tf.math.segment_min

Computes the minimum along segments of a tensor.

tf.math.segment_min(
    data, segment_ids, name=None
)

Read the section on segmentation for an explanation of segments.

Computes a tensor such that \(output_i = \min_j(data_j)\) where min is over j such that segment_ids[j] == i.

If the min is empty for a given segment ID i, output[i] = 0.

For example:

c = tf.constant([[1,2,3,4], [4, 3, 2, 1], [5,6,7,8]])
tf.segment_min(c, tf.constant([0, 0, 1]))
# ==> [[1, 2, 2, 1],
#      [5, 6, 7, 8]]

Args:

Returns:

A Tensor. Has the same type as data.