Layer factory function to create an average-pooling layer.

BatchNormalization(map_rank = NULL, init_scale = 1,
  normalization_time_constant = 5000, blend_time_constant = 0,
  epsilon = 1e-05, use_cntk_engine = FALSE, name = "")

Arguments

epsilon

(float, default 0.00001) - added to avoid division by 0

name

string (optional) the name of the Function instance in the network

init

(scalar or matrix or initializer, defaults to init_glorot_uniform()) – initial value of weights W_scale

Details

Like Convolution(), AveragePooling() processes items arranged on an N-dimensional grid, such as an image. Typically, each item is a vector. For each item, average-pooling computes the element-wise mean over a window (“receptive field”) of items surrounding the item’s position on the grid.

The size (spatial extent) of the receptive field is given by filter_shape. E.g. for 2D pooling, filter_shape should be a tuple of two integers, such as (5,5).