Fire Module

Learn about the central component of SqueezeNet, the fire module.

Chapter Goals:

  • Learn strategies for decreasing the number of parameters in a model
  • Understand how the fire module works and why it's effective
  • Write your own fire module function

A. Decreasing parameters

In order to make a smaller model, we need to decrease the number of weights per convolution layer. There are three ways to decrease the number of weights in a convolution layer:

  • Decrease the kernel size
  • Decrease the number of filters used
  • Decrease the number of input channels
We don't necessarily want to reduce the number of filters we use, since using a variety of filters allows us to extract different hidden features from the input. However, there are ways to decrease the kernel size and number of input channels while still maintaining good model performance. ...
Access this course and 1400+ top-rated courses and projects.