openvino.runtime.Tensor¶
-
class
openvino.runtime.
Tensor
¶ Bases:
pybind11_builtins.pybind11_object
openvino.runtime.Tensor holding either copy of memory or shared host memory.
-
__init__
(*args, **kwargs)¶ Overloaded function.
__init__(self: openvino.pyopenvino.Tensor, array: numpy.ndarray, shared_memory: bool = False) -> None
Tensor’s special constructor.
- param array
Array to create tensor from.
- type array
numpy.array
- param shared_memory
If True, this Tensor memory is being shared with a host, that means the responsibility of keeping host memory is on the side of a user. Any action performed on the host memory is reflected on this Tensor’s memory! If False, data is being copied to this Tensor. Requires data to be C_CONTIGUOUS if True.
- type shared_memory
bool
__init__(self: openvino.pyopenvino.Tensor, array: numpy.ndarray, shape: openvino.pyopenvino.Shape) -> None
Another Tensor’s special constructor.
It takes an array or slice of it, and shape that will be selected, starting from the first element of the given array/slice. Please use it only in advanced cases if necessary!
- param array
Underlaying methods will retrieve pointer on first element from it, which is simulating host_ptr from C++ API. Tensor memory is being shared with a host, that means the responsibility of keeping host memory is on the side of a user. Any action performed on the host memory will be reflected on this Tensor’s memory! Data is required to be C_CONTIGUOUS.
- type array
numpy.array
- param shape
Shape of the new tensor.
- type shape
openvino.runtime.Shape
- Example
import openvino.runtime as ov import numpy as np arr = np.array([[1, 2, 3], [4, 5, 6]]) t = ov.Tensor(arr[1][0:1], ov.Shape([3])) t.data[0] = 9 print(arr) >>> [[1 2 3] >>> [9 5 6]]
__init__(self: openvino.pyopenvino.Tensor, type: openvino.pyopenvino.Type, shape: openvino.pyopenvino.Shape) -> None
__init__(self: openvino.pyopenvino.Tensor, type: openvino.pyopenvino.Type, shape: List[int]) -> None
__init__(self: openvino.pyopenvino.Tensor, type: dtype, shape: List[int]) -> None
__init__(self: openvino.pyopenvino.Tensor, type: object, shape: List[int]) -> None
__init__(self: openvino.pyopenvino.Tensor, type: dtype, shape: openvino.pyopenvino.Shape) -> None
__init__(self: openvino.pyopenvino.Tensor, type: object, shape: openvino.pyopenvino.Shape) -> None
__init__(self: openvino.pyopenvino.Tensor, other: openvino.pyopenvino.Tensor, begin: openvino.pyopenvino.Coordinate, end: openvino.pyopenvino.Coordinate) -> None
__init__(self: openvino.pyopenvino.Tensor, other: openvino.pyopenvino.Tensor, begin: List[int], end: List[int]) -> None
Methods
__delattr__
(name, /)Implement delattr(self, name).
__dir__
()Default dir() implementation.
__eq__
(value, /)Return self==value.
__format__
(format_spec, /)Default object formatter.
__ge__
(value, /)Return self>=value.
__getattribute__
(name, /)Return getattr(self, name).
__gt__
(value, /)Return self>value.
__hash__
()Return hash(self).
__init__
(*args, **kwargs)Overloaded function.
This method is called when a class is subclassed.
__le__
(value, /)Return self<=value.
__lt__
(value, /)Return self<value.
__ne__
(value, /)Return self!=value.
__new__
(**kwargs)Create and return a new object.
Helper for pickle.
__reduce_ex__
(protocol, /)Helper for pickle.
__repr__
(self)__setattr__
(name, value, /)Implement setattr(self, name, value).
Size of object in memory, in bytes.
__str__
()Return str(self).
Abstract classes can override this to customize issubclass().
get_byte_size
(self)Gets Tensor’s size in bytes.
get_element_type
(self)Gets Tensor’s element type.
get_shape
(self)Gets Tensor’s shape.
get_size
(self)Gets Tensor’s size as total number of elements.
get_strides
(self)Gets Tensor’s strides in bytes.
set_shape
(*args, **kwargs)Overloaded function.
Attributes
Tensor’s size in bytes.
Access to Tensor’s data.
Tensor’s element type.
Tensor’s shape get/set.
Tensor’s size as total number of elements.
Tensor’s strides in bytes.
-
__class__
¶ alias of
pybind11_builtins.pybind11_type
-
__delattr__
(name, /)¶ Implement delattr(self, name).
-
__dir__
()¶ Default dir() implementation.
-
__eq__
(value, /)¶ Return self==value.
-
__format__
(format_spec, /)¶ Default object formatter.
-
__ge__
(value, /)¶ Return self>=value.
-
__getattribute__
(name, /)¶ Return getattr(self, name).
-
__gt__
(value, /)¶ Return self>value.
-
__hash__
()¶ Return hash(self).
-
__init__
(*args, **kwargs)¶ Overloaded function.
__init__(self: openvino.pyopenvino.Tensor, array: numpy.ndarray, shared_memory: bool = False) -> None
Tensor’s special constructor.
