open3d.core.Tensor¶

class open3d.core.Tensor¶

A Tensor is a view of a data Blob with shape, stride, data_ptr.

T(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Transpose <=2-D tensor by swapping dimension 0 and 1.0-D and 1-D Tensor remains the same.

__init__(*args, **kwargs)¶

Overloaded function.

__init__(self, np_array, dtype=None, device=None)
Initialize Tensor from a Numpy array.

Parameters

np_array (numpy.ndarray) –
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

__init__(self, scalar_value, dtype=None, device=None)

Parameters

scalar_value (bool) – Initial value for the single element tensor.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

__init__(self, scalar_value, dtype=None, device=None)

Parameters

scalar_value (int) – Initial value for the single element tensor.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

__init__(self, scalar_value, dtype=None, device=None)

Parameters

scalar_value (float) – Initial value for the single element tensor.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

__init__(self, shape, dtype=None, device=None)
Initialize Tensor from a nested list.

Parameters

shape (list) – List of Tensor dimensions.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

__init__(self, shape, dtype=None, device=None)
Initialize Tensor from a nested tuple.

Parameters

shape (tuple) – List of Tensor dimensions.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

abs(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

abs_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

add(*args, **kwargs)¶

Overloaded function.

add(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

add_(*args, **kwargs)¶

Overloaded function.

add_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
add_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

all(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶: Returns true if all elements in the tensor are true. Only works for boolean tensors.

allclose(self, other, rtol=1e-05, atol=1e-08)¶

Returns true if the two tensors are element-wise equal within a tolerance.

If the device is not the same: throws exception.
If the dtype is not the same: throws exception.
If the shape is not the same: returns false.
Returns true if: abs(self - other) <= (atol + rtol * abs(other)).

The equation is not symmetrical, i.e. a.allclose(b) might not be the same as b.allclose(a). Also see Numpy’s documentation.

Todo

Support nan.

Parameters

other (open3d.core.Tensor) – The other tensor to compare with.
rtol (float, optional, default=1e-05) – Relative tolerance.
atol (float, optional, default=1e-08) – Absolute tolerance.

Returns

bool

any(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶: Returns true if any elements in the tensor are true. Only works for boolean tensors.

append(self: open3d.cpu.pybind.core.Tensor, values: open3d.cpu.pybind.core.Tensor, axis: Optional[int] = None) → open3d.cpu.pybind.core.Tensor¶

Appends the values tensor, along the given axis and returns a copy of the original tensor. Both the tensors must have same data-type device, and number of dimensions. All dimensions must be the same, except the dimension along the axis the tensors are to be appended.

This is the similar to NumPy’s semantics: - https://numpy.org/doc/stable/reference/generated/numpy.append.html

Returns: A copy of the tensor with values appended to axis. Note that append does not occur in-place: a new array is allocated and filled. If axis is None, out is a flattened tensor.

Example

>>> a = o3d.core.Tensor([[0, 1], [2, 3]])
>>> b = o3d.core.Tensor([[4, 5]])
>>> a.append(b, axis = 0)
[[0 1],
 [2 3],
 [4 5]]
Tensor[shape={3, 2}, stride={2, 1}, Int64, CPU:0, 0x55555abc6b00]

>>> a.append(b)
[0 1 2 3 4 5]
Tensor[shape={6}, stride={1}, Int64, CPU:0, 0x55555abc6b70]

static arange(*args, **kwargs)¶

Overloaded function.

arange(stop: int, dtype: Optional[open3d.cpu.pybind.core.Dtype] = None, device: Optional[open3d.cpu.pybind.core.Device] = None) -> open3d.cpu.pybind.core.Tensor

Create a 1D tensor with evenly spaced values in the given interval.

arange(start: Optional[int] = None, stop: int, step: Optional[int] = None, dtype: Optional[open3d.cpu.pybind.core.Dtype] = None, device: Optional[open3d.cpu.pybind.core.Device] = None) -> open3d.cpu.pybind.core.Tensor

Create a 1D tensor with evenly spaced values in the given interval.

arange(stop: float, dtype: Optional[open3d.cpu.pybind.core.Dtype] = None, device: Optional[open3d.cpu.pybind.core.Device] = None) -> open3d.cpu.pybind.core.Tensor

Create a 1D tensor with evenly spaced values in the given interval.

arange(start: Optional[float] = None, stop: float, step: Optional[float] = None, dtype: Optional[open3d.cpu.pybind.core.Dtype] = None, device: Optional[open3d.cpu.pybind.core.Device] = None) -> open3d.cpu.pybind.core.Tensor

Create a 1D tensor with evenly spaced values in the given interval.

