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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.

Files changed (1) hide show
  1. Min1 → Min13 +11 -16
Min1 → Min13 RENAMED
@@ -1 +1 @@
1
- Element-wise min of each of the input tensors (with Numpy-style broadcasting support).
1
+ Element-wise min of each of the input tensors. All inputs and outputs must
2
- All inputs and outputs must have the same data type.
2
+ have the same shape and data type.
3
+
4
+ **Attributes**
5
+
6
+ * **consumed_inputs**:
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>_.
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 min.
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 numeric tensors.? ^^^^^^^
21
+ Constrain input and output types to float tensors.? ^^^^^