Deep Learning CNN Convolutional Neural Networks with Python - VGG

The video tutorial discusses the VGG convolutional neural network, which was introduced in 2014. It explains the structure of VGG blocks, consisting of multiple convolutional layers followed by a max pooling layer. The tutorial details the architecture of the VGG network, including the number of layers and channels in each block. It also covers the VGG 11, 16, and 19 models, highlighting their differences and features. The concept of spatial dimension reduction and the influence of VGG on subsequent networks like ResNet and Inception is also discussed.

What year was the VGG network originally introduced?

• 2012

• 2014

• 2016

• 2018

What is the typical size of the convolutional filter used in a VGG block?

• 5x5

• 7x7

• 1x1

• 3x3

What type of pooling layer is used in VGG blocks?

• Global Pooling

• Min Pooling

• Max Pooling

• Average Pooling

How many convolutional layers are there in the original VGG network?

• 5

• 11

• 8

• 16

What is the number of channels in the first block of the VGG network?

• 64

• 32

• 256

• 128

Which of the following is a variant of the VGG network?

• VGG 20

• VGG 16

• VGG 13

• VGG 10

Which networks were influenced by the VGG block concept?

• AlexNet and LeNet

• SqueezeNet and ShuffleNet

• ResNet and Inception

• DenseNet and MobileNet