CumSum - 11 vs 14#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.

Files changed (1) hide show
  1. CumSum11 → CumSum14 +1 -3
CumSum11 → CumSum14 RENAMED
@@ -1 +1 @@
1
1
  Performs cumulative sum of the input elements along the given axis.
2
2
  By default, it will do the sum inclusively meaning the first element is copied as is.
3
3
  Through an exclusive attribute, this behavior can change to exclude the first element.
4
4
  It can also perform summation in the opposite direction of the axis. For that, set reverse attribute to 1.
5
5
  Example:
6
6
  ::
7
7
  input_x = [1, 2, 3]
8
8
  axis=0
9
9
  output = [1, 3, 6]
10
10
  exclusive=1
11
11
  output = [0, 1, 3]
12
12
  exclusive=0
13
13
  reverse=1
14
14
  output = [6, 5, 3]
15
15
  exclusive=1
16
16
  reverse=1
17
17
  output = [5, 3, 0]
18
18
  **Attributes**
19
19
  * **exclusive**:
20
20
  If set to 1 will return exclusive sum in which the top element is
21
21
  not included. In other terms, if set to 1, the j-th output element
22
22
  would be the sum of the first (j-1) elements. Otherwise, it would be
23
23
  the sum of the first j elements.
24
24
  * **reverse**:
25
25
  If set to 1 will perform the sums in reverse direction.
26
26
  **Inputs**
27
27
  * **x** (heterogeneous) - **T**:
28
28
  An input tensor that is to be processed.
29
29
  * **axis** (heterogeneous) - **T2**:
30
30
  A 0-D tensor. Must be in the range [-rank(x), rank(x)-1]. Negative
31
31
  value means counting dimensions from the back.
32
32
  **Outputs**
33
33
  * **y** (heterogeneous) - **T**:
34
34
  Output tensor of the same type as 'x' with cumulative sums of the
35
35
  x's elements
36
36
  **Type Constraints**
37
37
  * **T** in (
38
- tensor(bfloat16),
39
38
  tensor(double),
40
39
  tensor(float),
41
- tensor(float16),
42
40
  tensor(int32),
43
41
  tensor(int64),
44
42
  tensor(uint32),
45
43
  tensor(uint64)
46
44
  ):
47
- Constrain input and output types to high-precision numeric tensors.
45
+ Input can be of any tensor type.
48
46
  * **T2** in (
49
47
  tensor(int32),
50
48
  tensor(int64)
51
49
  ):
52
50
  axis tensor can be int32 or int64 only