Quoted from: https://arxiv.org/abs/1409.1556

The basic building block of classic CNNs is a sequence of the following: (i) a convolutional layer with padding to maintain the resolution, (ii) a nonlinearity such as a ReLU, (iii) a pooling layer such as a max pooling layer. One VGG block consists of a sequence of convolutional layers, followed by a max pooling layer for spatial downsampling. In the original VGG paper, the authors employed convolutions with  3×3  kernels with padding of 1 (keeping height and width) and  2×2  max pooling with stride of 2 (halving the resolution after each block). In the code below, we define a function called vgg_block to implement one VGG block. The function takes two arguments corresponding to the number of convolutional layers num_convs and the number of output channels num_channels.

Like AlexNet and LeNet, the VGG Network can be partitioned into two parts: the first consisting mostly of convolutional and pooling layers and the second consisting of fully-connected layers. This is depicted in the following figure.

The original VGG network had 5 convolutional blocks, among which the first two have one convolutional layer each and the latter three contain two convolutional layers each. The first block has 64 output channels and each subsequent block doubles the number of output channels, until that number reaches 512. Since this network uses 8 convolutional layers and 3 fully-connected layers, it is often called VGG-11.