Blocked convolution optimization method and device for convolution neural network

Abstract

The invention relates to the field of deep neural networks and provides a blocked convolution optimization method and a device for a convolution neural network, so as to solve the bottleneck problem of convolution operation in a hardware processing system in the neural network. The optimization method comprises steps: a to-be-blocked convolution layer is selected, and the upper limit of the block size is determined; according to the upper limit of the block size, a block number and the block size of an input feature map are determined; based on the block number, the block size, the size of a convolution kernel, the size of the input feature map and the filling size of an input feature map boundary, the block boundary filling size of a block feature map is calculated; and based on the block number, the block size and the block boundary filling size, a convolution based on the block boundary filling is built to replace the original convolution. The resource constraint problem of the convolution neural network during operation of an embedded hardware platform is greatly alleviated, the burst length is improved maximally when a memory is read and written, the throughput is improved, the time delay is reduced, and the efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of deep neural networks, in particular to a block convolution optimization method and device for convolutional neural networks. Background technique [0002] Deep learning, as a cutting-edge branch of machine learning, has developed rapidly in theory and application in recent years. Driven by deep learning, traditional fields such as computer vision and speech and language processing are developing rapidly. Computers can even surpass humans in recognizing images, videos, and speech and text. A number of emerging industries and applications have emerged in the wave of deep learning development, such as self-driving cars, chat robots, smart monitoring, smart homes, etc. Intelligent applications can be seen almost everywhere in people's daily lives. Driven by big data and deep learning, traditional retail, banking, and insurance industries have entered a new era of Internet development. [0003] Deep convolut...

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above problems in the prior art, that is, in order to solve the bottleneck problem of convolution processing in the neural network in the hardware processing system, one aspect of the present invention proposes a block convolution optimization method for convolutional neural networks , including the following steps:

Images