The Architecture and Implementation of VGG-16

VGG is an acronym for the Visual Geometric Group from Oxford University and VGG-16 is a network with 16 layers proposed by the Visual Geometric Group. These 16 layers contain the trainable parameters and there are other layers also like the Max pool layer but those do not contain any trainable parameters. This architecture was the 1st runner up of the Visual Recognition Challenge of 2014 i.e. ILSVRC-2014 and was developed by Simonyan and Zisserman. The VGG research group released a series of the convolution network model starting from VGG11 to VGG19.