Python Deep Learning - Second Edition

VGG

The first architecture we're going to discuss is VGG (from Oxford's Visual Geometry Group, https://arxiv.org/abs/1409.1556). It was introduced in 2014, when it became a runner-up in the ImageNet challenge of that year. The VGG family of networks remains popular today and is often used as a benchmark against newer architectures. Prior to VGG (for example, LeNet-5: http://yann.lecun.com/exdb/lenet/) and AlexNet (https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf), the initial convolutional layers of a network used filters with large receptive fields, such as 7 x 7. Additionally, the networks usually had alternating single convolutional and pooling layers. The authors of the paper observed ...