An efficient image to column algorithm for convolutional neural networks
- Resource Type
- Conference
- Authors
- Gong, Chunye; Chen, Xinhai; Lv, Shuling; Liu, Jie; Yang, Bo; Wang, QingLin; Bao, Weimin; Pang, Yufei; Sun, Yang
- Source
- 2021 International Joint Conference on Neural Networks (IJCNN) Neural Networks (IJCNN), 2021 International Joint Conference on. :1-8 Jul, 2021
- Subject
- Bioengineering
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Deep learning
Pipelines
Neural networks
Inference algorithms
Convolutional neural networks
deep learning
image to column
convolution neural network
convolution kernel
efficient solution
- Language
- ISSN
- 2161-4407
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.