Min - 6 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Min6 → Min13 +6 -16
Min6 → Min13
RENAMED
|
@@ -1 +1 @@
|
|
|
1
|
+
Element-wise min of each of the input tensors. All inputs and outputs must
|
|
2
|
+
have the same shape and data type.
|
|
1
|
-
Element-wise min of each of the input tensors (with Numpy-style broadcasting support).
|
|
2
|
-
All inputs and outputs must have the same data type.
|
|
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
3
|
**Inputs**
|
|
5
4
|
Between 1 and 2147483647 inputs.
|
|
6
5
|
* **data_0** (variadic, heterogeneous) - **T**:
|
|
7
|
-
List of tensors for
|
|
6
|
+
List of tensors for Min
|
|
8
7
|
**Outputs**
|
|
9
8
|
* **min** (heterogeneous) - **T**:
|
|
10
|
-
Output tensor.
|
|
9
|
+
Output tensor. Same dimension as inputs.
|
|
11
10
|
**Type Constraints**
|
|
12
11
|
* **T** in (
|
|
13
|
-
tensor(bfloat16),
|
|
14
12
|
tensor(double),
|
|
15
13
|
tensor(float),
|
|
16
|
-
tensor(float16)
|
|
14
|
+
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
15
|
):
|
|
26
|
-
Constrain input and output types to
|
|
16
|
+
Constrain input and output types to float tensors.? ^^^^^
|