This version performs the same function as Dropout, however it drops entire 3D feature maps instead of individual elements. If adjacent voxels 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_3d will help promote independence between feature maps and should be used instead.

  data_format = NULL,
  batch_size = NULL,
  name = NULL,
  trainable = NULL,
  weights = NULL



What to compose the new Layer instance with. Typically a Sequential model or a Tensor (e.g., as returned by layer_input()). The return value depends on object. If object is:

  • missing or NULL, the Layer instance is returned.

  • a Sequential model, the model with an additional layer is returned.

  • a Tensor, the output tensor from layer_instance(object) is returned.


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 4. 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".


Fixed batch size for layer


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.


Whether the layer weights will be updated during training.


Initial weights for layer.

Input shape

5D tensor with shape: (samples, channels, dim1, dim2, dim3) if data_format='channels_first' or 5D tensor with shape: (samples, dim1, dim2, dim3, channels) if data_format='channels_last'.

Output shape

Same as input

See also