Max - 1 vs 6#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Max1 → Max6 +5 -0
Max1 → Max6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Element-wise max of each of the input tensors. All inputs and outputs must
|
|
2
2
|
have the same shape and data type.
|
|
3
|
+
|
|
4
|
+
**Attributes**
|
|
5
|
+
|
|
6
|
+
* **consumed_inputs**:
|
|
7
|
+
legacy optimization attribute.
|
|
3
8
|
**Inputs**
|
|
4
9
|
Between 1 and 2147483647 inputs.
|
|
5
10
|
* **data_0** (variadic, heterogeneous) - **T**:
|
|
6
11
|
List of tensors for Max.
|
|
7
12
|
**Outputs**
|
|
8
13
|
* **max** (heterogeneous) - **T**:
|
|
9
14
|
Output tensor. Same dimension as inputs.
|
|
10
15
|
**Type Constraints**
|
|
11
16
|
* **T** in (
|
|
12
17
|
tensor(double),
|
|
13
18
|
tensor(float),
|
|
14
19
|
tensor(float16)
|
|
15
20
|
):
|
|
16
21
|
Constrain input and output types to float tensors.
|