Average pooling operation
Average pooling operation
AveragePooling1D(pool_size = 2, strides = NULL, padding = "valid", input_shape = NULL) AveragePooling2D(pool_size = c(2, 2), strides = NULL, padding = "valid", data_format = NULL, input_shape = NULL) AveragePooling3D(pool_size = c(2, 2, 2), strides = NULL, padding = "valid", data_format = NULL, input_shape = NULL)
pool_size |
Integer or pair of integers; size(s) of the max pooling windows. |
strides |
Integer, pair of integers, or None. Factor(s) by which to downscale. E.g. 2 will halve the input. If NULL, it will default to pool_size. |
padding |
One of "valid" or "same" (case-insensitive). |
input_shape |
nD tensor with shape: |
data_format |
A string, one of channels_last (default) or channels_first |
Taylor B. Arnold, taylor.arnold@acm.org
Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.