ArgMax - 12 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- ArgMax12 → ArgMax13 +2 -2
ArgMax12 → ArgMax13
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
|
3
|
+
If keepdims equals 0, then the resulting tensor has the reduced dimension pruned.
|
4
4
|
If select_last_index is True (default False), the index of the last occurrence of the max
|
5
5
|
is selected if the max appears more than once in the input. Otherwise the index of the
|
6
6
|
first occurrence is selected.
|
7
7
|
The type of the output tensor is integer.
|
8
8
|
### Attributes
|
9
9
|
* **axis - INT** (default is '0'):
|
10
10
|
The axis in which to compute the arg indices. Accepted range is [-r, r-1] where r = rank(data).
|
11
11
|
* **keepdims - INT** (default is '1'):
|
12
12
|
Keep the reduced dimension or not, default 1 means keep reduced dimension.
|
13
13
|
* **select_last_index - INT** (default is '0'):
|
14
14
|
Whether to select the last index or the first index if the {name} appears in multiple indices, default is False (first index).
|
15
15
|
### Inputs
|
16
16
|
- **data** (heterogeneous) - **T**:
|
17
17
|
An input tensor.
|
18
18
|
### Outputs
|
19
19
|
- **reduced** (heterogeneous) - **tensor(int64)**:
|
20
20
|
Reduced output tensor with integer data type.
|
21
21
|
### Type Constraints
|
22
|
-
* **T** in ( tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
|
22
|
+
* **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
|
23
23
|
Constrain input and output types to all numeric tensors.
|