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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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 -6
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
|
+
* **max - FLOAT** (default is '(3.402823e+38)'):
|
5
|
-
* **consumed_inputs - INTS** :
|
6
|
-
|
7
|
-
legacy optimization attribute.
|
8
|
-
|
9
|
-
* **max - FLOAT** :
|
10
6
|
Maximum value, above which element is replaced by max
|
11
|
-
* **min - FLOAT** :
|
7
|
+
* **min - FLOAT** (default is '(-3.402823e+38)'):
|
12
8
|
Minimum value, under which element is replaced by min
|
13
9
|
### Inputs
|
14
10
|
- **input** (heterogeneous) - **T**:
|
15
11
|
Input tensor whose elements to be clipped
|
16
12
|
### Outputs
|
17
13
|
- **output** (heterogeneous) - **T**:
|
18
14
|
Output tensor with clipped input elements
|
19
15
|
### Type Constraints
|
20
16
|
* **T** in ( tensor(double), tensor(float), tensor(float16) ):
|
21
17
|
Constrain input and output types to float tensors.
|