PRelu - 6 vs 9#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. PRelu6 → PRelu9 +5 -10
PRelu6 → PRelu9 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>_.
5
4
  **Inputs**
6
5
  * **X** (heterogeneous) - **T**:
7
6
  Input tensor
8
7
  * **slope** (heterogeneous) - **T**:
9
- Slope tensor. The shape of slope can be smaller then first input X;
8
+ Slope tensor. If Slope is of size 1, the value is sharedacross
10
- if so, its shape must be unidirectional broadcastable to X
9
+ different channels
11
10
  **Outputs**
12
11
  * **Y** (heterogeneous) - **T**:
13
- Output tensor (same size as X)
12
+ Output tensor
14
13
  **Type Constraints**
15
14
  * **T** in (
16
15
  tensor(double),
17
16
  tensor(float),
18
- tensor(float16),
17
+ tensor(float16)
19
- tensor(int32),
20
- tensor(int64),
21
- tensor(uint32),
22
- tensor(uint64)
23
18
  ):
24
- Constrain input and output types to float/int tensors.? ----
19
+ Constrain input and output types to float tensors.