Return a strided slice from input
.
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
)
Note, most python users will want to use the Python Tensor.getitem
or Variable.getitem
rather than this op directly.
The goal of this op is to produce a new tensor with a subset of
the elements from the n
dimensional 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,foo[:, ...]
wherefoo
is shape(3, 4)
produces a(1, 3, 4)
tensor.A range
begin:end:stride
. This is used to specify how much to choose from a given dimension.stride
can be any integer but 0.begin
is an integer which represents the index of the first value to select whileend
represents the index of the last value to select. The number of values selected in each dimension isend - begin
ifstride > 0
andbegin - end
ifstride < 0
.begin
andend
can be negative where-1
is the last element,-2
is the second to last.begin_mask
controls whether to replace the explicitly givenbegin
with an implicit effective value of0
ifstride > 0
and-1
ifstride < 0
.end_mask
is analogous but produces the number required to create the largest open interval. For example, given a shape(3,)
tensorfoo[:]
, the effectivebegin
andend
are0
and3
. Do not assume this is equivalent tofoo[0:-1]
which has an effectivebegin
andend
of0
and2
. Another example isfoo[-2::-1]
which reverses the first dimension of a tensor while dropping the last two (in the original order elements). For examplefoo = [1,2,3,4]; foo[-2::-1]
is[4,3]
.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 inbegin
andend
andshrink_axis_mask
.
Each conceptual range specification is encoded in the op's argument. This
encoding is best understand by considering a non-trivial example. In
particular,
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 = 1
andend = begin + 1 = 2
. To disambiguate from the original spec2:4
we also set the appropriate bit inshrink_axis_mask
.2:4
is 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:-1
shows the use of negative indices. A negative indexi
associated with a dimension that has shapes
is converted to a positive indexs + i
. So-1
becomess-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::
or0::1
. begin, end, and strides receive 0, 0, and 1, respectively. The appropriate bits inbegin_mask
andend_mask
are also set.
Requirements:
0 != strides[i] for i in [0, m)
ellipsis_mask must be a power of two (only one ellipsis)
Args | |
---|---|
input
|
A Tensor .
|
begin
|
A Tensor . Must be one of the following types: int32 , int64 .
begin[k] specifies the offset into the k th range specification.
The exact dimension this corresponds to will be determined by context.
Out-of-bounds values will be silently clamped. If the k th bit of
begin_mask then begin[k] is ignored and the full range of the
appropriate dimension is used instead. Negative values causes indexing
to start from the highest element e.g. If foo==[1,2,3] then foo[-1]==3 .
|
end
|
A Tensor . Must have the same type as begin .
end[i] is like begin with the exception that end_mask is
used to determine full ranges.
|
strides
|
A Tensor . Must have the same type as begin .
strides[i] specifies the increment in the i th specification
after extracting a given element. Negative indices will reverse
the original order. Out or range values are
clamped to [0,dim[i]) if slice[i]>0 or [-1,dim[i]-1] if slice[i] < 0
|
begin_mask
|
An optional int . Defaults to 0 .
a bitmask where a bit i being 1 means to ignore the begin
value and instead use the largest interval possible. At runtime
begin[i] will be replaced with [0, n-1) if stride[i] > 0 or
[-1, n-1] if stride[i] < 0
|
end_mask
|
An optional int . Defaults to 0 . analogous to begin_mask
|
ellipsis_mask
|
An optional int . Defaults to 0 .
a bitmask where bit i being 1 means the i th
position is actually an ellipsis. One bit at most can be 1.
If ellipsis_mask == 0 , then an implicit ellipsis mask of 1 << (m+1)
is provided. This means that foo[3:5] == foo[3:5, ...] . An ellipsis
implicitly creates as many range specifications as necessary to fully
specify the sliced range for every dimension. For example for a 4-dimensional
tensor foo the slice foo[2, ..., 5:8] implies foo[2, :, :, 5:8] .
|
new_axis_mask
|
An optional int . Defaults to 0 .
a bitmask where bit i being 1 means the i th
specification creates a new shape 1 dimension. For example
foo[:4, tf.newaxis, :2] would produce a shape (4, 1, 2) tensor.
|
shrink_axis_mask
|
An optional int . Defaults to 0 .
a bitmask where bit i implies that the i th
specification should shrink the dimensionality. begin and end
must imply a slice of size 1 in the dimension. For example in
python one might do foo[:, 3, :] which would result in
shrink_axis_mask being 2.
|
name
|
A name for the operation (optional). |
Returns | |
---|---|
A Tensor . Has the same type as input .
|