Min - 1 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Min1 → Min13 +11 -16
Min1 → Min13
RENAMED
@@ -1 +1 @@
|
|
1
|
-
Element-wise min of each of the input tensors
|
1
|
+
Element-wise min 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**:
|
3
|
-
|
7
|
+
legacy optimization attribute.
|
4
8
|
**Inputs**
|
5
9
|
Between 1 and 2147483647 inputs.
|
6
10
|
* **data_0** (variadic, heterogeneous) - **T**:
|
7
|
-
List of tensors for
|
11
|
+
List of tensors for Min
|
8
12
|
**Outputs**
|
9
13
|
* **min** (heterogeneous) - **T**:
|
10
|
-
Output tensor.
|
14
|
+
Output tensor. Same dimension as inputs.
|
11
15
|
**Type Constraints**
|
12
16
|
* **T** in (
|
13
|
-
tensor(bfloat16),
|
14
17
|
tensor(double),
|
15
18
|
tensor(float),
|
16
|
-
tensor(float16)
|
19
|
+
tensor(float16)
|
17
|
-
tensor(int16),
|
18
|
-
tensor(int32),
|
19
|
-
tensor(int64),
|
20
|
-
tensor(int8),
|
21
|
-
tensor(uint16),
|
22
|
-
tensor(uint32),
|
23
|
-
tensor(uint64),
|
24
|
-
tensor(uint8)
|
25
20
|
):
|
26
|
-
Constrain input and output types to
|
21
|
+
Constrain input and output types to float tensors.? ^^^^^
|