MCPcopy Create free account
hub / github.com/alibaba/nann / rnn

Function rnn

tensorflow/tensorflow/python/keras/backend.py:3718–4077  ·  view source on GitHub ↗

Iterates over the time dimension of a tensor. Arguments: step_function: RNN step function. Args; input; Tensor with shape `(samples, ...)` (no time dimension), representing input for the batch of samples at a certain time step.

(step_function,
        inputs,
        initial_states,
        go_backwards=False,
        mask=None,
        constants=None,
        unroll=False,
        input_length=None,
        time_major=False,
        zero_output_for_mask=False)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Calls 15

unstackMethod · 0.95
swap_batch_timestepFunction · 0.85
tupleFunction · 0.85
_process_single_input_tFunction · 0.85
_get_input_tensorFunction · 0.85
_expand_maskFunction · 0.85
reverseFunction · 0.85
with_rank_at_leastMethod · 0.80
TensorArrayMethod · 0.80
expand_dimsFunction · 0.70
zeros_likeFunction · 0.70
rangeFunction · 0.50