Open3D (C++ API)
0.12.0
|
#include <Tensor.h>
Public Member Functions | |
Tensor () | |
Tensor (const SizeVector &shape, Dtype dtype, const Device &device=Device("CPU:0")) | |
Constructor for creating a contiguous Tensor. More... | |
template<typename T > | |
Tensor (const std::vector< T > &init_vals, const SizeVector &shape, Dtype dtype, const Device &device=Device("CPU:0")) | |
Constructor for creating a contiguous Tensor with initial values. More... | |
template<typename T > | |
Tensor (const T *init_vals, const SizeVector &shape, Dtype dtype, const Device &device=Device("CPU:0")) | |
Constructor from raw host buffer. The memory will be copied. More... | |
Tensor (const SizeVector &shape, const SizeVector &strides, void *data_ptr, Dtype dtype, const std::shared_ptr< Blob > &blob) | |
Tensor (const Tensor &other)=default | |
Tensor (Tensor &&other)=default | |
Tensor & | operator= (const Tensor &other) & |
Tensor & | operator= (Tensor &&other) & |
Tensor & | operator= (const Tensor &other) && |
Tensor assignment rvalue = lvalue, e.g. tensor_a[0] = tensor_b More... | |
Tensor & | operator= (Tensor &&other) && |
Tensor assignment rvalue = rvalue, e.g. tensor_a[0] = tensor_b[0] More... | |
template<typename T > | |
Tensor & | operator= (const T &v) && |
template<typename Object > | |
Tensor & | AssignObject (const Object &v) && |
template<typename Scalar > | |
void | Fill (Scalar v) |
Fill the whole Tensor with a scalar value, the scalar will be casted to the Tensor's dtype. More... | |
template<typename Object > | |
void | FillObject (const Object &v) |
Tensor | GetItem (const TensorKey &tk) const |
Tensor | GetItem (const std::vector< TensorKey > &tks) const |
Tensor | SetItem (const Tensor &value) |
Set all items. Equivalent to tensor[:] = value in Python. More... | |
Tensor | SetItem (const TensorKey &tk, const Tensor &value) |
Tensor | SetItem (const std::vector< TensorKey > &tks, const Tensor &value) |
void | Assign (const Tensor &other) |
Assign (copy) values from another Tensor, shape, dtype, device may change. More... | |
Tensor | Broadcast (const SizeVector &dst_shape) const |
Broadcast Tensor to a new broadcastable shape. More... | |
Tensor | Expand (const SizeVector &dst_shape) const |
Tensor | Reshape (const SizeVector &dst_shape) const |
Tensor | View (const SizeVector &dst_shape) const |
Tensor | Copy (const Device &device) const |
Tensor | Copy () const |
Copy Tensor to the same device. More... | |
void | CopyFrom (const Tensor &other) |
Copy Tensor values to current tensor for source tensor. More... | |
void | ShallowCopyFrom (const Tensor &other) |
Shallow copy a tensor, returning a tensor sharing the same memory. More... | |
Tensor | To (Dtype dtype, bool copy=false) const |
std::string | ToString (bool with_suffix=true, const std::string &indent="") const |
Tensor | operator[] (int64_t i) const |
Extract the i-th Tensor along the first axis, returning a new view. More... | |
Tensor | IndexExtract (int64_t dim, int64_t idx) const |
Tensor | Slice (int64_t dim, int64_t start, int64_t stop, int64_t step=1) const |
Tensor | AsRvalue () const |
Tensor | IndexGet (const std::vector< Tensor > &index_tensors) const |
Advanced indexing getter. More... | |
void | IndexSet (const std::vector< Tensor > &index_tensors, const Tensor &src_tensor) |
Advanced indexing getter. More... | |
Tensor | Permute (const SizeVector &dims) const |
Permute (dimension shuffle) the Tensor, returns a view. More... | |
Tensor | AsStrided (const SizeVector &new_shape, const SizeVector &new_strides) const |
Create a Tensor view of specified shape and strides. The underlying buffer and data_ptr offsets remain the same. More... | |
Tensor | Transpose (int64_t dim0, int64_t dim1) const |
Transpose a Tensor by swapping dimension dim0 and dim1 . More... | |
Tensor | T () const |
Expects input to be <= 2-D Tensor by swapping dimension 0 and 1. More... | |
double | Det () const |
Expects input to be 3x3 Matrix. More... | |
template<typename T > | |
T | Item () const |
Tensor | Add (const Tensor &value) const |
Adds a tensor and returns the resulting tensor. More... | |
template<typename T > | |
