Relu - 1 vs 6¶
- Relu1 → Relu6 +0 -5
Relu1 → Relu6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Relu takes one input data (Tensor<T>) and produces one output data
|
|
2
2
|
(Tensor<T>) where the rectified linear function, y = max(0, 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
14
|
tensor(float16)
|
|
20
15
|
):
|
|
21
16
|
Constrain input and output types to float tensors.
|