PRelu - 6 vs 7¶
- PRelu6 → PRelu7 +4 -3
PRelu6 → PRelu7
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
|
+
This operator supports **unidirectional broadcasting** (tensor slope should be unidirectional broadcastable to input tensor X); for more details please check Broadcasting in ONNX <https://github.com/onnx/onnx/blob/master/docs/Broadcasting.md>_.
|
4
5
|
**Inputs**
|
5
6
|
* **X** (heterogeneous) - **T**:
|
6
7
|
Input tensor
|
7
8
|
* **slope** (heterogeneous) - **T**:
|
8
|
-
Slope tensor.
|
9
|
+
Slope tensor. The shape of slope can be smaller then first input X;
|
9
|
-
|
10
|
+
if so, its shape must be unidirectional broadcastable to X
|
10
11
|
**Outputs**
|
11
12
|
* **Y** (heterogeneous) - **T**:
|
12
|
-
Output tensor
|
13
|
+
Output tensor (same size as X)
|
13
14
|
**Type Constraints**
|
14
15
|
* **T** in (
|
15
16
|
tensor(double),
|
16
17
|
tensor(float),
|
17
18
|
tensor(float16)
|
18
19
|
):
|
19
20
|
Constrain input and output types to float tensors.
|