Tensor | Add (T scalar_value) const |
Tensor | operator+ (const Tensor &value) const |
template<typename T > | |
Tensor | operator+ (T scalar_value) const |
Tensor | Add_ (const Tensor &value) |
template<typename T > | |
Tensor | Add_ (T scalar_value) |
Tensor | operator+= (const Tensor &value) |
template<typename T > | |
Tensor | operator+= (T scalar_value) |
Tensor | Sub (const Tensor &value) const |
Substracts a tensor and returns the resulting tensor. More... | |
template<typename T > | |
Tensor | Sub (T scalar_value) const |
Tensor | operator- (const Tensor &value) const |
template<typename T > | |
Tensor | operator- (T scalar_value) const |
Tensor | Sub_ (const Tensor &value) |
template<typename T > | |
Tensor | Sub_ (T scalar_value) |
Tensor | operator-= (const Tensor &value) |
template<typename T > | |
Tensor | operator-= (T scalar_value) |
Tensor | Mul (const Tensor &value) const |
Multiplies a tensor and returns the resulting tensor. More... | |
template<typename T > | |
Tensor | Mul (T scalar_value) const |
Tensor | operator* (const Tensor &value) const |
template<typename T > | |
Tensor | operator* (T scalar_value) const |
Tensor | Mul_ (const Tensor &value) |
template<typename T > | |
Tensor | Mul_ (T scalar_value) |
Tensor | operator*= (const Tensor &value) |
template<typename T > | |
Tensor | operator*= (T scalar_value) |
Tensor | Div (const Tensor &value) const |
Divides a tensor and returns the resulting tensor. More... | |
template<typename T > | |
Tensor | Div (T scalar_value) const |
Tensor | operator/ (const Tensor &value) const |
template<typename T > | |
Tensor | operator/ (T scalar_value) const |
Tensor | Div_ (const Tensor &value) |
template<typename T > | |
Tensor | Div_ (T scalar_value) |
Tensor | operator/= (const Tensor &value) |
template<typename T > | |
Tensor | operator/= (T scalar_value) |
Tensor | Sum (const SizeVector &dims, bool keepdim=false) const |
Tensor | Mean (const SizeVector &dims, bool keepdim=false) const |
Tensor | Prod (const SizeVector &dims, bool keepdim=false) const |
Tensor | Min (const SizeVector &dims, bool keepdim=false) const |
Tensor | Max (const SizeVector &dims, bool keepdim=false) const |
Tensor | ArgMin (const SizeVector &dims) const |
Tensor | ArgMax (const SizeVector &dims) const |
Tensor | Sqrt () const |
Element-wise square root of a tensor, returns a new tensor. More... | |
Tensor | Sqrt_ () |
Element-wise square root of a tensor, in-place. More... | |
Tensor | Sin () const |
Element-wise sine of a tensor, returning a new tensor. More... | |
Tensor | Sin_ () |
Element-wise sine of a tensor, in-place. More... | |
Tensor | Cos () const |
Element-wise cosine of a tensor, returning a new tensor. More... | |
Tensor | Cos_ () |
Element-wise cosine of a tensor, in-place. More... | |
Tensor | Neg () const |
Element-wise negation of a tensor, returning a new tensor. More... | |
Tensor | Neg_ () |
Element-wise negation of a tensor, in-place. More... | |
Tensor | Exp () const |
Element-wise exponential of a tensor, returning a new tensor. More... | |
Tensor | Exp_ () |
Element-wise base-e exponential of a tensor, in-place. More... | |
Tensor | Abs () const |
Element-wise absolute value of a tensor, returning a new tensor. More... | |
Tensor | Abs_ () |
Element-wise absolute value of a tensor, in-place. More... | |
Tensor | LogicalNot () const |
Tensor | LogicalNot_ () |
Tensor | LogicalAnd (const Tensor &value) const |
Tensor | operator && (const Tensor &value) const |
template<typename T > | |
Tensor | LogicalAnd (T scalar_value) const |
Tensor | LogicalAnd_ (const Tensor &value) |
template<typename T > | |
Tensor | LogicalAnd_ (T scalar_value) |
Tensor | LogicalOr (const Tensor &value) const |
Tensor | operator|| (const Tensor &value) const |
template<typename T > | |
Tensor | LogicalOr (T scalar_value) const |
Tensor | LogicalOr_ (const Tensor &value) |
template<typename T > | |
Tensor | LogicalOr_ (T scalar_value) |
Tensor | LogicalXor (const Tensor &value) const |
template<typename T > | |
Tensor | LogicalXor (T scalar_value) const |
Tensor | LogicalXor_ (const Tensor &value) |
template<typename T > | |
Tensor | LogicalXor_ (T scalar_value) |
