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.

1. __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.

2. __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.

3. __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.

4. __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.

5. __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.

6. __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.

1. add(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

add_(*args, **kwargs)

Overloaded function.

1. add_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

all(self: open3d.cpu.pybind.core.Tensor, dim: open3d.cpu.pybind.core.SizeVector | None = 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: open3d.cpu.pybind.core.SizeVector | None = 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: int | None = 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.

1. 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.

2. 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.

3. 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.

4. 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: open3d.cpu.pybind.core.SizeVector | None = None) → open3d.cpu.pybind.core.Tensor

argmin(self: open3d.cpu.pybind.core.Tensor, dim: open3d.cpu.pybind.core.SizeVector | None = None) → open3d.cpu.pybind.core.Tensor

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

clip(*args, **kwargs)

Overloaded function.

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

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

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

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

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

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

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

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

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

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

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

clip_(*args, **kwargs)

Overloaded function.

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

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

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

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

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

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

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

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

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

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

11. 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.

1. div(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

div_(*args, **kwargs)

Overloaded function.

1. div_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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.

1. eq(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

eq_(*args, **kwargs)

Overloaded function.

1. eq_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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: open3d.cpu.pybind.core.Dtype | None = None, device: open3d.cpu.pybind.core.Device | None = 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.

1. 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

2. 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

3. 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

4. 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

5. 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

6. 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

7. 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

8. 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

9. 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

10. 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

11. 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.

1. ge(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

ge_(*args, **kwargs)

Overloaded function.

1. ge_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

gt(*args, **kwargs)

Overloaded function.

1. gt(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

gt_(*args, **kwargs)

Overloaded function.

1. gt_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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.

1. le(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

le_(*args, **kwargs)

Overloaded function.

1. le_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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.

1. logical_and(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

logical_and_(*args, **kwargs)

Overloaded function.

1. logical_and_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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.

1. logical_or(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

logical_or_(*args, **kwargs)

Overloaded function.

1. logical_or_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

logical_xor(*args, **kwargs)

Overloaded function.

1. logical_xor(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

logical_xor_(*args, **kwargs)

Overloaded function.

1. logical_xor_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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.

1. lt(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

lt_(*args, **kwargs)

Overloaded function.

1. lt_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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: open3d.cpu.pybind.core.SizeVector | None = None, keepdim: bool = False) → open3d.cpu.pybind.core.Tensor

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

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

mul(*args, **kwargs)

Overloaded function.

1. mul(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

mul_(*args, **kwargs)

Overloaded function.

1. mul_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

ne(*args, **kwargs)

Overloaded function.

1. ne(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

ne_(*args, **kwargs)

Overloaded function.

1. ne_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

12. 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: open3d.cpu.pybind.core.SizeVector | None = 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.

1. sub(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

sub_(*args, **kwargs)

Overloaded function.

1. sub_(self: open3d.cpu.pybind.core.Tensor, arg0: open3d.cpu.pybind.core.Tensor) -> open3d.cpu.pybind.core.Tensor

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

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

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

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

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

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

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

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

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

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

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

sum(self: open3d.cpu.pybind.core.Tensor, dim: open3d.cpu.pybind.core.SizeVector | None = 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.

1. 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

2. 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

3. 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