MobileNet was introduced by a team of Google engineers in CVPR 2017 in their paper titled MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. You can find this MobileNet paper at https://arxiv.org/abs/1704.04861.
MobileNet proposes a depthwise separable convolution architecture that shrinks the neural network model so that it can work on the resource restriction issues of edge devices. MobileNet architecture consists of two main parts:
- Depthwise separable convolution
- Pointwise 1 x 1 convolution
Note that we described the importance of 1 x 1 convolution in Chapter 4, Deep Learning on Images, and Chapter 5, Neural Network Architecture and Models. You may want to revisit those chapters as a refresher.
The following diagram shows how depthwise convolution works:
In the preceding diagram, we can see the following:
- We get a reduction...
