Can use either greedy search (also known as best path) or a constrained dictionary search.
k_ctc_decode(y_pred, input_length, greedy = TRUE, beam_width = 100L,
top_paths = 1)tensor (samples, time_steps, num_categories) containing the
prediction, or output of the softmax.
tensor (samples, ) containing the sequence length for
each batch item in y_pred.
perform much faster best-path search if TRUE. This does not
use a dictionary.
if greedy is FALSE: a beam search decoder will be used
with a beam of this width.
if greedy is FALSE, how many of the most probable paths
will be returned.
If greedy is TRUE, returns a list of one element
that contains the decoded sequence. If FALSE, returns the top_paths
most probable decoded sequences. Important: blank labels are returned as
-1. Tensor (top_paths) that contains the log probability of each
decoded sequence.
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.