LpPool - 1 vs 11#

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.

Files changed (1) hide show
  1. LpPool1 → LpPool11 +17 -18
LpPool1 → LpPool11 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 output_shape[i]
10
+ SAME_UPPER or SAME_LOWER mean pad the input so that the output size
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
13
- on whether it is even or odd). In case the padding is an odd number,
11
+ match the input.In case of odd number add the extra padding at the
14
- the extra padding is added at the end for SAME_UPPER and at the
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
15
- beginning for SAME_LOWER.
15
+ to use explicit padding specified in the pads attribute.
16
- * **kernel_shape** (required):
16
+ * **kernel_shape**:
17
17
  The size of the kernel along each axis.
18
18
  * **p**:
19
- 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.
20
21
  * **pads**:
21
- Padding for the beginning and ending along each spatial axis, it can
22
+ Padding for the beginning and ending along each axis, it can take
22
- take any value greater than or equal to 0. The value represent the
23
+ any value greater than or equal to 0. The value represent the number
23
- number of pixels added to the beginning and end part of the
24
+ of pixels added to the beginning and end part of the corresponding
24
- corresponding axis. pads format should be as follow [x1_begin,
25
+ axis. pads format should be as follow [x1_begin,
25
26
  x2_begin...x1_end, x2_end,...], where xi_begin the number of pixels
26
27
  added at the beginning of axis i and xi_end, the number of pixels
27
28
  added at the end of axis i. This attribute cannot be used
28
- simultaneously with auto_pad attribute. If not present, the padding
29
+ simultaneously with auto_pad attribute.
29
- defaults to 0 along start and end of each spatial axis.
30
30
  * **strides**:
31
+ Stride along each axis.
31
- Stride along each spatial axis. If not present, the stride defaults
32
- to 1 along each spatial axis.
33
32
  **Inputs**
34
33
  * **X** (heterogeneous) - **T**:
35
34
  Input data tensor from the previous operator; dimensions for image
36
35
  case are (N x C x H x W), where N is the batch size, C is the number
37
36
  of channels, and H and W are the height and the width of the data.
38
- For non image case, the dimensions are in the form of (N x C x D1 x
37
+ For non image case, the dimension are in the form of (N x C x D1 x
39
38
  D2 ... Dn), where N is the batch size.
40
39
  **Outputs**
41
40
  * **Y** (heterogeneous) - **T**:
42
41
  Output data tensor from Lp pooling across the input tensor.
43
42
  Dimensions will vary based on various kernel, stride, and pad sizes.
44
43
  **Type Constraints**
45
44
  * **T** in (
46
45
  tensor(double),
47
46
  tensor(float),
48
47
  tensor(float16)
49
48
  ):
50
49
  Constrain input and output types to float tensors.