tf.math.segment_sum

Computes the sum along segments of a tensor.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.math.segment_sum, tf.compat.v1.segment_sum

tf.math.segment_sum(
    data: _atypes.TensorFuzzingAnnotation[TV_SegmentSum_T],
    segment_ids: _atypes.TensorFuzzingAnnotation[TV_SegmentSum_Tindices],
    name=None
) -> _atypes.TensorFuzzingAnnotation[TV_SegmentSum_T]

Read the section on segmentation for an explanation of segments.

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

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

Caution: On CPU, values in segment_ids are always validated to be sorted, and an error is thrown for indices that are not increasing. On GPU, this does not throw an error for unsorted indices. On GPU, out-of-order indices result in safe but unspecified behavior, which may include treating out-of-order indices as the same as a smaller following index.

For example:

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

Args
data	A Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, qint16, quint16, uint16, complex128, half, uint32, uint64.
segment_ids	A Tensor. Must be one of the following types: int32, int64. A 1-D tensor whose size is equal to the size of data's first dimension. Values should be sorted and can be repeated. Caution: The values are always validated to be sorted on CPU, never validated on GPU.
name	A name for the operation (optional).

Returns
A Tensor. Has the same type as data.