MeanVarianceNormalization - 9 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
MeanVarianceNormalization9 → MeanVarianceNormalization13
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
A MeanVarianceNormalization Function: Perform mean variance normalization
|
|
2
2
|
on the input tensor X using formula: <br/> (X-EX)/sqrt(E(X-EX)^2)
|
|
3
3
|
**Attributes**
|
|
4
4
|
* **axes**:
|
|
5
5
|
A list of integers, along which to reduce. The default is to
|
|
6
6
|
caculate along axes [0,2,3] for calculating mean and variance along
|
|
7
7
|
each channel. Two variables with the same C-coordinate are
|
|
8
8
|
associated with the same mean and variance.
|
|
9
9
|
**Inputs**
|
|
10
10
|
* **X** (heterogeneous) - **T**:
|
|
11
11
|
Input tensor
|
|
12
12
|
**Outputs**
|
|
13
13
|
* **Y** (heterogeneous) - **T**:
|
|
14
14
|
Output tensor
|
|
15
15
|
**Type Constraints**
|
|
16
16
|
* **T** in (
|
|
17
|
-
tensor(bfloat16),
|
|
18
17
|
tensor(double),
|
|
19
18
|
tensor(float),
|
|
20
19
|
tensor(float16)
|
|
21
20
|
):
|
|
22
21
|
Constrain input and output types to all numeric tensors.
|