1D Global average pooling

This block performs exactly the same operation as the 1D Average pooling block except that the pool size is the size of the entire input of the block, i.e., it computes a single average value for all the incoming data.

The 1D Global average pooling block takes a vector and computes the average value of all values for each of the input channels. The output is thus a tensor of size is 1 x 1 x (input channels).

1D Global average pooling
Figure 1. A 1D Global average pooling.

Use global average pooling blocks as an alternative to the Flattening block after the last pooling block of your convolutional neural network. Using 1D Global average pooling block can replace the fully connected blocks of your CNN. For more information, see Section 3.2 of Min Lin, Qiang Chen, Shuicheng Yan. Network In Network.

Get started for free