Mod - 10 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.

Files changed (1) hide show
  1. Mod10 → Mod13 +0 -1
Mod10 → Mod13 RENAMED
@@ -1 +1 @@
1
1
  Performs element-wise binary modulus (with Numpy-style broadcasting support).
2
2
  The sign of the remainder is the same as that of the Divisor.
3
3
  Mod operator can also behave like C fmod() or numpy.fmod. In this case, the sign of the remainder however, will be the same as the Dividend
4
4
  (in contrast to integer mod). To force a behavior like numpy.fmod() an 'fmod' Attribute is provided.
5
5
  This attribute is set to 0 by default causing the behavior to be like integer mod.
6
6
  Setting this attribute to 1 causes the remainder to be calculated similar to that of numpy.fmod().
7
7
  If the input type is floating point, then fmod attribute must be set to 1.
8
8
  In case of dividend being zero, the results will be platform dependent.
9
9
  This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check Broadcasting in ONNX <https://github.com/onnx/onnx/blob/master/docs/Broadcasting.md>_.
10
10
  **Attributes**
11
11
  * **fmod**:
12
12
  Whether the operator should behave like fmod (default=0 meaning it
13
13
  will do integer mods); Set this to 1 to force fmod treatment
14
14
  **Inputs**
15
15
  * **A** (heterogeneous) - **T**:
16
16
  Dividend tensor
17
17
  * **B** (heterogeneous) - **T**:
18
18
  Divisor tensor
19
19
  **Outputs**
20
20
  * **C** (heterogeneous) - **T**:
21
21
  Remainder tensor
22
22
  **Type Constraints**
23
23
  * **T** in (
24
- tensor(bfloat16),
25
24
  tensor(double),
26
25
  tensor(float),
27
26
  tensor(float16),
28
27
  tensor(int16),
29
28
  tensor(int32),
30
29
  tensor(int64),
31
30
  tensor(int8),
32
31
  tensor(uint16),
33
32
  tensor(uint32),
34
33
  tensor(uint64),
35
34
  tensor(uint8)
36
35
  ):
37
36
  Constrain input and output types to high-precision numeric tensors.