LpPool - 2 vs 11¶
- LpPool2 → LpPool11 +8 -5
LpPool2 → LpPool11
RENAMED
@@ -1 +1 @@
|
|
1
1
|
LpPool consumes an input tensor X and applies Lp pooling across
|
2
2
|
the tensor according to kernel sizes, stride sizes, and pad lengths.
|
3
3
|
Lp pooling consisting of computing the Lp norm on all values of a subset
|
4
4
|
of the input tensor according to the kernel size and downsampling the
|
5
5
|
data into the output tensor Y for further processing.
|
6
6
|
**Attributes**
|
7
7
|
* **auto_pad**:
|
8
8
|
auto_pad must be either NOTSET, SAME_UPPER, SAME_LOWER or VALID.
|
9
9
|
Where default value is NOTSET, which means explicit padding is used.
|
10
|
-
SAME_UPPER or SAME_LOWER mean pad the input so that
|
10
|
+
SAME_UPPER or SAME_LOWER mean pad the input so that output_shape[i]
|
11
|
+
= ceil(input_shape[i] / strides[i]) for each axis i. The padding
|
12
|
+
is split between the two sides equally or almost equally (depending
|
11
|
-
|
13
|
+
on whether it is even or odd). In case the padding is an odd number,
|
12
|
-
padding at the end for SAME_UPPER and at the
|
14
|
+
the extra padding is added at the end for SAME_UPPER and at the
|
13
|
-
|
15
|
+
beginning for SAME_LOWER.
|
14
16
|
* **kernel_shape** (required):
|
15
17
|
The size of the kernel along each axis.
|
16
18
|
* **p**:
|
17
19
|
p value of the Lp norm used to pool over the input data.
|
18
20
|
* **pads**:
|
19
21
|
Padding for the beginning and ending along each spatial axis, it can
|
20
22
|
take any value greater than or equal to 0. The value represent the
|
21
23
|
number of pixels added to the beginning and end part of the
|
22
24
|
corresponding axis. pads format should be as follow [x1_begin,
|
23
25
|
x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels
|
24
26
|
added at the beginning of axis i and xi_end, the number of pixels
|
25
27
|
added at the end of axis i. This attribute cannot be used
|
26
28
|
simultaneously with auto_pad attribute. If not present, the padding
|
27
29
|
defaults to 0 along start and end of each spatial axis.
|
28
30
|
* **strides**:
|
31
|
+
Stride along each spatial axis. If not present, the stride defaults
|
29
|
-
|
32
|
+
to 1 along each spatial axis.
|
30
33
|
**Inputs**
|
31
34
|
* **X** (heterogeneous) - **T**:
|
32
35
|
Input data tensor from the previous operator; dimensions for image
|
33
36
|
case are (N x C x H x W), where N is the batch size, C is the number
|
34
37
|
of channels, and H and W are the height and the width of the data.
|
35
38
|
For non image case, the dimensions are in the form of (N x C x D1 x
|
36
39
|
D2 ... Dn), where N is the batch size.
|
37
40
|
**Outputs**
|
38
41
|
* **Y** (heterogeneous) - **T**:
|
39
42
|
Output data tensor from Lp pooling across the input tensor.
|
40
43
|
Dimensions will vary based on various kernel, stride, and pad sizes.
|
41
44
|
**Type Constraints**
|
42
45
|
* **T** in (
|
43
46
|
tensor(double),
|
44
47
|
tensor(float),
|
45
48
|
tensor(float16)
|
46
49
|
):
|
47
50
|
Constrain input and output types to float tensors.
|