TopK - 1 vs 10#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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. TopK1 → TopK10 +2 -4
TopK1 → TopK10 RENAMED
@@ -1 +1 @@
1
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
-
9
8
  Given two equivalent values, this operator uses the indices along the axis as
10
9
  a tiebreaker. That is, the element with the lower index will appear first.
11
10
  **Attributes**
12
11
  * **axis**:
13
12
  Dimension on which to do the sort.
13
+ * **k** (required):
14
+ Number of top elements to retrieve
14
15
  **Inputs**
15
16
  * **X** (heterogeneous) - **T**:
16
17
  Tensor of shape [a_1, a_2, ..., a_n, r]
17
- * **K** (heterogeneous) - **tensor(int64)**:
18
- A 1-D tensor containing a single positive value corresponding to the
19
- number of top elements to retrieve
20
18
  **Outputs**
21
19
  * **Values** (heterogeneous) - **T**:
22
20
  Tensor of shape [a_1, a_2, ..., a_{axis-1}, k, a_{axis+1}, ... a_n]
23
21
  containing top K values from the input tensor
24
22
  * **Indices** (heterogeneous) - **I**:
25
23
  Tensor of shape [a_1, a_2, ..., a_{axis-1}, k, a_{axis+1}, ... a_n]
26
24
  containing the corresponding input tensor indices for the top K
27
25
  values.
28
26
  **Type Constraints**
29
27
  * **T** in (
30
28
  tensor(double),
31
29
  tensor(float),
32
30
  tensor(float16)
33
31
  ):
34
32
  Constrain input and output types to float tensors.
35
33
  * **I** in (
36
34
  tensor(int64)
37
35
  ):
38
36
  Constrain index tensor to int64