Iterates over the time dimension of a tensor

k_rnn(
step_function,
inputs,
initial_states,
go_backwards = FALSE,
constants = NULL,
unroll = FALSE,
input_length = NULL
)

Arguments

step_function RNN step function. Tensor with shape (samples, ...) (no time dimension), representing input for the batch of samples at a certain time step. Tensor with shape (samples, output_dim) (no time dimension), containing the initial values for the states used in the step function. Logical If TRUE, do the iteration over the time dimension in reverse order and return the reversed sequence. Binary tensor with shape (samples, time, 1), with a zero for every element that is masked. A list of constant values passed at each step. Whether to unroll the RNN or to use a symbolic loop (while_loop or scan depending on backend). Not relevant in the TensorFlow implementation. Must be specified if using unrolling with Theano.

Value

A list with:

• last_output: the latest output of the rnn, of shape (samples, ...)

• outputs: tensor with shape (samples, time, ...) where each entry outputs[s, t] is the output of the step function at time t for sample s.

• new_states: list of tensors, latest states returned by the step function, of shape (samples, ...).

Keras Backend

This function is part of a set of Keras backend functions that enable lower level access to the core operations of the backend tensor engine (e.g. TensorFlow, CNTK, Theano, etc.).

You can see a list of all available backend functions here: https://keras.rstudio.com/articles/backend.html#backend-functions.