kerasR (version 0.8.1)

MaxPooling: Max pooling operations

Description

Max pooling operations

Usage

MaxPooling1D(pool_size = 2, strides = NULL, padding = "valid",
  input_shape = NULL)
MaxPooling2D(pool_size = c(2, 2), strides = NULL, padding = "valid",
  data_format = NULL, input_shape = NULL)
MaxPooling3D(pool_size = c(2, 2, 2), strides = NULL, padding = "valid",
  data_format = NULL, input_shape = NULL)

Arguments

pool_size

Integer or triplet of integers; size(s) of the max pooling windows.

strides

Integer, triplet 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

only need when first layer of a model; sets the input shape of the data

data_format

A string, one of channels_last (default) or channels_first

Author

Taylor B. Arnold,

References

Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.

See Also

Other layers: Activation, ActivityRegularization, AdvancedActivation, BatchNormalization, Conv, Dense, Dropout, Embedding, Flatten, GaussianNoise, LayerWrapper, LocallyConnected, Masking, Permute, RNN, RepeatVector, Reshape, Sequential

Examples

if(keras_available()) {
  X_train <- array(rnorm(100 * 28 * 28), dim = c(100, 28, 28, 1))
  Y_train <- to_categorical(matrix(sample(0:2, 100, TRUE), ncol = 1), 3)
  
  mod <- Sequential()
  mod$add(Conv2D(filters = 2, kernel_size = c(2, 2),
                 input_shape = c(28, 28, 1)))
  mod$add(Activation("relu"))
  mod$add(MaxPooling2D(pool_size=c(2, 2)))
  mod$add(LocallyConnected2D(filters = 2, kernel_size = c(2, 2)))
  mod$add(Activation("relu"))
  mod$add(MaxPooling2D(pool_size=c(2, 2)))
  mod$add(Dropout(0.25))
  
  mod$add(Flatten())
  mod$add(Dropout(0.5))
  mod$add(Dense(3, activation='softmax'))
  
  keras_compile(mod, loss='categorical_crossentropy', optimizer=RMSprop())
  keras_fit(mod, X_train, Y_train, verbose = 0)
}