Returns the gradient of `StridedSlice`.
Since `StridedSlice` cuts out pieces of its `input` which is size `shape`, its gradient will have the same shape (which is passed here as `shape`). The gradient will be zero in any element that the slice does not select.
Arguments are the same as StridedSliceGrad with the exception that `dy` is the input gradient to be propagated and `shape` is the shape of `StridedSlice`'s `input`.
Nested Classes
class | StridedSliceGrad.Options | Optional attributes for StridedSliceGrad
|
Public Methods
Output<U> |
asOutput()
Returns the symbolic handle of a tensor.
|
static StridedSliceGrad.Options |
beginMask(Long beginMask)
|
static <U, T extends Number> StridedSliceGrad<U> | |
static StridedSliceGrad.Options |
ellipsisMask(Long ellipsisMask)
|
static StridedSliceGrad.Options |
endMask(Long endMask)
|
static StridedSliceGrad.Options |
newAxisMask(Long newAxisMask)
|
Output<U> |
output()
|
static StridedSliceGrad.Options |
shrinkAxisMask(Long shrinkAxisMask)
|
Inherited Methods
Public Methods
public Output<U> 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 StridedSliceGrad<U> create (Scope scope, Operand<T> shape, Operand<T> begin, Operand<T> end, Operand<T> strides, Operand<U> dy, Options... options)
Factory method to create a class wrapping a new StridedSliceGrad operation.
Parameters
scope | current scope |
---|---|
options | carries optional attributes values |
Returns
- a new instance of StridedSliceGrad