ReduceL2 - 1 vs 11

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. ReduceL21 → ReduceL211 +2 -3
ReduceL21 → ReduceL211 RENAMED
@@ -1 +1 @@
1
1
  Computes the L2 norm of the input tensor's element along the provided axes. The resulting
2
2
  tensor has the same rank as the input if keepdims equals 1. If keepdims equal 0, then
3
- the resulted tensor have the reduced dimension pruned. Input tensors of rank zero are
3
+ the resulted tensor have the reduced dimension pruned.
4
- valid. Reduction over an empty set of values yields 0.
5
4
  The above behavior is similar to numpy, with the exception that numpy defaults keepdims to
6
5
  False instead of True.
7
6
  ### Attributes
8
7
  * **axes - INTS** :
9
- A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor.
8
+ A list of integers, along which to reduce. The default is to reduce over all the dimensions of the input tensor. Accepted range is [-r, r-1] where r = rank(data).
10
9
  * **keepdims - INT** (default is '1'):
11
10
  Keep the reduced dimension or not, default 1 means keep reduced dimension.
12
11
  ### Inputs
13
12
  - **data** (heterogeneous) - **T**:
14
13
  An input tensor.
15
14
  ### Outputs
16
15
  - **reduced** (heterogeneous) - **T**:
17
16
  Reduced output tensor.
18
17
  ### Type Constraints
19
18
  * **T** in ( tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64) ):
20
19
  Constrain input and output types to high-precision numeric tensors.