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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.

Files changed (1) hide show
  1. 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 equal 0, then the resulting tensor has the reduced dimension pruned.
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.