> For the complete documentation index, see [llms.txt](https://alfredo-reyes-montero.gitbook.io/keras/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://alfredo-reyes-montero.gitbook.io/keras/chapter1/vgg-network.md).

# VGG network

The VGG network architecture was introduced by Simonyan and Zisserman in their 2014 paper, [*Very Deep Convolutional Networks for Large Scale Image Recognition*](https://arxiv.org/abs/1409.1556).

This network is characterized by its simplicity, using only *3×3* convolutional layers stacked on top of each other in increasing depth. Reducing volume size is handled by max pooling. Two fully-connected layers, each with 4,096 nodes are then followed by a softmax classifier (above).

The “16” and “19” stand for the number of weight layers in the network (columns D and E show in the Figure Below:

![](https://1341290981-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-Lj1MxDpb9OGomj9BsLG%2F-Lj1N0EXCoTLs_2TSipa%2F-Lj1NXoFPOzfJVOTGOuZ%2Fimport.png?generation=1562334343050931\&alt=media)