VGG net - rugbyprof/5443-Data-Mining GitHub Wiki
VGG net
VGG 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.The two major drawbacks with VGGNet is it is painfully slow to train and the network architecture weights themselves are quite large. (https://www.pyimagesearch.com/2017/03/20/imagenet-vggnet-resnet-inception-xception-keras/)