argmax(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None) → open3d.cpu.pybind.core.Tensor¶

argmin(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None) → open3d.cpu.pybind.core.Tensor¶

ceil(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

clip(*args, **kwargs)¶

Overloaded function.

clip(self: open3d.cpu.pybind.core.Tensor, arg0: float, arg1: float) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: float, arg1: float) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip(self: open3d.cpu.pybind.core.Tensor, arg0: bool, arg1: bool) -> open3d.cpu.pybind.core.Tensor

clip_(*args, **kwargs)¶

Overloaded function.

clip_(self: open3d.cpu.pybind.core.Tensor, arg0: float, arg1: float) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: float, arg1: float) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: int, arg1: int) -> open3d.cpu.pybind.core.Tensor
clip_(self: open3d.cpu.pybind.core.Tensor, arg0: bool, arg1: bool) -> open3d.cpu.pybind.core.Tensor

clone(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Copy Tensor to the same device.

contiguous(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Returns a contiguous tensor containing the same data in the same device. If the tensor is already contiguous, the same underlying memory will be used.

cos(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

cos_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

cpu(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Transfer the tensor to CPU. If the tensor is already on CPU, no copy will be performed.

cuda(self: open3d.cpu.pybind.core.Tensor, device_id: int = 0) → open3d.cpu.pybind.core.Tensor¶: Transfer the tensor to a CUDA device. If the tensor is already on the specified CUDA device, no copy will be performed.

det(self: open3d.cpu.pybind.core.Tensor) → float¶: Compute the determinant of a 2D square tensor.

static diag(arg0: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

div(*args, **kwargs)¶

Overloaded function.

div(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

div_(*args, **kwargs)¶

Overloaded function.

div_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
div_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

static empty(shape, dtype=None, device=None)¶

Create Tensor with a given shape.

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

eq(*args, **kwargs)¶

Overloaded function.

eq(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

eq_(*args, **kwargs)¶

Overloaded function.

eq_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
eq_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

exp(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

exp_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

static eye(n: int, dtype: Optional[open3d.cpu.pybind.core.Dtype] = None, device: Optional[open3d.cpu.pybind.core.Device] = None) → open3d.cpu.pybind.core.Tensor¶: Create an identity matrix of size n x n.

flatten(self, start_dim=0, end_dim=- 1)¶

Flattens input by reshaping it into a one-dimensional tensor. If start_dim or end_dim are passed, only dimensions starting with start_dim and ending with end_dim are flattened. The order of elements in input is unchanged.

Unlike NumPy’s flatten, which always copies input’s data, this function may return the original object, a view, or copy. If no dimensions are flattened, then the original object input is returned. Otherwise, if input can be viewed as the flattened shape, then that view is returned. Finally, only if the input cannot be viewed as the flattened shape is input’s data copied.

Ref: - https://pytorch.org/docs/stable/tensors.html - aten/src/ATen/native/TensorShape.cpp - aten/src/ATen/TensorUtils.cpp

Parameters

start_dim (int, optional, default=0) – The first dimension to flatten (inclusive).
end_dim (int, optional, default=-1) – The last dimension to flatten, starting from start_dim (inclusive).

Returns

open3d.core.Tensor

floor(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

static from_dlpack(arg0: capsule) → open3d.cpu.pybind.core.Tensor¶

static from_numpy(arg0: numpy.ndarray) → open3d.cpu.pybind.core.Tensor¶

static full(*args, **kwargs)¶

Overloaded function.

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (float) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (float) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (int) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

full(shape, fill_value, dtype=None, device=None)

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
fill_value (bool) – Scalar value to initialize all elements with.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

ge(*args, **kwargs)¶

Overloaded function.

ge(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

ge_(*args, **kwargs)¶

Overloaded function.

ge_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ge_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

gt(*args, **kwargs)¶

Overloaded function.

gt(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

gt_(*args, **kwargs)¶

Overloaded function.

gt_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
gt_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

inv(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Computes the matrix inverse of the square matrix self with LU factorization and returns the result.

is_contiguous(self: open3d.cpu.pybind.core.Tensor) → bool¶: Returns True if the underlying memory buffer is contiguous.

isclose(self, other, rtol=1e-05, atol=1e-08)¶

Element-wise version of tensor.allclose.

If the device is not the same: throws exception.
If the dtype is not the same: throws exception.
If the shape is not the same: throws exception.
For each element in the returned tensor: abs(self - other) <= (atol + rtol * abs(other)).

The equation is not symmetrical, i.e. a.is_close(b) might not be the same as b.is_close(a). Also see Numpy’s documentation.

Todo

Support nan.

Returns

A boolean tensor indicating where the tensor is close.

Parameters

other (open3d.core.Tensor) – The other tensor to compare with.
rtol (float, optional, default=1e-05) – Relative tolerance.
atol (float, optional, default=1e-08) – Absolute tolerance.

