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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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 +2 -2
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
  input_x = [1, 2, 3]
7
7
  axis=0
8
8
  output = [1, 3, 6]
9
9
  exclusive=1
10
10
  output = [0, 1, 3]
11
11
  exclusive=0
12
12
  reverse=1
13
13
  output = [6, 5, 3]
14
14
  exclusive=1
15
15
  reverse=1
16
16
  output = [5, 3, 0]
17
17
  ### Attributes
18
18
  * **exclusive - INT** (default is '0'):
19
19
  If set to 1 will return exclusive sum in which the top element is not included. In other terms, if set to 1, the j-th output element would be the sum of the first (j-1) elements. Otherwise, it would be the sum of the first j elements.
20
20
  * **reverse - INT** (default is '0'):
21
21
  If set to 1 will perform the sums in reverse direction.
22
22
  ### Inputs
23
23
  - **x** (heterogeneous) - **T**:
24
24
  An input tensor that is to be processed.
25
25
  - **axis** (heterogeneous) - **T2**:
26
26
  A 0-D tensor. Must be in the range [-rank(x), rank(x)-1]. Negative value means counting dimensions from the back.
27
27
  ### Outputs
28
28
  - **y** (heterogeneous) - **T**:
29
29
  Output tensor of the same type as 'x' with cumulative sums of the x's elements
30
30
  ### Type Constraints
31
- * **T** in ( tensor(double), tensor(float), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):
31
+ * **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):
32
- Input can be of any tensor type.
32
+ Constrain input and output types to high-precision numeric tensors.
33
33
  * **T2** in ( tensor(int32), tensor(int64) ):
34
34
  axis tensor can be int32 or int64 only