PRelu - 1 vs 7¶
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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 → PRelu7 +3 -8
PRelu1 → 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/main/docs/Broadcasting.md).
|
4
|
-
|
5
|
-
### Attributes
|
6
|
-
|
7
|
-
* **consumed_inputs - INTS** :
|
8
|
-
|
9
|
-
legacy optimization attribute.
|
10
5
|
### Inputs
|
11
6
|
- **X** (heterogeneous) - **T**:
|
12
7
|
Input tensor
|
13
8
|
- **slope** (heterogeneous) - **T**:
|
14
|
-
Slope tensor.
|
9
|
+
Slope tensor. The shape of slope can be smaller than first input X; if so, its shape must be unidirectional broadcastable to X
|
15
10
|
### Outputs
|
16
11
|
- **Y** (heterogeneous) - **T**:
|
17
|
-
Output tensor
|
12
|
+
Output tensor (same size as X)
|
18
13
|
### Type Constraints
|
19
14
|
* **T** in ( tensor(double), tensor(float), tensor(float16) ):
|
20
15
|
Constrain input and output types to float tensors.
|