Abs - 1 vs 6

Files changed (1) hide show
  1. Abs1 → Abs6 +10 -7
Abs1 → Abs6 RENAMED
@@ -1 +1 @@
1
1
  Absolute takes one input data (Tensor<T>) and produces one output data
2
2
  (Tensor<T>) where the absolute is, y = abs(x), is applied to
3
3
  the tensor elementwise.
4
-
5
- **Attributes**
6
-
7
- * **consumed_inputs**:
8
- legacy optimization attribute.
9
4
  **Inputs**
10
5
  * **X** (heterogeneous) - **T**:
11
6
  Input tensor
12
7
  **Outputs**
13
8
  * **Y** (heterogeneous) - **T**:
14
9
  Output tensor
15
10
  **Type Constraints**
16
11
  * **T** in (
17
12
  tensor(double),
18
13
  tensor(float),
19
- tensor(float16)
14
+ tensor(float16),
15
+ tensor(int16),
16
+ tensor(int32),
17
+ tensor(int64),
18
+ tensor(int8),
19
+ tensor(uint16),
20
+ tensor(uint32),
21
+ tensor(uint64),
22
+ tensor(uint8)
20
23
  ):
21
- Constrain input and output types to float tensors.? ^ ^^^
24
+ Constrain input and output types to all numeric tensors.? ^ ^^^^^^^^^