tf.raw_ops.StridedSliceGrad

Returns the gradient of StridedSlice.

tf.raw_ops.StridedSliceGrad(
    shape,
    begin,
    end,
    strides,
    dy,
    begin_mask=0,
    end_mask=0,
    ellipsis_mask=0,
    new_axis_mask=0,
    shrink_axis_mask=0,
    name=None
)

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.

shapeA Tensor. Must be one of the following types: int32, int64.
beginA Tensor. Must have the same type as shape.
endA Tensor. Must have the same type as shape.
stridesA Tensor. Must have the same type as shape.
dyA Tensor.
begin_maskAn optional int. Defaults to 0.
end_maskAn optional int. Defaults to 0.
ellipsis_maskAn optional int. Defaults to 0.
new_axis_maskAn optional int. Defaults to 0.
shrink_axis_maskAn optional int. Defaults to 0.
nameA name for the operation (optional).

A Tensor. Has the same type as dy.