Returns

open3d.core.Tensor

isfinite(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

isinf(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

isnan(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

issame(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) → bool¶: Returns true iff the tensor is the other tensor. This means that, the two tensors have the same underlying memory, device, dtype, shape, strides and etc.

item(self: open3d.cpu.pybind.core.Tensor) → object¶: Helper function to return the scalar value of a scalar tensor. The tensor must be 0 - dimensional (i.e. have an empty shape).

le(*args, **kwargs)¶

Overloaded function.

le(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

le_(*args, **kwargs)¶

Overloaded function.

le_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
le_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

static load(file_name: str) → open3d.cpu.pybind.core.Tensor¶: Load tensor from Numpy’s npy format.

logical_and(*args, **kwargs)¶

Overloaded function.

logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

logical_and_(*args, **kwargs)¶

Overloaded function.

logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

logical_not(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

logical_not_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

logical_or(*args, **kwargs)¶

Overloaded function.

logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

logical_or_(*args, **kwargs)¶

Overloaded function.

logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

logical_xor(*args, **kwargs)¶

Overloaded function.

logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

logical_xor_(*args, **kwargs)¶

Overloaded function.

logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

lstsq(self: open3d.cpu.pybind.core.Tensor, B: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Solves the linear system AX = B with QR decomposition and returns X. A is a (m, n) matrix with m >= n.

lt(*args, **kwargs)¶

Overloaded function.

lt(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

lt_(*args, **kwargs)¶

Overloaded function.

lt_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
lt_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

lu(self, permute_l=False)¶

Computes LU factorisation of the 2D square tensor, using A = P * L * U; where P is the permutation matrix, L is the lower-triangular matrix with diagonal elements as 1.0 and U is the upper-triangular matrix, and returns tuple (P, L, U).

Returns: Tuple (P, L, U).
Parameters: permute_l (bool, optional, default=False) – If True, returns L as P * L.
Returns: Tuple[open3d.core.Tensor, open3d.core.Tensor, open3d.core.Tensor]

lu_ipiv(self: open3d.cpu.pybind.core.Tensor) → Tuple[open3d.cpu.pybind.core.Tensor, open3d.cpu.pybind.core.Tensor]¶

Computes LU factorisation of the 2D square tensor, using A = P * L * U; where P is the permutation matrix, L is the lower-triangular matrix with diagonal elements as 1.0 and U is the upper-triangular matrix, and returns tuple output tensor of shape {n,n} and ipiv tensor of shape {n}, where {n,n} is the shape of input tensor.

Returns

ipiv is a 1D integer pivot indices tensor. It contains the pivot: indices, indicating row i of the matrix was interchanged with row ipiv[i]
output: It has L as lower triangular values and U as upper triangle: values including the main diagonal (diagonal elements of L to be taken as unity).

Return type

ipiv

Example

>>> ipiv, output = a.lu_ipiv()

matmul(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Computes matrix multiplication of a 2D tensor with another tensor of compatible shape.

max(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶

mean(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶

min(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶

mul(*args, **kwargs)¶

Overloaded function.

mul(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

mul_(*args, **kwargs)¶

Overloaded function.

mul_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
mul_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

ne(*args, **kwargs)¶

Overloaded function.

ne(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

ne_(*args, **kwargs)¶

Overloaded function.

ne_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
ne_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

neg(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

neg_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

nonzero(self, as_tuple=False)¶

Find the indices of the elements that are non-zero.

Parameters: as_tuple (bool, optional, default=False) – If as_tuple is True, returns an int64 tensor of shape {num_dims, num_non_zeros}, where the i-th row contains the indices of the non-zero elements in i-th dimension of the original tensor. If as_tuple is False, Returns a vector of int64 Tensors, each containing the indices of the non-zero elements in each dimension.
Returns: object

num_elements(self: open3d.cpu.pybind.core.Tensor) → int¶

numpy(self: open3d.cpu.pybind.core.Tensor) → numpy.ndarray¶

static ones(shape, dtype=None, device=None)¶

Create Tensor with a given shape.

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

prod(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶

reshape(self, dst_shape)¶

Returns a tensor with the same data and number of elements as input, but with the specified shape. When possible, the returned tensor will be a view of input. Otherwise, it will be a copy.

Contiguous inputs and inputs with compatible strides can be reshaped without copying, but you should not depend on the copying vs. viewing behavior.

