tf.reverse_sequence

TensorFlow 1 version

View source on GitHub

Reverses variable length slices. (deprecated arguments) (deprecated arguments)

tf.reverse_sequence(
    input, seq_lengths, seq_axis=None, batch_axis=None, name=None
)

This op first slices input along the dimension batch_axis, and for each slice i, reverses the first seq_lengths[i] elements along the dimension seq_axis.

The elements of seq_lengths must obey seq_lengths[i] <= input.dims[seq_dim], and seq_lengths must be a vector of length input.dims[batch_dim].

The output slice i along dimension batch_axis is then given by input slice i, with the first seq_lengths[i] slices along dimension seq_axis reversed.

Example usage:

seq_lengths = [7, 2, 3, 5]
input = [[1, 2, 3, 4, 5, 0, 0, 0], [1, 2, 0, 0, 0, 0, 0, 0],
         [1, 2, 3, 4, 0, 0, 0, 0], [1, 2, 3, 4, 5, 6, 7, 8]]
output = tf.reverse_sequence(input, seq_lengths, seq_axis=1, batch_axis=0)
output
<tf.Tensor: shape=(4, 8), dtype=int32, numpy=
array([[0, 0, 5, 4, 3, 2, 1, 0],
       [2, 1, 0, 0, 0, 0, 0, 0],
       [3, 2, 1, 4, 0, 0, 0, 0],
       [5, 4, 3, 2, 1, 6, 7, 8]], dtype=int32)>