Elu - 1 vs 6¶
- Elu1 → Elu6 +2 -4
Elu1 → Elu6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Elu takes one input data (Tensor<T>) and produces one output data
|
|
2
2
|
(Tensor<T>) where the function f(x) = alpha * (exp(x) - 1.) for x <
|
|
3
3
|
0, f(x) = x for x >= 0., is applied to the tensor elementwise.
|
|
4
4
|
**Attributes**
|
|
5
5
|
* **alpha**:
|
|
6
|
+
Coefficient of ELU.
|
|
6
|
-
Coefficient of ELU default to 1.0.
|
|
7
|
-
* **consumed_inputs**:
|
|
8
|
-
legacy optimization attribute.
|
|
9
7
|
**Inputs**
|
|
10
8
|
* **X** (heterogeneous) - **T**:
|
|
11
9
|
1D input tensor
|
|
12
10
|
**Outputs**
|
|
13
11
|
* **Y** (heterogeneous) - **T**:
|
|
14
|
-
1D
|
|
12
|
+
1D output tensor
|
|
15
13
|
**Type Constraints**
|
|
16
14
|
* **T** in (
|
|
17
15
|
tensor(double),
|
|
18
16
|
tensor(float),
|
|
19
17
|
tensor(float16)
|
|
20
18
|
):
|
|
21
19
|
Constrain input and output types to float tensors.
|