The following is a list of some of the popular CNN models available:
- LeNet: LeNet was the first successful CNN applied to recognize handwritten digits. It was developed by Yann LeCun in the 1990s. You can know more about LeNet architecture and its related publications at Yann LeCun's home page (http://yann.lecun.com/exdb/lenet/).
- VGGNet: This was the runner-up in ILSVRC 2014, developed by Karen Simonyan and Andrew Zisserman. Its first version contains 16 Convolution+FC layers and was called VGG16, later they brought VGG19 with 19 layers. The details about its performance and publications can be accessed from the University of Oxford site (http://www.robots.ox.ac.uk/~vgg/research/very_deep/).
- ResNet: Developed by Kaiming ...