LpPool - 1 vs 2#
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
- LpPool1 → LpPool2 +17 -15
LpPool1 → LpPool2
RENAMED
@@ -1 +1 @@
|
|
1
|
-
LpPool consumes an input tensor X and applies Lp pooling across
|
1
|
+
LpPool consumes an input tensor X and applies Lp pooling across the
|
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 the output
|
10
|
+
SAME_UPPER or SAME_LOWER mean pad the input so that the output size
|
11
|
-
|
11
|
+
match the input.In case of odd number add the extra padding at the
|
12
|
-
|
12
|
+
end for SAME_UPPER and at the beginning for SAME_LOWER. VALID mean
|
13
|
+
no padding. DEPRECATION NOTE: auto_pad is only intended to support
|
14
|
+
legacy uses, and for framework authors, one is explicitly encouraged
|
13
|
-
|
15
|
+
to use explicit padding specified in the pads attribute.
|
14
|
-
* **kernel_shape
|
16
|
+
* **kernel_shape**:
|
15
17
|
The size of the kernel along each axis.
|
16
18
|
* **p**:
|
17
|
-
p value of the Lp norm used to pool over the input data
|
19
|
+
p value of the Lp norm used to pool over the input data, default is
|
20
|
+
2.0.
|
18
21
|
* **pads**:
|
19
|
-
Padding for the beginning and ending along each
|
22
|
+
Padding for the beginning and ending along each axis, it can take
|
20
|
-
|
23
|
+
any value greater than or equal to 0. The value represent the number
|
21
|
-
|
24
|
+
of pixels added to the beginning and end part of the corresponding
|
22
|
-
|
25
|
+
axis. pads format should be as follow [x1_begin,
|
23
26
|
x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels
|
24
27
|
added at the beginning of axis i and xi_end, the number of pixels
|
25
28
|
added at the end of axis i. This attribute cannot be used
|
26
|
-
simultaneously with auto_pad attribute.
|
29
|
+
simultaneously with auto_pad attribute.
|
27
|
-
defaults to 0 along start and end of each spatial axis.
|
28
30
|
* **strides**:
|
29
|
-
Stride along each
|
31
|
+
Stride along each axis.
|
30
32
|
**Inputs**
|
31
33
|
* **X** (heterogeneous) - **T**:
|
32
34
|
Input data tensor from the previous operator; dimensions for image
|
33
35
|
case are (N x C x H x W), where N is the batch size, C is the number
|
34
36
|
of channels, and H and W are the height and the width of the data.
|
35
|
-
For non image case, the
|
37
|
+
For non image case, the dimension are in the form of (N x C x D1 x
|
36
38
|
D2 ... Dn), where N is the batch size.
|
37
39
|
**Outputs**
|
38
40
|
* **Y** (heterogeneous) - **T**:
|
39
41
|
Output data tensor from Lp pooling across the input tensor.
|
40
42
|
Dimensions will vary based on various kernel, stride, and pad sizes.
|
41
43
|
**Type Constraints**
|
42
44
|
* **T** in (
|
43
45
|
tensor(double),
|
44
46
|
tensor(float),
|
45
47
|
tensor(float16)
|
46
48
|
):
|
47
49
|
Constrain input and output types to float tensors.
|