ArgMin - 1 vs 11#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- ArgMin1 → ArgMin11 +2 -3
ArgMin1 → ArgMin11
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 equal 0, then the
|
|
3
|
+
If keepdims equal 0, then the resulted tensor have the reduced dimension pruned.
|
|
4
4
|
The type of the output tensor is integer.
|
|
5
5
|
**Attributes**
|
|
6
6
|
* **axis**:
|
|
7
|
-
The axis in which to compute the arg indices.
|
|
7
|
+
The axis in which to compute the arg indices.
|
|
8
|
-
r-1] where r = rank(data).
|
|
9
8
|
* **keepdims**:
|
|
10
9
|
Keep the reduced dimension or not, default 1 means keep reduced
|
|
11
10
|
dimension.
|
|
12
11
|
**Inputs**
|
|
13
12
|
* **data** (heterogeneous) - **T**:
|
|
14
13
|
An input tensor.
|
|
15
14
|
**Outputs**
|
|
16
15
|
* **reduced** (heterogeneous) - **tensor(int64)**:
|
|
17
16
|
Reduced output tensor with integer data type.
|
|
18
17
|
**Type Constraints**
|
|
19
18
|
* **T** in (
|
|
20
19
|
tensor(double),
|
|
21
20
|
tensor(float),
|
|
22
21
|
tensor(float16),
|
|
23
22
|
tensor(int16),
|
|
24
23
|
tensor(int32),
|
|
25
24
|
tensor(int64),
|
|
26
25
|
tensor(int8),
|
|
27
26
|
tensor(uint16),
|
|
28
27
|
tensor(uint32),
|
|
29
28
|
tensor(uint64),
|
|
30
29
|
tensor(uint8)
|
|
31
30
|
):
|
|
32
31
|
Constrain input and output types to all numeric tensors.
|