Convolutional neural network system

A convolutional neural network method includes: determining a temporary buffer layer between a first layer and a final layer of a convolutional neural network system; in a first stage, convolution operation is executed from a first layer to a temporary buffer layer of the convolutional neural networ...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LIN YUNSHENG, TANG DIWEN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A convolutional neural network method includes: determining a temporary buffer layer between a first layer and a final layer of a convolutional neural network system; in a first stage, convolution operation is executed from a first layer to a temporary buffer layer of the convolutional neural network system according to part of input data of a previous level of the temporary buffer layer so as togenerate a feature map line; and in the second stage, executing convolution operation from the temporary buffer layer to the final layer of the convolutional neural network system to generate a feature map. 一种卷积神经网络方法,其包含:决定一暂时缓冲层,其位于卷积神经网络系统的第一层与最终层之间;于第一阶段,从卷积神经网络系统的第一层至暂时缓冲层,根据该暂时缓冲层之前层级的部分输入数据,执行卷积操作以产生一特征图线;及于第二阶段,从卷积神经网络系统的暂时缓冲层至最终层,执行卷积操作以产生一特征图。