tf.sequence_mask

TensorFlow 2 version

View source on GitHub

Returns a mask tensor representing the first N positions of each cell.

tf.sequence_mask(
    lengths, maxlen=None, dtype=tf.dtypes.bool, name=None
)

If lengths has shape [d_1, d_2, ..., d_n] the resulting tensor mask has dtype dtype and shape [d_1, d_2, ..., d_n, maxlen], with

mask[i_1, i_2, ..., i_n, j] = (j < lengths[i_1, i_2, ..., i_n])

Examples:

tf.sequence_mask([1, 3, 2], 5)  # [[True, False, False, False, False],
                                #  [True, True, True, False, False],
                                #  [True, True, False, False, False]]

tf.sequence_mask([[1, 3],[2,0]])  # [[[True, False, False],
                                  #   [True, True, True]],
                                  #  [[True, True, False],
                                  #   [False, False, False]]]