keras: layer_spatial_dropout_2d – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

layer_spatial_dropout_2d

Spatial 2D version of Dropout.

Description

This version performs the same function as Dropout, however it drops entire 2D feature maps instead of individual elements. If adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then regular dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, layer_spatial_dropout_2d will help promote independence between feature maps and should be used instead.

Usage

layer_spatial_dropout_2d(
  object,
  rate,
  data_format = NULL,
  batch_size = NULL,
  name = NULL,
  trainable = NULL,
  weights = NULL
)

Arguments

`object`	Model or layer object
`rate`	float between 0 and 1. Fraction of the input units to drop.
`data_format`	'channels_first' or 'channels_last'. In 'channels_first' mode, the channels dimension (the depth) is at index 1, in 'channels_last' mode is it at index 3. It defaults to the `image_data_format` value found in your Keras config file at `~/.keras/keras.json`. If you never set it, then it will be "channels_last".
`batch_size`	Fixed batch size for layer
`name`	An optional name string for the layer. Should be unique in a model (do not reuse the same name twice). It will be autogenerated if it isn't provided.
`trainable`	Whether the layer weights will be updated during training.
`weights`	Initial weights for layer.

Input shape

4D tensor with shape: (samples, channels, rows, cols) if data_format='channels_first' or 4D tensor with shape: (samples, rows, cols, channels) if data_format='channels_last'.

Output shape

Same as input

References

- Efficient Object Localization Using Convolutional Networks