PoolingLayer

PoolingLayer[sz]

represents a pooling net layer using kernels of size sz.

PoolingLayer[{w}]

represents a layer performing one-dimensional pooling with kernels of size w.

PoolingLayer[{h,w}]

represents a layer performing two-dimensional pooling with kernels of size h×w.

PoolingLayer[kernel,stride]

represents a layer that uses stride as the step size between kernel applications.

PoolingLayer[kernel,opts]

includes options for other pooling methods, padding and other parameters.

Details and Options

  • PoolingLayer[n,…] represents a layer that, applied to an input tensor with c input channels and one or more spatial dimensions, performs c distinct pooling operations across the spatial dimensions to produce an output tensor with c channels. The channel dimension is taken to be the first dimension of the input and output tensors.
  • PoolingLayer[n] is equivalent to PoolingLayer[n,1].
  • The following optional parameters can be included:
  • "Dimensionality"Automaticnumber of spatial dimensions of the pooling
    "Function"Maxaggregation function to use
    "PaddingSize"0amount of zero padding to apply to the input
  • The settings for kernel, stride, and "PaddingSize" can be of the following forms:
  • nuse the value n for all dimensions
    {…,ni,…}use the value ni for the i^(th) dimension
  • PoolingLayer[…][input] explicitly computes the output from applying the layer.
  • PoolingLayer[…][{input1,input2,…}] explicitly computes outputs for each of the inputi.
  • PoolingLayer is typically used inside NetChain, NetGraph, etc.
  • NetExtract can be used to extract parameter values from a PoolingLayer object.
  • PoolingLayer exposes the following ports for use in NetGraph etc.:
  • "Input"a matrix or rank-3 tensor
    "Output"a matrix or rank-3 tensor
  • Possible explicit settings for the "Function" option include:
  • Maxthe maximum is used
    Meanthe mean value is used
    Totalthe sum of all values is used
  • When it cannot be inferred from other layers in a larger net, the option "Input"->{d1,…,dn} can be used to fix the input dimensions of PoolingLayer.
  • Given an input tensor of dimensions d1×…×di×…, the output tensor will be of dimensions ×…××…, where the channel dimension remains unchanged (i.e. d1=) and the sizes of spatial dimensions are transformed according to , where is the padding size, is the kernel size, and is the stride size for each dimension.

Examples

open allclose all

Basic Examples  (2)

Create a PoolingLayer with a kernel size of 5:

In[1]:=
Click for copyable input
Out[1]=

Create a one-dimensional PoolingLayer:

In[1]:=
Click for copyable input
Out[1]=

Apply the layer to an input matrix:

In[2]:=
Click for copyable input
Out[2]=

Scope  (3)

Options  (3)

Properties & Relations  (2)

See Also

ConvolutionLayer  BatchNormalizationLayer  SpatialTransformationLayer  AggregationLayer  NetChain  NetGraph  NetTrain

Introduced in 2016
(11.0)
| Updated in 2017
(11.1)