Div - 13 vs 14¶
- Div13 → Div14 +8 -2
Div13 → Div14
RENAMED
@@ -1 +1 @@
|
|
1
1
|
Performs element-wise binary division (with Numpy-style broadcasting support).
|
2
2
|
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>_.
|
3
|
+
|
4
|
+
(Opset 14 change): Extend supported types to include uint8, int8, uint16, and int16.
|
3
5
|
**Inputs**
|
4
6
|
* **A** (heterogeneous) - **T**:
|
5
7
|
First operand.
|
6
8
|
* **B** (heterogeneous) - **T**:
|
7
9
|
Second operand.
|
8
10
|
**Outputs**
|
9
11
|
* **C** (heterogeneous) - **T**:
|
10
12
|
Result, has same element type as two inputs
|
11
13
|
**Type Constraints**
|
12
14
|
* **T** in (
|
13
15
|
tensor(bfloat16),
|
14
16
|
tensor(double),
|
15
17
|
tensor(float),
|
16
18
|
tensor(float16),
|
19
|
+
tensor(int16),
|
17
20
|
tensor(int32),
|
18
21
|
tensor(int64),
|
22
|
+
tensor(int8),
|
23
|
+
tensor(uint16),
|
19
24
|
tensor(uint32),
|
20
|
-
tensor(uint64)
|
25
|
+
tensor(uint64),
|
26
|
+
tensor(uint8)
|
21
27
|
):
|
22
|
-
Constrain input and output types to
|
28
|
+
Constrain input and output types to all numeric tensors.? ^^^
|