Clip - 1 vs 6#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Clip1 → Clip6 +2 -0
Clip1 → Clip6
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Clip operator limits the given input within an interval. The interval is
|
|
2
2
|
specified with arguments 'min' and 'max'. They default to
|
|
3
3
|
numeric_limits::lowest() and numeric_limits::max() respectively.
|
|
4
4
|
**Attributes**
|
|
5
|
+
* **consumed_inputs**:
|
|
6
|
+
legacy optimization attribute.
|
|
5
7
|
* **max**:
|
|
6
8
|
Maximum value, above which element is replaced by max
|
|
7
9
|
* **min**:
|
|
8
10
|
Minimum value, under which element is replaced by min
|
|
9
11
|
**Inputs**
|
|
10
12
|
* **input** (heterogeneous) - **T**:
|
|
11
13
|
Input tensor whose elements to be clipped
|
|
12
14
|
**Outputs**
|
|
13
15
|
* **output** (heterogeneous) - **T**:
|
|
14
16
|
Output tensor with clipped input elements
|
|
15
17
|
**Type Constraints**
|
|
16
18
|
* **T** in (
|
|
17
19
|
tensor(double),
|
|
18
20
|
tensor(float),
|
|
19
21
|
tensor(float16)
|
|
20
22
|
):
|
|
21
23
|
Constrain input and output types to float tensors.
|