Method MaxPool
MaxPool(TensorFloat, int[], int[], int[])
Calculates an output tensor by pooling the maximum values of the input tensor across its spatial dimensions according to the given pool and stride values.
Declaration
public TensorFloat MaxPool(TensorFloat X, int[] pool, int[] stride, int[] pad)Parameters
| Type | Name | Description |
|---|---|---|
| TensorFloat | X | The input tensor. |
| int[] | pool | The size of the kernel along each spatial axis. |
| int[] | stride | The stride along each spatial axis. |
| int[] | pad | The lower and upper padding values for each spatial dimension. For example, [pad_left, pad_right] for 1D, or [pad_top, pad_bottom, pad_left, pad_right] for 2D. |
Returns
| Type | Description |
|---|---|
| TensorFloat | The computed output tensor. |