The input should be at least 3D, and the dimension of index one will be considered to be the temporal dimension.
time_distributed( object, layer, input_shape = NULL, batch_input_shape = NULL, batch_size = NULL, dtype = NULL, name = NULL, trainable = NULL, weights = NULL )
What to call the new
A layer instance.
Dimensionality of the input (integer) not including the samples axis. This argument is required when using this layer as the first layer in a model.
Shapes, including the batch size. For instance,
Fixed batch size for layer
The data type expected by the input, as a string (
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.
Consider a batch of 32 samples, where each sample is a sequence of 10 vectors of 16 dimensions. The batch
input shape of the layer is then
(32, 10, 16), and the
including the samples dimension, is
(10, 16). You can then use
time_distributed to apply a
layer_dense to each of the 10 timesteps,
Other layer wrappers: