tf.math.unsorted_segment_prod  |  TensorFlow v2.16.1 (original) (raw)

tf.math.unsorted_segment_prod

Stay organized with collections Save and categorize content based on your preferences.

Computes the product along segments of a tensor.

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.math.unsorted_segment_prod, tf.compat.v1.unsorted_segment_prod

tf.math.unsorted_segment_prod(
    data: Annotated[Any, tf.raw_ops.Any],
    segment_ids: Annotated[Any, tf.raw_ops.Any],
    num_segments: Annotated[Any, tf.raw_ops.Any],
    name=None
) -> Annotated[Any, tf.raw_ops.Any]

Readthe section on segmentationfor an explanation of segments.

This operator is similar to tf.math.unsorted_segment_sum, Instead of computing the sum over segments, it computes the product of all entries belonging to a segment such that:

\(output_i = \prod_{j...} data[j...]\) where the product is over tuplesj... such that segment_ids[j...] == i.

For example:

c = tf.constant([[1,2,3,4], [5,6,7,8], [4,3,2,1]]) tf.math.unsorted_segment_prod(c, tf.constant([0, 1, 0]), num_segments=2).numpy() array([[4, 6, 6, 4], [5, 6, 7, 8]], dtype=int32)

If there is no entry for a given segment ID i, it outputs 1.

If the given segment ID i is negative, then the corresponding value is dropped, and will not be included in the result. Caution: On CPU, values in segment_ids are always validated to be less thannum_segments, and an error is thrown for out-of-bound indices. On GPU, this does not throw an error for out-of-bound indices. On Gpu, out-of-bound indices result in safe but unspecified behavior, which may include ignoring out-of-bound indices or outputting a tensor with a 0 stored in the first dimension of its shape if num_segments is 0.