LeakyRelu - 1 vs 16

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. LeakyRelu1 → LeakyRelu16 +3 -5

LeakyRelu1 → LeakyRelu16 RENAMED Viewed

	@@ -1 +1 @@
1 1	LeakyRelu takes input data (Tensor<T>) and an argument alpha, and produces one
2 2	output data (Tensor<T>) where the function f(x) = alpha * x for x < 0,
3 3	f(x) = x for x >= 0, is applied to the data tensor elementwise.
4	- **History**
5	- - Version 16 adds bfloat16 to the types allowed.
6	-
7 4	**Attributes**
8 5	* **alpha**:
9	- Coefficient of leakage.
6	+ Coefficient of leakage default to 0.01.
7	+ * **consumed_inputs**:
8	+ legacy optimization attribute.
10 9	**Inputs**
11 10	* **X** (heterogeneous) - **T**:
12 11	Input tensor
13 12	**Outputs**
14 13	* **Y** (heterogeneous) - **T**:
15 14	Output tensor
16 15	**Type Constraints**
17 16	* **T** in (
18	- tensor(bfloat16),
19 17	tensor(double),
20 18	tensor(float),
21 19	tensor(float16)
22 20	):
23 21	Constrain input and output types to float tensors.