Unsqueeze - 11 vs 13#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
Unsqueeze11 → Unsqueeze13
RENAMED
@@ -1 +1 @@
|
|
1
1
|
Insert single-dimensional entries to the shape of an input tensor (data).
|
2
|
-
Takes one required
|
2
|
+
Takes one required argument axes - which contains a list of dimension indices and this operator will insert a dimension of value 1 into the corresponding index of the output tensor (expanded).
|
3
3
|
For example:
|
4
4
|
Given an input tensor (data) of shape [3, 4, 5], then
|
5
5
|
Unsqueeze(data, axes=[0, 4]) outputs a tensor (expanded) containing same data as data but with shape [1, 3, 4, 5, 1].
|
6
|
-
The
|
6
|
+
The attribute axes should not contain any duplicate entries. It is an error if it contains duplicates.
|
7
7
|
The rank of the output tensor (output_rank) is the rank of the input tensor (data) plus the number of values in axes.
|
8
8
|
Each value in axes should be within the (inclusive) range [-output_rank , output_rank - 1].
|
9
9
|
The order of values in axes does not matter and can come in any order.
|
10
|
+
|
11
|
+
**Attributes**
|
12
|
+
|
13
|
+
* **axes** (required):
|
14
|
+
List of integers indicating the dimensions to be inserted. Negative
|
15
|
+
value means counting dimensions from the back. Accepted range is
|
16
|
+
[-r, r-1] where r = rank(expanded).
|
10
17
|
**Inputs**
|
11
18
|
* **data** (heterogeneous) - **T**:
|
12
19
|
Original tensor
|
13
|
-
* **axes** (heterogeneous) - **tensor(int64)**:
|
14
|
-
List of integers indicating the dimensions to be inserted. Negative
|
15
|
-
value means counting dimensions from the back. Accepted range is
|
16
|
-
[-r, r-1] where r = rank(expanded).
|
17
20
|
**Outputs**
|
18
21
|
* **expanded** (heterogeneous) - **T**:
|
19
22
|
Reshaped tensor with same data as input.
|
20
23
|
**Type Constraints**
|
21
24
|
* **T** in (
|
22
|
-
tensor(bfloat16),
|
23
25
|
tensor(bool),
|
24
26
|
tensor(complex128),
|
25
27
|
tensor(complex64),
|
26
28
|
tensor(double),
|
27
29
|
tensor(float),
|
28
30
|
tensor(float16),
|
29
31
|
tensor(int16),
|
30
32
|
tensor(int32),
|
31
33
|
tensor(int64),
|
32
34
|
tensor(int8),
|
33
35
|
tensor(string),
|
34
36
|
tensor(uint16),
|
35
37
|
tensor(uint32),
|
36
38
|
tensor(uint64),
|
37
39
|
tensor(uint8)
|
38
40
|
):
|
39
41
|
Constrain input and output types to all tensor types.
|