tf.raw_ops.SegmentProdV2

Computes the product along segments of a tensor.

tf.raw_ops.SegmentProdV2(
    data, segment_ids, num_segments, name=None
)

Read the section on segmentation for an explanation of segments.

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

If the product is empty for a given segment ID i, output[i] = 1.

The only difference with SegmentProd is the additional input num_segments. This helps in evaluating the output shape in compile time. num_segments should be consistent with segment_ids. e.g. Max(segment_ids) - 1 should be equal to num_segments for a 1-d segment_ids With inconsistent num_segments, the op still runs. only difference is, the output takes the size of num_segments irrespective of size of segment_ids and data. for num_segments less than expected output size, the last elements are ignored for num_segments more than the expected output size, last elements are assigned 1.

For example:

@tf.function(jit_compile=True)
def test(c):
  return tf.raw_ops.SegmentProdV2(data=c, segment_ids=tf.constant([0, 0, 1]), num_segments=2)
c = tf.constant([[1,2,3,4], [4, 3, 2, 1], [5,6,7,8]])
test(c).numpy()
array([[4, 6, 6, 4],
       [5, 6, 7, 8]], dtype=int32)

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. The values must be less than num_segments.