GlobalLpPool#
GlobalLpPool - 2#
Version
name: GlobalLpPool (GitHub)
domain: main
since_version: 2
function: False
support_level: SupportType.COMMON
shape inference: True
This version of the operator has been available since version 2.
Summary
GlobalLpPool consumes an input tensor X and applies lp pool pooling across the values in the same channel. This is equivalent to LpPool with kernel size equal to the spatial dimension of input tensor.
Attributes
p: p value of the Lp norm used to pool over the input data. Default value is
2.
Inputs
X (heterogeneous) - T: Input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data. For non image case, the dimensions are in the form of (N x C x D1 x D2 … Dn), where N is the batch size.
Outputs
Y (heterogeneous) - T: Output data tensor from pooling across the input tensor. The output tensor has the same rank as the input. The first two dimensions of output shape are the same as the input (N x C), while the other dimensions are all 1.
Type Constraints
T in ( tensor(double), tensor(float), tensor(float16) ): Constrain input and output types to float tensors.
Examples
Differences
0 | 0 | GlobalLpPool consumes an input tensor X and applies lp pool pooling across the | |
1 | 1 | the values in the same channel. This is equivalent to LpPool with kernel size | the values in the same channel. This is equivalent to LpPool with kernel size |
2 | 2 | equal to the spatial dimension of input tensor. | equal to the spatial dimension of input tensor. |
3 | 3 | | |
4 | 4 | **Attributes** | **Attributes** |
5 | 5 | | |
6 | 6 | * **p**: | * **p**: |
7 | 7 | p value of the Lp norm used to pool over the input data, default is | |
8 | 2.0. Default value is 2.0. | ||
9 | 8 | | |
10 | 9 | **Inputs** | **Inputs** |
11 | 10 | | |
12 | 11 | * **X** (heterogeneous) - **T**: | * **X** (heterogeneous) - **T**: |
13 | 12 | Input data tensor from the previous operator; dimensions for image | Input data tensor from the previous operator; dimensions for image |
14 | 13 | case are (N x C x H x W), where N is the batch size, C is the number | case are (N x C x H x W), where N is the batch size, C is the number |
15 | 14 | of channels, and H and W are the height and the width of the data. | of channels, and H and W are the height and the width of the data. |
16 | 15 | For non image case, the dimension are in the form of (N x C x D1 x | |
17 | 16 | D2 ... Dn), where N is the batch size. | D2 ... Dn), where N is the batch size. |
18 | 17 | | |
19 | 18 | **Outputs** | **Outputs** |
20 | 19 | | |
21 | 20 | * **Y** (heterogeneous) - **T**: | * **Y** (heterogeneous) - **T**: |
22 | 21 | Output data tensor from pooling across the input tensor. Dimensions | |
23 | 22 | will be N x C x 1 x 1 | |
23 | output shape are the same as the input (N x C), while the other | ||
24 | dimensions are all 1. | ||
24 | 25 | | |
25 | 26 | **Type Constraints** | **Type Constraints** |
26 | 27 | | |
27 | 28 | * **T** in ( | * **T** in ( |
28 | 29 | tensor(double), | tensor(double), |
29 | 30 | tensor(float), | tensor(float), |
30 | 31 | tensor(float16) | tensor(float16) |
31 | 32 | ): | ): |
32 | 33 | Constrain input and output types to float tensors. | Constrain input and output types to float tensors. |
GlobalLpPool - 1#
Version
name: GlobalLpPool (GitHub)
domain: main
since_version: 1
function: False
support_level: SupportType.COMMON
shape inference: False
This version of the operator has been available since version 1.
Summary
GlobalLpPool consumes an input tensor X and applies lp pool pooling across the the values in the same channel. This is equivalent to LpPool with kernel size equal to the spatial dimension of input tensor.
Attributes
p: p value of the Lp norm used to pool over the input data, default is 2.0. Default value is
2.0.
Inputs
X (heterogeneous) - T: Input data tensor from the previous operator; dimensions for image case are (N x C x H x W), where N is the batch size, C is the number of channels, and H and W are the height and the width of the data. For non image case, the dimension are in the form of (N x C x D1 x D2 … Dn), where N is the batch size.
Outputs
Y (heterogeneous) - T: Output data tensor from pooling across the input tensor. Dimensions will be N x C x 1 x 1
Type Constraints
T in ( tensor(double), tensor(float), tensor(float16) ): Constrain input and output types to float tensors.