ReduceMin - 18 vs 20¶
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
ReduceMin18 → ReduceMin20
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Computes the min of the input tensor's elements along the provided axes. The resulting
|
|
2
2
|
tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then
|
|
3
3
|
the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are
|
|
4
4
|
valid. Reduction over an empty set of values yields plus infinity (if supported by the datatype) or the maximum value of the data type otherwise.
|
|
5
|
+
|
|
6
|
+
If the input data type is Boolean, the comparison should consider False < True.
|
|
5
7
|
The above behavior is similar to numpy, with the exception that numpy defaults keepdims
|
|
6
8
|
to False instead of True.
|
|
7
9
|
### Attributes
|
|
8
10
|
* **keepdims - INT** (default is '1'):
|
|
9
11
|
Keep the reduced dimension or not, default 1 means keep reduced dimension.
|
|
10
12
|
* **noop_with_empty_axes - INT** (default is '0'):
|
|
11
13
|
Defines behavior when axes is not provided or is empty. If false (default), reduction happens over all axes. If true, no reduction is applied, but other operations will be performed. For example, ReduceSumSquare acts as a vanilla Square.
|
|
12
14
|
### Inputs
|
|
13
15
|
Between 1 and 2 inputs.
|
|
14
16
|
- **data** (heterogeneous) - **T**:
|
|
15
17
|
An input tensor.
|
|
16
18
|
- **axes** (optional, heterogeneous) - **tensor(int64)**:
|
|
17
19
|
Optional input list of integers, along which to reduce. The default is to reduce over empty axes. When axes is empty (either not provided or explicitly empty), behavior depends on 'noop_with_empty_axes': reduction over all axes if 'noop_with_empty_axes' is false, or no reduction is applied if 'noop_with_empty_axes' is true (but other operations will be performed). Accepted range is [-r, r-1] where r = rank(data).
|
|
18
20
|
### Outputs
|
|
19
21
|
- **reduced** (heterogeneous) - **T**:
|
|
20
22
|
Reduced output tensor.
|
|
21
23
|
### Type Constraints
|
|
22
|
-
* **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(int8), tensor(uint32), tensor(uint64), tensor(uint8) ):
|
|
24
|
+
* **T** in ( tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(int8), tensor(uint32), tensor(uint64), tensor(uint8) ):
|
|
23
|
-
Constrain input and output types to numeric tensors.+ Constrain input and output types to numeric and Boolean tensors.? ++++++++++++
|