KR Daejeon
- Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
- Current Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
- Current Assignee Address: KR Daejeon
- Priority: KR10-2021-0015589 20210203
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06K9/62 ; G06K9/72

Abstract:
Disclosed herein are an apparatus and method for converting a neural network. The method includes separating neural network data of a source framework to form a tree structure by analyzing the same, converting the neural network data in a tree structure to a neural network optimized for a target framework, classifying training data based on the result of analysis of the neural network data of the source framework, converting the classified training data to the training data structure of the target framework, and creating a neural network and training data of the target framework by combining the converted neural network and the converted training data.
Information query