Min - 1 vs 12¶
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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 → Min12 +7 -12
Min1 → Min12
RENAMED
|
@@ -1 +1 @@
|
|
|
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/main/docs/Broadcasting.md).
|
|
1
|
-
Element-wise min of each of the input tensors. All inputs and outputs must
|
|
2
|
-
have the same shape and data type.
|
|
3
|
-
|
|
4
|
-
### Attributes
|
|
5
|
-
|
|
6
|
-
* **consumed_inputs - INTS** :
|
|
7
|
-
|
|
8
|
-
legacy optimization attribute.
|
|
9
4
|
### Inputs
|
|
10
5
|
Between 1 and 2147483647 inputs.
|
|
11
6
|
- **data_0** (variadic, heterogeneous) - **T**:
|
|
12
|
-
List of tensors for
|
|
7
|
+
List of tensors for min.
|
|
13
8
|
### Outputs
|
|
14
9
|
- **min** (heterogeneous) - **T**:
|
|
15
|
-
Output tensor.
|
|
10
|
+
Output tensor.
|
|
16
11
|
### Type Constraints
|
|
17
|
-
* **T** in ( tensor(double), tensor(float), tensor(float16) ):
|
|
12
|
+
* **T** in ( tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
|
|
18
|
-
Constrain input and output types to
|
|
13
|
+
Constrain input and output types to numeric tensors.? ^^^^^^^
|