Ref: - https://pytorch.org/docs/stable/tensors.html - aten/src/ATen/native/TensorShape.cpp - aten/src/ATen/TensorUtils.cpp

Parameters: dst_shape (open3d.core.SizeVector) – Compatible destination shape with the same number of elements.
Returns: open3d.core.Tensor

round(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

save(self: open3d.cpu.pybind.core.Tensor, file_name: str) → None¶: Save tensor to Numpy’s npy format.

sin(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

sin_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

solve(self: open3d.cpu.pybind.core.Tensor, B: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶: Solves the linear system AX = B with LU decomposition and returns X. A must be a square matrix.

sqrt(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

sqrt_(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

sub(*args, **kwargs)¶

Overloaded function.

sub(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

sub_(*args, **kwargs)¶

Overloaded function.

sub_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: float) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: int) -> open3d.cpu.pybind.core.Tensor
sub_(self: open3d.cpu.pybind.core.Tensor, arg0: bool) -> open3d.cpu.pybind.core.Tensor

sum(self: open3d.cpu.pybind.core.Tensor, dim: Optional[open3d.cpu.pybind.core.SizeVector] = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor¶

svd(self: open3d.cpu.pybind.core.Tensor) → Tuple[open3d.cpu.pybind.core.Tensor, open3d.cpu.pybind.core.Tensor, open3d.cpu.pybind.core.Tensor]¶: Computes the matrix SVD decomposition \(A = U S V^T\) and returns the result. Note \(V^T\) (V transpose) is returned instead of \(V\).

to(*args, **kwargs)¶

Overloaded function.

to(self, dtype, copy=False)
Returns a tensor with the specified dtype.

Parameters

dtype (open3d.core.Dtype) – Data type for the Tensor.
copy (bool, optional, default=False) – If true, a new tensor is always created; if false, the copy is avoided when the original tensor already has the targeted dtype.

Returns

open3d.core.Tensor

to(self, device, copy=False)
Returns a tensor with the specified device.

Parameters

device (open3d.core.Device) – Compute device to store and operate on the Tensor.
copy (bool, optional, default=False) – If true, a new tensor is always created; if false, the copy is avoided when the original tensor already has the targeted dtype.

Returns

open3d.core.Tensor

to(self, dtype, copy=False)

Parameters

dtype (open3d.core.Dtype) – Data type for the Tensor.
copy (bool, optional, default=False) – If true, a new tensor is always created; if false, the copy is avoided when the original tensor already has the targeted dtype.

Returns

open3d.core.Tensor

to_dlpack(self: open3d.cpu.pybind.core.Tensor) → capsule¶

tril(self, diagonal=0)¶

Returns the lower triangular matrix of the 2D tensor, above the given diagonal index. [The value of diagonal = col - row, therefore 0 is the main diagonal (row = col), and it shifts towards right for positive values (for diagonal = 1, col - row = 1), and towards left for negative values. The value of the diagonal parameter must be between [-m, n] where {m, n} is the shape of input tensor.

Parameters: diagonal (int, optional, default=0) – Value of [col - row], below which the elements are to be taken for lower triangular matrix.
Returns: open3d.core.Tensor

triu(self, diagonal=0)¶

Returns the upper triangular matrix of the 2D tensor, above the given diagonal index. [The value of diagonal = col - row, therefore 0 is the main diagonal (row = col), and it shifts towards right for positive values (for diagonal = 1, col - row = 1), and towards left for negative values. The value of the diagonal parameter must be between [-m, n] for a {m,n} shaped tensor.

Parameters: diagonal (int, optional, default=0) – Value of [col - row], above which the elements are to be taken for upper triangular matrix.
Returns: open3d.core.Tensor

triul(self, diagonal=0)¶

Returns the tuple of upper and lower triangular matrix of the 2D tensor, above and below the given diagonal index. The diagonal elements of lower triangular matrix are taken to be unity. [The value of diagonal = col - row, therefore 0 is the main diagonal (row = col), and it shifts towards right for positive values (for diagonal = 1, col - row = 1), and towards left for negative values. The value of the diagonal parameter must be between [-m, n] where {m, n} is the shape of input tensor.

Parameters: diagonal (int, optional, default=0) – Value of [col - row], above and below which the elements are to be taken for upper (diag. included) and lower triangular matrix.
Returns: Tuple[open3d.core.Tensor, open3d.core.Tensor]

trunc(self: open3d.cpu.pybind.core.Tensor) → open3d.cpu.pybind.core.Tensor¶

static zeros(shape, dtype=None, device=None)¶

Create Tensor with a given shape.

Parameters

shape (open3d.core.SizeVector) – List of Tensor dimensions.
dtype (Optional[open3d.core.Dtype], optional, default=None) – Data type for the Tensor.
device (Optional[open3d.core.Device], optional, default=None) – Compute device to store and operate on the Tensor.

Returns

open3d.core.Tensor

property blob¶

property device¶

property dtype¶

property is_cpu¶

property is_cuda¶

property ndim¶

property shape¶

property strides¶