PRelu - 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- PRelu1 → PRelu6 +5 -0
PRelu1 → PRelu6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
PRelu takes input data (Tensor<T>) and slope tensor as input, and produces one
|
|
2
2
|
output data (Tensor<T>) where the function f(x) = slope * x for x < 0,
|
|
3
3
|
f(x) = x for x >= 0., is applied to the data tensor elementwise.
|
|
4
|
+
|
|
5
|
+
**Attributes**
|
|
6
|
+
|
|
7
|
+
* **consumed_inputs**:
|
|
8
|
+
legacy optimization attribute.
|
|
4
9
|
**Inputs**
|
|
5
10
|
* **X** (heterogeneous) - **T**:
|
|
6
11
|
Input tensor
|
|
7
12
|
* **slope** (heterogeneous) - **T**:
|
|
8
13
|
Slope tensor. If Slope is of size 1, the value is sharedacross
|
|
9
14
|
different channels
|
|
10
15
|
**Outputs**
|
|
11
16
|
* **Y** (heterogeneous) - **T**:
|
|
12
17
|
Output tensor
|
|
13
18
|
**Type Constraints**
|
|
14
19
|
* **T** in (
|
|
15
20
|
tensor(double),
|
|
16
21
|
tensor(float),
|
|
17
22
|
tensor(float16)
|
|
18
23
|
):
|
|
19
24
|
Constrain input and output types to float tensors.
|