ArgMax - 1 vs 11¶
- ArgMax1 → ArgMax11 +3 -2
ArgMax1 → ArgMax11
RENAMED
@@ -1 +1 @@
|
|
1
1
|
Computes the indices of the max 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 resulting tensor has 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. Accepted range is [-r,
|
8
|
+
r-1] where r = rank(data).
|
8
9
|
* **keepdims**:
|
9
10
|
Keep the reduced dimension or not, default 1 means keep reduced
|
10
11
|
dimension.
|
11
12
|
**Inputs**
|
12
13
|
* **data** (heterogeneous) - **T**:
|
13
14
|
An input tensor.
|
14
15
|
**Outputs**
|
15
16
|
* **reduced** (heterogeneous) - **tensor(int64)**:
|
16
17
|
Reduced output tensor with integer data type.
|
17
18
|
**Type Constraints**
|
18
19
|
* **T** in (
|
19
20
|
tensor(double),
|
20
21
|
tensor(float),
|
21
22
|
tensor(float16),
|
22
23
|
tensor(int16),
|
23
24
|
tensor(int32),
|
24
25
|
tensor(int64),
|
25
26
|
tensor(int8),
|
26
27
|
tensor(uint16),
|
27
28
|
tensor(uint32),
|
28
29
|
tensor(uint64),
|
29
30
|
tensor(uint8)
|
30
31
|
):
|
31
32
|
Constrain input and output types to all numeric tensors.
|