Method ConvTranspose
ConvTranspose(TensorFloat, TensorFloat, TensorFloat, int[], int[], int[])
Applies a transpose convolution filter to an input tensor.
Declaration
public TensorFloat ConvTranspose(TensorFloat X, TensorFloat K, TensorFloat B, int[] stride, int[] pad, int[] outputAdjustment)Parameters
| Type | Name | Description |
|---|---|---|
| TensorFloat | X | The input tensor. |
| TensorFloat | K | The filter tensor. |
| TensorFloat | B | The optional bias tensor. |
| int[] | stride | The optional stride value for each spatial dimension of the filter. |
| int[] | pad | The optional lower and upper padding values for each spatial dimension of the filter. |
| int[] | outputAdjustment | The output padding value for each spatial dimension in the filter. |
Returns
| Type | Description |
|---|---|
| TensorFloat | The computed output tensor. |