vgg

VGG

In this directory, we aim to implement the VGG family of convolutional neural network (CNN) models for image classification, including the well-known VGG-16 and VGG-19 models, to be tested with the ImageNet dataset.

Available implementations:

	Description	Library	Notebook
v1	Basic impl	Keras

Implementation notes for v1:

1. We haven't yet trained or tested this network (work in progress).

Our implementation is based on the following paper:

• Karen Simonyan and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).

Note: this paper was also published in ICLR 2015.

This paper is available via:

• Visual Geometry Group at Oxford
• arXiv
• CiteSeerX

See also:

• VGG report from the authors - links to download models
• Papers with Code