Depth in neural networks is a very important parameter. Before ResNet, the VGG network was able to prove its importance by scaling up AlexNet to 16-19 layers.
In this tutorial, we'll take a look at the theory behind the architecture as well as a Pytorch implementation from the official documentation.
Table of Content
- The Importance of Depth in Neural Networks: 0:00
- VGG Network Architecture: 0:57
- VGG Network Training Regiment: 4:23
- VGG Network Result: 5:19
- VGG Pytorch Code Walkthrough: 7:41
- Conclusion: 15:39
Important Links:
📌 Paper: arxiv.org/pdf/1409.1556
📌 Github: github.com/yacineMahdid/deep-...
Abstract:
"In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.
Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results.
We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision. "
----
Join the Discord for general discussion: / discord
----
Follow Me Online Here:
GitHub: github.com/yacineMahdid
LinkedIn: / yacinemahdid
___
Have a great week! 👋