|TensorFlow 1 version||View source on GitHub|
Spatial 2D version of Dropout.
Compat aliases for migration
See Migration guide for more details.
tf.keras.layers.SpatialDropout2D( rate, data_format=None, **kwargs )
Used in the notebooks
|Used in the tutorials|
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, SpatialDropout2D will help promote independence between feature maps and should be used instead.
||Float between 0 and 1. Fraction of the input units to drop.|
'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
inputs: A 4D tensor.
training: Python boolean indicating whether the layer should behave in training mode (adding dropout) or in inference mode (doing nothing).
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'.
Same as input.