Have a personal or library account? Click to login

Deep Capsule Network Handwritten Digit Recognition

International Journal of Advanced Network, Monitoring and Controls
Volume 5 (2020): Issue 4 (January 2020)
By:
Open Access
|Jan 2021

Figures & Tables

Figure 1.

Network structure of deep capsule
Network structure of deep capsule

Figure 2.

Decoder network
Decoder network

Figure 3.

Dynamic routing algorithm
Dynamic routing algorithm

Figure 4.

Test precision chart of capsule network under 50 epochs
Test precision chart of capsule network under 50 epochs

Figure 5.

Test accuracy chart of deep capsule network under 50 epochs
Test accuracy chart of deep capsule network under 50 epochs

Figure 6.

Test precision chart of capsule network under 30 epochs
Test precision chart of capsule network under 30 epochs

Figure 7.

Test accuracy chart of deep capsule network under 30 epochs
Test accuracy chart of deep capsule network under 30 epochs

Figure 8.

Comparison between the accuracy of capsule network and deep capsule network
Comparison between the accuracy of capsule network and deep capsule network

Figure 9.

Impact of changing the number of routing iterations on the deep capsule network
Impact of changing the number of routing iterations on the deep capsule network

Figure 10.

Influence of different iteration times of two routes on deep capsule network
Influence of different iteration times of two routes on deep capsule network

Figure 11.

Influence of the same number of two routing iterations on deep capsule network
Influence of the same number of two routing iterations on deep capsule network

Figure 12.

Schematic diagram of some pictures in MNIST database
Schematic diagram of some pictures in MNIST database

Figure 13.

Schematic diagram of reconstructed image
Schematic diagram of reconstructed image

Figure 14.

Comparison of input and output images of the network
Comparison of input and output images of the network

Figure 15.

Partial reconstruction results of the improved network
Partial reconstruction results of the improved network

Figure 16.

Improved partial error reconstruction results
Improved partial error reconstruction results

STRUCTURE COMPARISON OF CAPSULE NETWORK AND DEEP CAPSULE NETWORK

Capsule networkDeep capsule network
Convolution layerConv1: 256*9*9Conv1: 512*9*9 Conv2: 256*5*5
Primary Capsule9*95*5
Digit CapsuleOne time dynamic routingThree iterationsTwice dynamic routingThe main route has three iterations, and the secondary route has three iterations
FC

EXPERIMENTAL ENVIRONMENT

Operating systemWindows10(RAM16.0GB)
CPUIntel(R)Core(TM)i7-9750H
GPUNVIDIA GeForce GTX 1660 Ti
DatasetMNIST
Otherpytorch1.5.0+cu101 python 3.7.7
DOI: https://doi.org/10.21307/ijanmc-2020-031 | Journal eISSN: 2470-8038
Journal RSS Feed
Language: English
Page range: 1 - 8
Published on: Jan 11, 2021
Published by: Xi’an Technological University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
Component,
Deeplearning,
Nerve Capsule,
Deep Capsule Network,
Handwritten Digit Recognition
Related subjects:
Computer sciences,
Computer sciences, other

© 2021 Yuxing Tan, Hongge Yao, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution 4.0 License.

Volume 5 (2020): Issue 4 (January 2020)Next article