Return a strided slice from
Compat aliases for migration
See Migration guide for more details.
tf.raw_ops.StridedSlice( input, begin, end, strides, begin_mask=0, end_mask=0, ellipsis_mask=0, new_axis_mask=0, shrink_axis_mask=0, name=None )
The goal of this op is to produce a new tensor with a subset of
the elements from the
input tensor. The subset is chosen using
a sequence of
m sparse range specifications encoded into the arguments
of this function. Note, in some cases
m could be equal to
n, but this need not be the case. Each
range specification entry can be one of the following:
An ellipsis (...). Ellipses are used to imply zero or more dimensions of full-dimension selection and are produced using
ellipsis_mask. For example,
foo[...]is the identity slice.
A new axis. This is used to insert a new shape=1 dimension and is produced using
new_axis_mask. For example,
(3, 4)produces a
(1, 3, 4)tensor.
begin:end:stride. This is used to specify how much to choose from a given dimension.
stridecan be any integer but 0.
beginis an integer which represents the index of the first value to select while
endrepresents the index of the last value to select. The number of values selected in each dimension is
end - beginif
stride > 0and
begin - endif
stride < 0.
endcan be negative where
-1is the last element,
-2is the second to last.
begin_maskcontrols whether to replace the explicitly given
beginwith an implicit effective value of
stride > 0and
stride < 0.
end_maskis analogous but produces the number required to create the largest open interval. For example, given a shape
foo[:], the effective
3. Do not assume this is equivalent to
foo[0:-1]which has an effective
2. Another example is
foo[-2::-1]which reverses the first dimension of a tensor while dropping the last two (in the original order elements). For example
foo = [1,2,3,4]; foo[-2::-1]is
A single index. This is used to keep only elements that have a given index. For example (
foo[2, :]on a shape
(5,6)tensor produces a shape
(6,)tensor. This is encoded in
Each conceptual range specification is encoded in the op's argument. This
encoding is best understand by considering a non-trivial example. In
foo[1, 2:4, None, ..., :-3:-1, :] will be encoded as
begin = [1, 2, x, x, 0, x] # x denotes don't care (usually 0) end = [2, 4, x, x, -3, x] strides = [1, 1, x, x, -1, 1] begin_mask = 1<<4 | 1<<5 = 48 end_mask = 1<<5 = 32 ellipsis_mask = 1<<3 = 8 new_axis_mask = 1<<2 = 4 shrink_axis_mask = 1<<0 = 1
In this case if
foo.shape is (5, 5, 5, 5, 5, 5) the final shape of
the slice becomes (2, 1, 5, 5, 2, 5).
Let us walk step by step through each argument specification.
The first argument in the example slice is turned into
begin = 1and
end = begin + 1 = 2. To disambiguate from the original spec
2:4we also set the appropriate bit in
2:4is contributes 2, 4, 1 to begin, end, and stride. All masks have zero bits contributed.
None is a synonym for
tf.newaxis. This means insert a dimension of size 1 dimension in the final shape. Dummy values are contributed to begin, end and stride, while the new_axis_mask bit is set.
...grab the full ranges from as many dimensions as needed to fully specify a slice for every dimension of the input shape.
:-3:-1shows the use of negative indices. A negative index
iassociated with a dimension that has shape
sis converted to a positive index
s + i. So
s-1(i.e. the last element). This conversion is done internally so begin, end and strides receive x, -3, and -1. The appropriate begin_mask bit is set to indicate the start range is the full range (ignoring the x).
:indicates that the entire contents of the corresponding dimension is selected. This is equivalent to
0::1. begin, end, and strides receive 0, 0, and 1, respectively. The appropriate bits in
end_maskare also set.
0 != strides[i] for i in [0, m)
ellipsis_mask must be a power of two (only one ellipsis)