Less - 1 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. Less1 → Less13 +6 -18
Less1 → Less13 RENAMED
@@ -1 +1 @@
1
1
  Returns the tensor resulted from performing the less logical operation
2
- elementwise on the input tensors A and B.
2
+ elementwise on the input tensors A and B (with Numpy-style broadcasting support).
3
+ This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).
3
- If broadcasting is enabled, the right-hand-side argument will be broadcasted
4
- to match the shape of left-hand-side argument. See the doc of Add for a
5
- detailed description of the broadcasting rules.
6
-
7
- ### Attributes
8
-
9
- * **axis - INT** :
10
-
11
- If set, defines the broadcast dimensions.
12
-
13
- * **broadcast - INT** (default is '0'):
14
-
15
- Enable broadcasting
16
4
  ### Inputs
17
5
  - **A** (heterogeneous) - **T**:
18
- Left input tensor for the logical operator.
6
+ First input operand for the logical operator.
19
7
  - **B** (heterogeneous) - **T**:
20
- Right input tensor for the logical operator.
8
+ Second input operand for the logical operator.
21
9
  ### Outputs
22
10
  - **C** (heterogeneous) - **T1**:
23
11
  Result tensor.
24
12
  ### Type Constraints
25
- * **T** in ( tensor(double), tensor(float), tensor(float16) ):
13
+ * **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
26
- Constrain input to float tensors.
14
+ Constrain input types to all numeric tensors.
27
15
  * **T1** in ( tensor(bool) ):
28
16
  Constrain output to boolean tensor.