Effects of data count and image scaling on Deep Learning training
Background Deep learning using convolutional neural networks (CNN) has achieved significant results in various fields that use images. Deep learning can automatically extract features from data, and CNN extracts image features by convolution processing. We assumed that increasing the image size usin...
Main Authors: | Daisuke Hirahara, Eichi Takaya, Taro Takahara, Takuya Ueda |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2020-11-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-312.pdf |
Similar Items
-
Comparison of interpolation methods for raster images scaling
by: Trubakov A.O., et al.
Published: (2017-03-01) -
Feature Image Watermarking Based on Bicubic Interpolation of Wavelet Coefficients Using CRT
by: Prajanto Wahyu Adi, et al.
Published: (2017-10-01) -
Sonar Image Detection Based on Multi-Scale Multi-Column Convolution Neural Networks
by: Zhen Wang, et al.
Published: (2019-01-01) -
Project management under uncertainty beyond beta: The generalized bicubic distribution
by: José García Pérez, et al.
Published: (2016-01-01) -
Oscilações intrasazonais no Indo-Pacífico e na zona de convergência do Atlântico Sul: estudo observacional e numérico
by: Augusto Cesar Barros Barbosa
Published: (2012)