Sum - 6 vs 8

Files changed (1) hide show
  1. Sum6 → Sum8 +5 -4
Sum6 → Sum8 RENAMED
@@ -1 +1 @@
1
- Element-wise sum of each of the input tensors. All inputs and outputs must
1
+ Element-wise sum of each of the input tensors (with Numpy-style broadcasting support).
2
- have the same shape and data type.
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>_.
3
4
  **Inputs**
4
5
  Between 1 and 2147483647 inputs.
5
6
  * **data_0** (variadic, heterogeneous) - **T**:
6
- List of tensors for Sum.
7
+ List of tensors for sum.
7
8
  **Outputs**
8
9
  * **sum** (heterogeneous) - **T**:
9
- Output tensor. Same dimension as inputs.
10
+ Output tensor.
10
11
  **Type Constraints**
11
12
  * **T** in (
12
13
  tensor(double),
13
14
  tensor(float),
14
15
  tensor(float16)
15
16
  ):
16
17
  Constrain input and output types to float tensors.