Max - 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Max12 → Max13 +0 -1
Max12 → Max13
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Element-wise max of each of the input tensors (with Numpy-style broadcasting support).
|
|
2
2
|
All inputs and outputs must have the same data type.
|
|
3
3
|
This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check Broadcasting in ONNX <https://github.com/onnx/onnx/blob/master/docs/Broadcasting.md>_.
|
|
4
4
|
**Inputs**
|
|
5
5
|
Between 1 and 2147483647 inputs.
|
|
6
6
|
* **data_0** (variadic, heterogeneous) - **T**:
|
|
7
7
|
List of tensors for max.
|
|
8
8
|
**Outputs**
|
|
9
9
|
* **max** (heterogeneous) - **T**:
|
|
10
10
|
Output tensor.
|
|
11
11
|
**Type Constraints**
|
|
12
12
|
* **T** in (
|
|
13
|
-
tensor(bfloat16),
|
|
14
13
|
tensor(double),
|
|
15
14
|
tensor(float),
|
|
16
15
|
tensor(float16),
|
|
17
16
|
tensor(int16),
|
|
18
17
|
tensor(int32),
|
|
19
18
|
tensor(int64),
|
|
20
19
|
tensor(int8),
|
|
21
20
|
tensor(uint16),
|
|
22
21
|
tensor(uint32),
|
|
23
22
|
tensor(uint64),
|
|
24
23
|
tensor(uint8)
|
|
25
24
|
):
|
|
26
25
|
Constrain input and output types to numeric tensors.
|