ArgMin - 11 vs 12¶
- ArgMin11 → ArgMin12 +6 -0
ArgMin11 → ArgMin12
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
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.
|
|
4
7
|
The type of the output tensor is integer.
|
|
5
8
|
**Attributes**
|
|
6
9
|
* **axis**:
|
|
7
10
|
The axis in which to compute the arg indices. Accepted range is [-r,
|
|
8
11
|
r-1] where r = rank(data).
|
|
9
12
|
* **keepdims**:
|
|
10
13
|
Keep the reduced dimension or not, default 1 means keep reduced
|
|
11
14
|
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).
|
|
12
18
|
**Inputs**
|
|
13
19
|
* **data** (heterogeneous) - **T**:
|
|
14
20
|
An input tensor.
|
|
15
21
|
**Outputs**
|
|
16
22
|
* **reduced** (heterogeneous) - **tensor(int64)**:
|
|
17
23
|
Reduced output tensor with integer data type.
|
|
18
24
|
**Type Constraints**
|
|
19
25
|
* **T** in (
|
|
20
26
|
tensor(double),
|
|
21
27
|
tensor(float),
|
|
22
28
|
tensor(float16),
|
|
23
29
|
tensor(int16),
|
|
24
30
|
tensor(int32),
|
|
25
31
|
tensor(int64),
|
|
26
32
|
tensor(int8),
|
|
27
33
|
tensor(uint16),
|
|
28
34
|
tensor(uint32),
|
|
29
35
|
tensor(uint64),
|
|
30
36
|
tensor(uint8)
|
|
31
37
|
):
|
|
32
38
|
Constrain input and output types to all numeric tensors.
|