Gradient op for `MirrorPad` op. This op folds a mirror-padded tensor.
This operation folds the padded areas of `input` by `MirrorPad` according to the `paddings` you specify. `paddings` must be the same as `paddings` argument given to the corresponding `MirrorPad` op.
The folded size of each dimension D of the output is:
`input.dim_size(D) - paddings(D, 0) - paddings(D, 1)`
For example:
# 't' is [[1, 2, 3], [4, 5, 6], [7, 8, 9]].
# 'paddings' is [[0, 1]], [0, 1]].
# 'mode' is SYMMETRIC.
# rank of 't' is 2.
pad(t, paddings) ==> [[ 1, 5]
[11, 28]]
Public Methods
Output <T> |
asOutput
()
Returns the symbolic handle of a tensor.
|
static <T, U extends Number> MirrorPadGrad <T> | |
Output <T> |
output
()
The folded tensor.
|
Inherited Methods
Public Methods
public Output <T> asOutput ()
Returns the symbolic handle of a tensor.
Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
public static MirrorPadGrad <T> create ( Scope scope, Operand <T> input, Operand <U> paddings, String mode)
Factory method to create a class wrapping a new MirrorPadGrad operation.
Parameters
scope | current scope |
---|---|
input | The input tensor to be folded. |
paddings | A two-column matrix specifying the padding sizes. The number of rows must be the same as the rank of `input`. |
mode | The mode used in the `MirrorPad` op. |
Returns
- a new instance of MirrorPadGrad