ArgMin - 12 vs 13#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. ArgMin12 → ArgMin13 +1 -2
ArgMin12 → ArgMin13 RENAMED
@@ -1 +1 @@
1
1
  Computes the indices of the min elements of the input tensor's element along the
2
2
  provided axis. The resulting tensor has the same rank as the input if keepdims equals 1.
3
- If keepdims equals 0, then the resulting tensor has the reduced dimension pruned.
3
+ If keepdims equal 0, then the resulting tensor has the reduced dimension pruned.
4
4
  If select_last_index is True (default False), the index of the last occurrence of the min
5
5
  is selected if the min appears more than once in the input. Otherwise the index of the
6
6
  first occurrence is selected.
7
7
  The type of the output tensor is integer.
8
8
  **Attributes**
9
9
  * **axis**:
10
10
  The axis in which to compute the arg indices. Accepted range is [-r,
11
11
  r-1] where r = rank(data).
12
12
  * **keepdims**:
13
13
  Keep the reduced dimension or not, default 1 means keep reduced
14
14
  dimension.
15
15
  * **select_last_index**:
16
16
  Whether to select the last index or the first index if the {name}
17
17
  appears in multiple indices, default is False (first index).
18
18
  **Inputs**
19
19
  * **data** (heterogeneous) - **T**:
20
20
  An input tensor.
21
21
  **Outputs**
22
22
  * **reduced** (heterogeneous) - **tensor(int64)**:
23
23
  Reduced output tensor with integer data type.
24
24
  **Type Constraints**
25
25
  * **T** in (
26
- tensor(bfloat16),
27
26
  tensor(double),
28
27
  tensor(float),
29
28
  tensor(float16),
30
29
  tensor(int16),
31
30
  tensor(int32),
32
31
  tensor(int64),
33
32
  tensor(int8),
34
33
  tensor(uint16),
35
34
  tensor(uint32),
36
35
  tensor(uint64),
37
36
  tensor(uint8)
38
37
  ):
39
38
  Constrain input and output types to all numeric tensors.