Sigmoid - 1 vs 6¶
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.
- Sigmoid1 → Sigmoid6 +0 -6
Sigmoid1 → Sigmoid6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Sigmoid takes one input data (Tensor<T>) and produces one output data
|
|
2
2
|
(Tensor<T>) where the sigmoid function, y = 1 / (1 + exp(-x)), is applied to the
|
|
3
3
|
tensor elementwise.
|
|
4
|
-
|
|
5
|
-
### Attributes
|
|
6
|
-
|
|
7
|
-
* **consumed_inputs - INTS** :
|
|
8
|
-
|
|
9
|
-
legacy optimization attribute.
|
|
10
4
|
### Inputs
|
|
11
5
|
- **X** (heterogeneous) - **T**:
|
|
12
6
|
Input tensor
|
|
13
7
|
### Outputs
|
|
14
8
|
- **Y** (heterogeneous) - **T**:
|
|
15
9
|
Output tensor
|
|
16
10
|
### Type Constraints
|
|
17
11
|
* **T** in ( tensor(double), tensor(float), tensor(float16) ):
|
|
18
12
|
Constrain input and output types to float tensors.
|