ReduceMean - 11 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
ReduceMean11 → ReduceMean13
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Computes the mean of the input tensor's element along the provided axes. The resulting
|
|
2
|
-
tensor has the same rank as the input if keepdims equals 1. If keepdims
|
|
2
|
+
tensor has the same rank as the input if keepdims equals 1. If keepdims equal 0, then
|
|
3
|
-
the
|
|
3
|
+
the resulted tensor have the reduced dimension pruned.
|
|
4
4
|
The above behavior is similar to numpy, with the exception that numpy defaults keepdims to
|
|
5
5
|
False instead of True.
|
|
6
6
|
**Attributes**
|
|
7
7
|
* **axes**:
|
|
8
8
|
A list of integers, along which to reduce. The default is to reduce
|
|
9
9
|
over all the dimensions of the input tensor. Accepted range is [-r,
|
|
10
10
|
r-1] where r = rank(data).
|
|
11
11
|
* **keepdims**:
|
|
12
12
|
Keep the reduced dimension or not, default 1 means keep reduced
|
|
13
13
|
dimension.
|
|
14
14
|
**Inputs**
|
|
15
15
|
* **data** (heterogeneous) - **T**:
|
|
16
16
|
An input tensor.
|
|
17
17
|
**Outputs**
|
|
18
18
|
* **reduced** (heterogeneous) - **T**:
|
|
19
19
|
Reduced output tensor.
|
|
20
20
|
**Type Constraints**
|
|
21
21
|
* **T** in (
|
|
22
|
-
tensor(bfloat16),
|
|
23
22
|
tensor(double),
|
|
24
23
|
tensor(float),
|
|
25
24
|
tensor(float16),
|
|
26
25
|
tensor(int32),
|
|
27
26
|
tensor(int64),
|
|
28
27
|
tensor(uint32),
|
|
29
28
|
tensor(uint64)
|
|
30
29
|
):
|
|
31
30
|
Constrain input and output types to high-precision numeric tensors.
|