Average pooling 1D

The 1D Average pooling block represents an average pooling operation.

This block outputs a smaller tensor than its input, which means downstream blocks in your model will need fewer parameters and amount of computation; it also serves to control overfitting.

How does average pooling work?

The 1D Average pooling block moves a pool (window) with a set size (Horizontal pool) over the incoming data, computing the average in each specific window. How big steps the window takes is determined by the Horizontal stride.

1D Average pooling
Figure 1. A 1D average pooling with a pool sized 2 and a stride of 2.

Average pooling blocks are inserted after one or more convolutional blocks; they help inner convolutional block receive information from a bigger portion of the original vector. If we see convolutional blocks as detectors of a specific feature, average pooling finds the “mean” value of that feature inside the pooling vector. Each channel (hence each feature) is treated separately.

Parameters

Horizontal pool: The length of the vector with which the average is computed. Default: 2

Horizontal stride: Distance between the left edge of consecutive pooling windows. Default: 1

Padding: Same results in padding the input such that the output has the same length as the original input. Valid means "no padding".

Was this page helpful?
YesNo