tf.keras.ops.segment_min

Computes the min of segments in a tensor.

tf.keras.ops.segment_min(
    data, segment_ids, num_segments=None, sorted=False
)

Args
`data`	Input tensor.
`segment_ids`	A N-D tensor containing segment indices for each element in `data`. data.shape[:len(segment_ids.shape)] should match.
`num_segments`	An integer representing the total number of segments. If not specified, it is inferred from the maximum value in `segment_ids`.
`sorted`	A boolean indicating whether `segment_ids` is sorted. Defaults to `False`.

Returns
A tensor containing the min of segments, where each element represents the min of the corresponding segment in `data`.

Example:

data = keras.ops.convert_to_tensor([1, 2, 10, 20, 100, 200])
segment_ids = keras.ops.convert_to_tensor([0, 0, 1, 1, 2, 2])
num_segments = 3
keras.ops.segment_min(data, segment_ids, num_segments)
array([1, 10, 100], dtype=int32)

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2026-10-31 UTC.

tf.keras.ops.segment_min Stay organized with collections Save and categorize content based on your preferences.

Args

Returns

Example:

tf.keras.ops.segment_min