Slice - 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Slice10 → Slice11 +5 -9
Slice10 → Slice11
RENAMED
@@ -1 +1 @@
|
|
1
1
|
Produces a slice of the input tensor along multiple axes. Similar to numpy:
|
2
2
|
https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
|
3
3
|
Slices uses starts, ends, axes and steps inputs to specify the start and end
|
4
4
|
dimension and step for each axis in the list of axes, it uses this information to
|
5
5
|
slice the input data tensor. If a negative value is passed for any of the
|
6
|
-
start or end indices, it
|
6
|
+
start or end indices, it represent number of elements before the end of that
|
7
7
|
dimension. If the value passed to start or end is larger than the n (the
|
8
8
|
number of elements in this dimension), it represents n. For slicing to the
|
9
|
-
end of a dimension with unknown size, it is recommended to pass in INT_MAX
|
9
|
+
end of a dimension with unknown size, it is recommended to pass in INT_MAX.
|
10
|
-
when slicing forward and 'INT_MIN' when slicing backward.
|
11
10
|
If a negative value is passed for step, it represents slicing backward.
|
12
|
-
However step value cannot be 0.
|
13
11
|
If axes are omitted, they are set to [0, ..., ndim-1].
|
14
12
|
If steps are omitted, they are set to [1, ..., 1] of length len(starts)
|
15
13
|
Example 1:
|
16
14
|
data = [
|
17
15
|
[1, 2, 3, 4],
|
18
16
|
[5, 6, 7, 8],
|
19
17
|
]
|
20
18
|
axes = [0, 1]
|
21
19
|
starts = [1, 0]
|
22
20
|
ends = [2, 3]
|
23
21
|
steps = [1, 2]
|
24
22
|
result = [
|
25
23
|
[5, 7],
|
26
24
|
]
|
27
25
|
Example 2:
|
28
26
|
data = [
|
29
27
|
[1, 2, 3, 4],
|
30
28
|
[5, 6, 7, 8],
|
31
29
|
]
|
32
30
|
starts = [0, 1]
|
33
31
|
ends = [-1, 1000]
|
34
32
|
result = [
|
35
33
|
[2, 3, 4],
|
36
34
|
]
|
37
35
|
**Inputs**
|
38
36
|
Between 3 and 5 inputs.
|
39
37
|
* **data** (heterogeneous) - **T**:
|
40
38
|
Tensor of data to extract slices from.
|
41
39
|
* **starts** (heterogeneous) - **Tind**:
|
42
40
|
1-D tensor of starting indices of corresponding axis in axes
|
43
41
|
* **ends** (heterogeneous) - **Tind**:
|
44
42
|
1-D tensor of ending indices (exclusive) of corresponding axis in
|
45
43
|
axes
|
46
44
|
* **axes** (optional, heterogeneous) - **Tind**:
|
47
|
-
1-D tensor of axes that starts and ends apply to.
|
45
|
+
1-D tensor of axes that starts and ends apply to.
|
48
|
-
means counting dimensions from the back. Accepted range is [-r, r-1]
|
49
|
-
where r = rank(data).
|
50
46
|
* **steps** (optional, heterogeneous) - **Tind**:
|
51
|
-
1-D tensor of slice step of corresponding axis in axes.
|
47
|
+
1-D tensor of slice step of corresponding axis in axes. Default to
|
52
|
-
|
48
|
+
1.
|
53
49
|
**Outputs**
|
54
50
|
* **output** (heterogeneous) - **T**:
|
55
51
|
Sliced data tensor.
|
56
52
|
**Type Constraints**
|
57
53
|
* **T** in (
|
58
54
|
tensor(bool),
|
59
55
|
tensor(complex128),
|
60
56
|
tensor(complex64),
|
61
57
|
tensor(double),
|
62
58
|
tensor(float),
|
63
59
|
tensor(float16),
|
64
60
|
tensor(int16),
|
65
61
|
tensor(int32),
|
66
62
|
tensor(int64),
|
67
63
|
tensor(int8),
|
68
64
|
tensor(string),
|
69
65
|
tensor(uint16),
|
70
66
|
tensor(uint32),
|
71
67
|
tensor(uint64),
|
72
68
|
tensor(uint8)
|
73
69
|
):
|
74
70
|
Constrain input and output types to all tensor types.
|
75
71
|
* **Tind** in (
|
76
72
|
tensor(int32),
|
77
73
|
tensor(int64)
|
78
74
|
):
|
79
75
|
Constrain indices to integer types
|