ArgMin - 11 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- ArgMin11 → ArgMin13 +1 -8
ArgMin11 → 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
|
3
|
+
If keepdims equal 0, then the resulting tensor has the reduced dimension pruned.
|
4
|
-
If select_last_index is True (default False), the index of the last occurrence of the min
|
5
|
-
is selected if the min appears more than once in the input. Otherwise the index of the
|
6
|
-
first occurrence is selected.
|
7
4
|
The type of the output tensor is integer.
|
8
5
|
**Attributes**
|
9
6
|
* **axis**:
|
10
7
|
The axis in which to compute the arg indices. Accepted range is [-r,
|
11
8
|
r-1] where r = rank(data).
|
12
9
|
* **keepdims**:
|
13
10
|
Keep the reduced dimension or not, default 1 means keep reduced
|
14
11
|
dimension.
|
15
|
-
* **select_last_index**:
|
16
|
-
Whether to select the last index or the first index if the {name}
|
17
|
-
appears in multiple indices, default is False (first index).
|
18
12
|
**Inputs**
|
19
13
|
* **data** (heterogeneous) - **T**:
|
20
14
|
An input tensor.
|
21
15
|
**Outputs**
|
22
16
|
* **reduced** (heterogeneous) - **tensor(int64)**:
|
23
17
|
Reduced output tensor with integer data type.
|
24
18
|
**Type Constraints**
|
25
19
|
* **T** in (
|
26
|
-
tensor(bfloat16),
|
27
20
|
tensor(double),
|
28
21
|
tensor(float),
|
29
22
|
tensor(float16),
|
30
23
|
tensor(int16),
|
31
24
|
tensor(int32),
|
32
25
|
tensor(int64),
|
33
26
|
tensor(int8),
|
34
27
|
tensor(uint16),
|
35
28
|
tensor(uint32),
|
36
29
|
tensor(uint64),
|
37
30
|
tensor(uint8)
|
38
31
|
):
|
39
32
|
Constrain input and output types to all numeric tensors.
|