Upsample - 1 vs 7¶
- Upsample1 → Upsample7 +21 -30
Upsample1 → Upsample7
RENAMED
@@ -1 +1 @@
|
|
1
1
|
Upsample the input tensor.
|
2
|
+
Each dimension value of the output tensor is:
|
3
|
+
output_dimension = floor(input_dimension * scale).
|
2
|
-
The width and height of the output tensor are:
|
3
|
-
output_width = floor(input_width * width_scale),
|
4
|
-
output_height = floor(input_height * height_scale).
|
5
|
-
Example:
|
6
|
-
Given data tensor, width_scale, height_scale, mode,
|
7
|
-
Upsample the input 4-D tensor in nearest mode:
|
8
|
-
data = [[[
|
9
|
-
[1, 2],
|
10
|
-
[3, 4]
|
11
|
-
]]]
|
12
|
-
width_scale = 2
|
13
|
-
height_scale = 2
|
14
|
-
mode = "nearest"
|
15
|
-
output = [[[
|
16
|
-
[1, 1, 2, 2],
|
17
|
-
[1, 1, 2, 2],
|
18
|
-
[3, 3, 4, 4],
|
19
|
-
[3, 3, 4, 4]
|
20
|
-
]]]
|
21
4
|
**Attributes**
|
22
|
-
* **height_scale** (required):
|
23
|
-
The scale along height dimension. It takes value greater than or
|
24
|
-
equal to 1.
|
25
5
|
* **mode**:
|
26
|
-
Two interpolation modes: nearest(default),
|
6
|
+
Two interpolation modes: nearest (default), and linear (including
|
7
|
+
bilinear, trilinear, etc)
|
27
|
-
* **
|
8
|
+
* **scales** (required):
|
28
|
-
The scale along
|
9
|
+
The scale array along each dimension. It takes value greater than or
|
10
|
+
equal to 1. The number of elements of 'scales' should be the same as
|
29
|
-
|
11
|
+
the rank of input 'X'.
|
30
12
|
**Inputs**
|
31
13
|
* **X** (heterogeneous) - **T**:
|
32
|
-
|
14
|
+
N-D tensor
|
33
15
|
**Outputs**
|
34
16
|
* **Y** (heterogeneous) - **T**:
|
35
|
-
|
17
|
+
N-D tensor after resizing
|
36
18
|
**Type Constraints**
|
37
19
|
* **T** in (
|
38
20
|
tensor(bool),
|
21
|
+
tensor(complex128),
|
22
|
+
tensor(complex64),
|
39
23
|
tensor(double),
|
40
24
|
tensor(float),
|
41
25
|
tensor(float16),
|
26
|
+
tensor(int16),
|
42
27
|
tensor(int32),
|
43
|
-
tensor(int64)
|
28
|
+
tensor(int64),
|
29
|
+
tensor(int8),
|
30
|
+
tensor(string),
|
31
|
+
tensor(uint16),
|
32
|
+
tensor(uint32),
|
33
|
+
tensor(uint64),
|
34
|
+
tensor(uint8)
|
44
35
|
):
|
36
|
+
Constrain input and output types to all tensor types.- Constrain output types to bool, int32, int64, float16, float, double
|
45
|
-
tensors.
|