Round - 11 vs 22¶
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Round11 → Round22 +1 -1
Round11 → Round22
RENAMED
@@ -1 +1 @@
|
|
1
1
|
Round takes one input Tensor and rounds the values, element-wise, meaning
|
2
2
|
it finds the nearest integer for each value.
|
3
3
|
In case of halves, the rule is to round them to the nearest even integer.
|
4
4
|
If input x is integral, +0, -0, NaN, or infinite, x itself is returned.
|
5
5
|
The output tensor has the same shape and type as the input.
|
6
6
|
Examples:
|
7
7
|
round([0.9]) = [1.0]
|
8
8
|
round([2.5]) = [2.0]
|
9
9
|
round([2.3]) = [2.0]
|
10
10
|
round([1.5]) = [2.0]
|
11
11
|
round([-4.5]) = [-4.0]
|
12
12
|
### Inputs
|
13
13
|
- **X** (heterogeneous) - **T**:
|
14
14
|
Input tensor
|
15
15
|
### Outputs
|
16
16
|
- **Y** (heterogeneous) - **T**:
|
17
17
|
Output tensor
|
18
18
|
### Type Constraints
|
19
|
-
* **T** in ( tensor(double), tensor(float), tensor(float16) ):
|
19
|
+
* **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16) ):
|
20
20
|
Constrain input and output types to float tensors.
|