ArgMax - 1 vs 11

Files changed (1) hide show
  1. 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 resulted tensor have the reduced dimension pruned.
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.