- param array
Array to create tensor from.
- type array
numpy.array
- param shared_memory
If True, this Tensor memory is being shared with a host, that means the responsibility of keeping host memory is on the side of a user. Any action performed on the host memory is reflected on this Tensor’s memory! If False, data is being copied to this Tensor. Requires data to be C_CONTIGUOUS if True.
- type shared_memory
bool
__init__(self: openvino.pyopenvino.Tensor, array: numpy.ndarray, shape: openvino.pyopenvino.Shape) -> None
Another Tensor’s special constructor.
It takes an array or slice of it, and shape that will be selected, starting from the first element of the given array/slice. Please use it only in advanced cases if necessary!
- param array
Underlaying methods will retrieve pointer on first element from it, which is simulating host_ptr from C++ API. Tensor memory is being shared with a host, that means the responsibility of keeping host memory is on the side of a user. Any action performed on the host memory will be reflected on this Tensor’s memory! Data is required to be C_CONTIGUOUS.
- type array
numpy.array
- param shape
Shape of the new tensor.
- type shape
openvino.runtime.Shape
- Example
import openvino.runtime as ov import numpy as np arr = np.array([[1, 2, 3], [4, 5, 6]]) t = ov.Tensor(arr[1][0:1], ov.Shape([3])) t.data[0] = 9 print(arr) >>> [[1 2 3] >>> [9 5 6]]
__init__(self: openvino.pyopenvino.Tensor, type: openvino.pyopenvino.Type, shape: openvino.pyopenvino.Shape) -> None
__init__(self: openvino.pyopenvino.Tensor, type: openvino.pyopenvino.Type, shape: List[int]) -> None
__init__(self: openvino.pyopenvino.Tensor, type: dtype, shape: List[int]) -> None
__init__(self: openvino.pyopenvino.Tensor, type: object, shape: List[int]) -> None
__init__(self: openvino.pyopenvino.Tensor, type: dtype, shape: openvino.pyopenvino.Shape) -> None
__init__(self: openvino.pyopenvino.Tensor, type: object, shape: openvino.pyopenvino.Shape) -> None
__init__(self: openvino.pyopenvino.Tensor, other: openvino.pyopenvino.Tensor, begin: openvino.pyopenvino.Coordinate, end: openvino.pyopenvino.Coordinate) -> None
__init__(self: openvino.pyopenvino.Tensor, other: openvino.pyopenvino.Tensor, begin: List[int], end: List[int]) -> None
-
__init_subclass__
()¶ This method is called when a class is subclassed.
The default implementation does nothing. It may be overridden to extend subclasses.
-
__le__
(value, /)¶ Return self<=value.
-
__lt__
(value, /)¶ Return self<value.
-
__ne__
(value, /)¶ Return self!=value.
-
__new__
(**kwargs)¶ Create and return a new object. See help(type) for accurate signature.
-
__reduce__
()¶ Helper for pickle.
-
__reduce_ex__
(protocol, /)¶ Helper for pickle.
-
__repr__
(self: openvino.pyopenvino.Tensor) → str¶
-
__setattr__
(name, value, /)¶ Implement setattr(self, name, value).
-
__sizeof__
()¶ Size of object in memory, in bytes.
-
__str__
()¶ Return str(self).
-
__subclasshook__
()¶ Abstract classes can override this to customize issubclass().
This is invoked early on by abc.ABCMeta.__subclasscheck__(). It should return True, False or NotImplemented. If it returns NotImplemented, the normal algorithm is used. Otherwise, it overrides the normal algorithm (and the outcome is cached).
-
property
byte_size
¶ Tensor’s size in bytes.
- Return type
int
-
property
data
¶ Access to Tensor’s data.
- Return type
numpy.array
-
property
element_type
¶ Tensor’s element type.
- Return type
-
get_byte_size
(self: openvino.pyopenvino.Tensor) → int¶ Gets Tensor’s size in bytes.
- Return type
int
-
get_element_type
(self: openvino.pyopenvino.Tensor) → openvino.pyopenvino.Type¶ Gets Tensor’s element type.
- Return type
-
get_shape
(self: openvino.pyopenvino.Tensor) → openvino.pyopenvino.Shape¶ Gets Tensor’s shape.
- Return type
-
get_size
(self: openvino.pyopenvino.Tensor) → int¶ Gets Tensor’s size as total number of elements.
- Return type
int
-
get_strides
(self: openvino.pyopenvino.Tensor) → openvino.pyopenvino.Strides¶ Gets Tensor’s strides in bytes.
- Return type
-
set_shape
(*args, **kwargs)¶ Overloaded function.
set_shape(self: openvino.pyopenvino.Tensor, arg0: openvino.pyopenvino.Shape) -> None
Sets Tensor’s shape.
set_shape(self: openvino.pyopenvino.Tensor, arg0: List[int]) -> None
Sets Tensor’s shape.
-
property
shape
¶ Tensor’s shape get/set.
-
property
size
¶ Tensor’s size as total number of elements.
- Return type
int
-
property
strides
¶ Tensor’s strides in bytes.
- Return type
-