TopK - 10 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. TopK10 → TopK11 +5 -23
TopK10 → TopK11 RENAMED
@@ -1 +1 @@
1
- Retrieve the top-K largest or smallest elements along a specified axis. Given an input tensor of
1
+ Retrieve the top-K elements along a specified axis. Given an input tensor of
2
2
  shape [a_1, a_2, ..., a_n, r] and integer argument k, return two outputs:
3
3
  -Value tensor of shape [a_1, a_2, ..., a_{axis-1}, k, a_{axis+1}, ... a_n]
4
4
  which contains the values of the top k elements along the specified axis
5
5
  -Index tensor of shape [a_1, a_2, ..., a_{axis-1}, k, a_{axis+1}, ... a_n] which
6
6
  contains the indices of the top k elements (original indices from the input
7
7
  tensor).
8
- If "largest" is 1 (the default value) then the k largest elements are returned.
9
- If "sorted" is 1 (the default value) then the resulting k elements will be sorted.
10
- If "sorted" is 0, order of returned 'Values' and 'Indices' are undefined.
11
-
12
- Given two equivalent values, this operator uses the indices along the axis as
8
+ Given two equivalent values, this operator uses the indices along the axis as
13
9
  a tiebreaker. That is, the element with the lower index will appear first.
14
10
  **Attributes**
15
11
  * **axis**:
12
+ Dimension on which to do the sort.
16
- Dimension on which to do the sort. Negative value means counting
17
- dimensions from the back. Accepted range is [-r, r-1] where r =
18
- rank(input).
19
- * **largest**:
20
- Whether to return the top-K largest or smallest elements.
21
- * **sorted**:
22
- Whether to return the elements in sorted order.
23
13
  **Inputs**
24
14
  * **X** (heterogeneous) - **T**:
25
15
  Tensor of shape [a_1, a_2, ..., a_n, r]
26
16
  * **K** (heterogeneous) - **tensor(int64)**:
27
17
  A 1-D tensor containing a single positive value corresponding to the
28
18
  number of top elements to retrieve
29
19
  **Outputs**
30
20
  * **Values** (heterogeneous) - **T**:
31
21
  Tensor of shape [a_1, a_2, ..., a_{axis-1}, k, a_{axis+1}, ... a_n]
32
22
  containing top K values from the input tensor
33
23
  * **Indices** (heterogeneous) - **I**:
34
24
  Tensor of shape [a_1, a_2, ..., a_{axis-1}, k, a_{axis+1}, ... a_n]
35
25
  containing the corresponding input tensor indices for the top K
36
26
  values.
37
27
  **Type Constraints**
38
28
  * **T** in (
39
29
  tensor(double),
40
30
  tensor(float),
41
- tensor(float16),
31
+ tensor(float16)
42
- tensor(int16),
43
- tensor(int32),
44
- tensor(int64),
45
- tensor(int8),
46
- tensor(uint16),
47
- tensor(uint32),
48
- tensor(uint64),
49
- tensor(uint8)
50
32
  ):
51
- Constrain input and output types to numeric tensors.
33
+ Constrain input and output types to float tensors.
52
34
  * **I** in (
53
35
  tensor(int64)
54
36
  ):
55
37
  Constrain index tensor to int64