1-D max pooling layer
A 1-D max pooling layer performs downsampling by dividing the input into 1-D pooling regions, then computing the maximum of each region.
The dimension that the layer pools over depends on the layer input:
For time series and vector sequence input (data with three dimensions corresponding to the channels, observations, and time steps), the layer pools over the time dimension.
For 1-D image input (data with three dimensions corresponding to the spatial pixels, channels, and observations), the layer pools over the spatial dimension.
For 1-D image sequence input (data with four dimensions corresponding to the spatial pixels, channels, observations, and time steps), the layer pools over the spatial dimension.
creates a 1-D max pooling layer and sets thelayer
= maxPooling1dLayer(poolSize
)PoolSize
property.
还指定了填充或设置layer
= maxPooling1dLayer(poolSize
,Name=Value
)Stride
andName
properties using one or more optional name-value arguments. For example,maxPooling1dLayer(3,Padding=1,Stride=2)
creates a 1-D max pooling layer with a pool size of3
, a stride of2
, and padding of size1
on both the left and right of the input.
trainingOptions
|trainNetwork
|sequenceInputLayer
|lstmLayer
|bilstmLayer
|gruLayer
|convolution1dLayer
|averagePooling1dLayer
|globalMaxPooling1dLayer
|globalAveragePooling1dLayer