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Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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

Files changed (1) hide show
  1. GlobalLpPool1 → GlobalLpPool2 +6 -7
GlobalLpPool1 → GlobalLpPool2 RENAMED
@@ -1 +1 @@
1
- GlobalLpPool consumes an input tensor X and applies lp pool pooling across
1
+ GlobalLpPool consumes an input tensor X and applies lp pool pooling across the
2
2
  the values in the same channel. This is equivalent to LpPool with kernel size
3
3
  equal to the spatial dimension of input tensor.
4
4
  **Attributes**
5
5
  * **p**:
6
- p value of the Lp norm used to pool over the input data.
6
+ p value of the Lp norm used to pool over the input data, default is
7
+ 2.0.
7
8
  **Inputs**
8
9
  * **X** (heterogeneous) - **T**:
9
10
  Input data tensor from the previous operator; dimensions for image
10
11
  case are (N x C x H x W), where N is the batch size, C is the number
11
12
  of channels, and H and W are the height and the width of the data.
12
- For non image case, the dimensions are in the form of (N x C x D1 x
13
+ For non image case, the dimension are in the form of (N x C x D1 x
13
14
  D2 ... Dn), where N is the batch size.
14
15
  **Outputs**
15
16
  * **Y** (heterogeneous) - **T**:
16
- Output data tensor from pooling across the input tensor. The output
17
+ Output data tensor from pooling across the input tensor. Dimensions
18
+ will be N x C x 1 x 1
17
- tensor has the same rank as the input. The first two dimensions of
18
- output shape are the same as the input (N x C), while the other
19
- dimensions are all 1.
20
19
  **Type Constraints**
21
20
  * **T** in (
22
21
  tensor(double),
23
22
  tensor(float),
24
23
  tensor(float16)
25
24
  ):
26
25
  Constrain input and output types to float tensors.