Upsample - 9 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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- Upsample9 → Upsample10 +0 -0
Upsample9 → Upsample10
RENAMED
|
@@ -1 +1 @@
|
|
|
1
1
|
Upsample the input tensor.
|
|
2
2
|
Each dimension value of the output tensor is:
|
|
3
3
|
output_dimension = floor(input_dimension * scale).
|
|
4
4
|
**Attributes**
|
|
5
5
|
* **mode**:
|
|
6
6
|
Two interpolation modes: nearest (default), and linear (including
|
|
7
7
|
bilinear, trilinear, etc)
|
|
8
8
|
**Inputs**
|
|
9
9
|
* **X** (heterogeneous) - **T**:
|
|
10
10
|
N-D tensor
|
|
11
11
|
* **scales** (heterogeneous) - **tensor(float)**:
|
|
12
12
|
The scale array along each dimension. It takes value greater than or
|
|
13
13
|
equal to 1. The number of elements of 'scales' should be the same as
|
|
14
14
|
the rank of input 'X'.
|
|
15
15
|
**Outputs**
|
|
16
16
|
* **Y** (heterogeneous) - **T**:
|
|
17
17
|
N-D tensor after resizing
|
|
18
18
|
**Type Constraints**
|
|
19
19
|
* **T** in (
|
|
20
20
|
tensor(bool),
|
|
21
21
|
tensor(complex128),
|
|
22
22
|
tensor(complex64),
|
|
23
23
|
tensor(double),
|
|
24
24
|
tensor(float),
|
|
25
25
|
tensor(float16),
|
|
26
26
|
tensor(int16),
|
|
27
27
|
tensor(int32),
|
|
28
28
|
tensor(int64),
|
|
29
29
|
tensor(int8),
|
|
30
30
|
tensor(string),
|
|
31
31
|
tensor(uint16),
|
|
32
32
|
tensor(uint32),
|
|
33
33
|
tensor(uint64),
|
|
34
34
|
tensor(uint8)
|
|
35
35
|
):
|
|
36
36
|
Constrain input 'X' and output 'Y' to all tensor types.
|