Relu - 1 vs 13#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Relu1 → Relu13 +5 -1
Relu1 → Relu13
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Relu takes one input data (Tensor<T>) and produces one output data
|
|
2
2
|
(Tensor<T>) where the rectified linear function, y = max(0, x), is applied to
|
|
3
3
|
the tensor elementwise.
|
|
4
|
+
|
|
5
|
+
**Attributes**
|
|
6
|
+
|
|
7
|
+
* **consumed_inputs**:
|
|
8
|
+
legacy optimization attribute.
|
|
4
9
|
**Inputs**
|
|
5
10
|
* **X** (heterogeneous) - **T**:
|
|
6
11
|
Input tensor
|
|
7
12
|
**Outputs**
|
|
8
13
|
* **Y** (heterogeneous) - **T**:
|
|
9
14
|
Output tensor
|
|
10
15
|
**Type Constraints**
|
|
11
16
|
* **T** in (
|
|
12
|
-
tensor(bfloat16),
|
|
13
17
|
tensor(double),
|
|
14
18
|
tensor(float),
|
|
15
19
|
tensor(float16)
|
|
16
20
|
):
|
|
17
21
|
Constrain input and output types to float tensors.
|