Improve Research Reproducibility A Bio-protocol resource
Concise Method
tooltip

Wide ResNet-50-2

RK Rohit Kundu
HB Hritam Basak
PS Pawan Kumar Singh
AA Ali Ahmadian
MF Massimiliano Ferrara
RS Ram Sarkar
request Request a Protocol
ask Ask a question
Favorite

Wide ResNet architecture was proposed in 2016 by Zagoruyko et al.39 2016. The Wide ResNet model mitigates some of the problems of ResNet40 by making the network shallow and wide, thereby reducing the training time and parameters without compromising the performance. The authors of ResNet have made the network shallow to increase the depth, thereby opening up the possibility of the network’s inability to learn anything during training due to the absence of anything to force it to go through the residual block weights. That might lead to a problem of feature reuse: a problem of only a few blocks having important information and the rest of the blocks sharing a small contribution towards the final output. The architecture of the Wide ResNet-50-2 CNN model is shown in Fig. 7.

Architecture of the Wide ResNet-50-2 base model.

Copyright and License information: The Author(s) ©2021
Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A