maxPooling1dLayer
1-D max pooling layer
Description
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.
Creation
Description
creates a 1-D max pooling layer and sets the layer
= maxPooling1dLayer(poolSize
)PoolSize
property.
also specifies the padding or sets the layer
= maxPooling1dLayer(poolSize
,Name=Value
)Stride
and Name
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 of 3
, a stride of 2
, and
padding of size 1
on both the left and right of the input.
Input Arguments
Properties
Examples
Algorithms
Version History
Introduced in R2021b
See Also
trainingOptions
| trainNetwork
| sequenceInputLayer
| lstmLayer
| bilstmLayer
| gruLayer
| convolution1dLayer
| averagePooling1dLayer
| globalMaxPooling1dLayer
| globalAveragePooling1dLayer
Topics
- Sequence Classification Using 1-D Convolutions
- Sequence-to-Sequence Classification Using 1-D Convolutions
- Sequence Classification Using Deep Learning
- Sequence-to-Sequence Classification Using Deep Learning
- Sequence-to-Sequence Regression Using Deep Learning
- Time Series Forecasting Using Deep Learning
- Long Short-Term Memory Networks
- List of Deep Learning Layers
- Deep Learning Tips and Tricks