An efficient image to column algorithm for convolutional neural networks

Convolutional Neural Networks (CNNs) are a class of deep neural networks. The image to column (im2col) procedure is an important step for CNN and consumes about 28.8% of the whole inference time. In this paper, we present an efficient im2col algorithm, name im2cole (word "e" means efficien...

Full description

Saved in:
Bibliographic Details
Main Authors: Gong, Chunye, Chen, Xinhai, Lv, Shuling, Liu, Jie, Yang, Bo, Wang, QingLin, Bao, Weimin, Pang, Yufei, Sun, Yang
Format: Conference Proceeding
Language:English
Subjects:
convolution kernel
convolution neural network
Convolutional neural networks
Deep learning
efficient solution
image to column
Inference algorithms
Neural networks
Pipelines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional Neural Networks (CNNs) are a class of deep neural networks. The image to column (im2col) procedure is an important step for CNN and consumes about 28.8% of the whole inference time. In this paper, we present an efficient im2col algorithm, name im2cole (word "e" means efficient). The condition with different stride and pad in im2cole is well handled and the judgements in the innermost loop are removed. The procedure with pad = 1 is split into three conditions. This will reduce the pause of CPU instruction pipeline. The performances of the presented im2cole algorithm are reported with different inputs. Some discussion and performance issues are also reported. The experimental results show that the overall performance speedup of im2cole ranges from 2.12 to 4.33 compared with the original algorithm. The real application with Darknet shows that im2cole can get 20.75% whole performance improvement.
ISSN:2161-4407
DOI:10.1109/IJCNN52387.2021.9533579