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

tf.math.unsorted_segment_min

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

Computes the minimum along segments of a tensor.

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.math.unsorted_segment_min, tf.compat.v1.unsorted_segment_min

tf.math.unsorted_segment_min(
    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 minimum such that:

\(output_i = \min_{j...} data_[j...]\) where min is over tuples j... such that segment_ids[j...] == i.

If the minimum is empty for a given segment ID i, it outputs the largest possible value for the specific numeric type,output[i] = numeric_limits<T>::max().

For example:

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

If the given segment ID i is negative, then the corresponding value is dropped, and will not be included in the result.