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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.

Files changed (1) hide show
  1. PRelu1 → PRelu7 +8 -4
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/master/docs/Broadcasting.md>_.
4
+
5
+ **Attributes**
6
+
7
+ * **consumed_inputs**:
8
+ legacy optimization attribute.
5
9
  **Inputs**
6
10
  * **X** (heterogeneous) - **T**:
7
11
  Input tensor
8
12
  * **slope** (heterogeneous) - **T**:
9
- Slope tensor. The shape of slope can be smaller then first input X;
13
+ Slope tensor. If Slope is of size 1, the value is sharedacross
10
- if so, its shape must be unidirectional broadcastable to X
14
+ different channels
11
15
  **Outputs**
12
16
  * **Y** (heterogeneous) - **T**:
13
- Output tensor (same size as X)
17
+ Output tensor
14
18
  **Type Constraints**
15
19
  * **T** in (
16
20
  tensor(double),
17
21
  tensor(float),
18
22
  tensor(float16)
19
23
  ):
20
24
  Constrain input and output types to float tensors.