GlobalMaxPool - 1 vs 22¶
Next section compares an older to a newer version of the same operator after both definition are converted into markdown text.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.
GlobalMaxPool1 → GlobalMaxPool22
RENAMED
@@ -1 +1 @@
|
|
1
1
|
GlobalMaxPool consumes an input tensor X and applies max pooling across
|
2
2
|
the values in the same channel. This is equivalent to MaxPool with kernel size
|
3
3
|
equal to the spatial dimension of input tensor.
|
4
4
|
### Inputs
|
5
5
|
- **X** (heterogeneous) - **T**:
|
6
6
|
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.
|
7
7
|
### Outputs
|
8
8
|
- **Y** (heterogeneous) - **T**:
|
9
9
|
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.
|
10
10
|
### Type Constraints
|
11
|
-
* **T** in ( tensor(double), tensor(float), tensor(float16) ):
|
11
|
+
* **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16) ):
|
12
12
|
Constrain input and output types to float tensors.
|