Tensor | Gt (const Tensor &value) const |
Element-wise greater-than of tensors, returning a new boolean tensor. More... | |
Tensor | operator> (const Tensor &value) const |
template<typename T > | |
Tensor | Gt (T scalar_value) const |
Tensor | Gt_ (const Tensor &value) |
template<typename T > | |
Tensor | Gt_ (T scalar_value) |
Tensor | Lt (const Tensor &value) const |
Element-wise less-than of tensors, returning a new boolean tensor. More... | |
Tensor | operator< (const Tensor &value) const |
template<typename T > | |
Tensor | Lt (T scalar_value) const |
Tensor | Lt_ (const Tensor &value) |
template<typename T > | |
Tensor | Lt_ (T scalar_value) |
Tensor | Ge (const Tensor &value) const |
Tensor | operator>= (const Tensor &value) const |
template<typename T > | |
Tensor | Ge (T scalar_value) const |
Tensor | Ge_ (const Tensor &value) |
template<typename T > | |
Tensor | Ge_ (T scalar_value) |
Tensor | Le (const Tensor &value) const |
Tensor | operator<= (const Tensor &value) const |
template<typename T > | |
Tensor | Le (T scalar_value) const |
Tensor | Le_ (const Tensor &value) |
template<typename T > | |
Tensor | Le_ (T scalar_value) |
Tensor | Eq (const Tensor &value) const |
Element-wise equals-to of tensors, returning a new boolean tensor. More... | |
Tensor | operator== (const Tensor &value) const |
template<typename T > | |
Tensor | Eq (T scalar_value) const |
Tensor | Eq_ (const Tensor &value) |
template<typename T > | |
Tensor | Eq_ (T scalar_value) |
Tensor | Ne (const Tensor &value) const |
Element-wise not-equals-to of tensors, returning a new boolean tensor. More... | |
Tensor | operator!= (const Tensor &value) const |
template<typename T > | |
Tensor | Ne (T scalar_value) const |
Tensor | Ne_ (const Tensor &value) |
template<typename T > | |
Tensor | Ne_ (T scalar_value) |
std::vector< Tensor > | NonZeroNumpy () const |
Tensor | NonZero () const |
bool | IsNonZero () const |
bool | All () const |
bool | Any () const |
bool | AllClose (const Tensor &other, double rtol=1e-5, double atol=1e-8) const |
Tensor | IsClose (const Tensor &other, double rtol=1e-5, double atol=1e-8) const |
bool | IsSame (const Tensor &other) const |
template<typename T > | |
std::vector< T > | ToFlatVector () const |
Retrive all values as an std::vector, for debugging and testing. More... | |
bool | IsContiguous () const |
Tensor | Contiguous () const |
Tensor | Matmul (const Tensor &rhs) const |
Tensor | Solve (const Tensor &rhs) const |
Tensor | LeastSquares (const Tensor &rhs) const |
Tensor | Inverse () const |
std::tuple< Tensor, Tensor, Tensor > | SVD () const |
int64_t | GetLength () const |
SizeVector | GetShape () const |
const SizeVector & | GetShapeRef () const |
int64_t | GetShape (int64_t dim) const |
SizeVector | GetStrides () const |
const SizeVector & | GetStridesRef () const |
int64_t | GetStride (int64_t dim) const |
void * | GetDataPtr () |
const void * | GetDataPtr () const |
Dtype | GetDtype () const |
Device | GetDevice () const |
std::shared_ptr< Blob > | GetBlob () const |
int64_t | NumElements () const |
int64_t | NumDims () const |
template<typename T > | |
void | AssertTemplateDtype () const |
DLManagedTensor * | ToDLPack () const |
Convert the Tensor to DLManagedTensor. More... | |
void | AssertShape (const SizeVector &expected_shape) const |
Assert that the Tensor has the specified shape. More... | |
void | AssertShapeCompatible (const DynamicSizeVector &expected_shape) const |
Assert that Tensor's shape is compatible with a dynamic shape. More... | |
void | AssertDevice (const Device &expected_device) const |
Assert that the Tensor has the specified device. More... | |
void | AssertDtype (const Dtype &expected_dtype) const |
Assert that the Tensor has the specified dtype. More... | |
template<> | |
Tensor (const std::vector< bool > &init_vals, const SizeVector &shape, Dtype dtype, const Device &device) | |
template<> | |
std::vector< bool > | ToFlatVector () const |
template<> | |
bool | Item () const |
Static Public Member Functions | |
static Tensor | Empty (const SizeVector &shape, Dtype dtype, const Device &device=Device("CPU:0")) |
Create a tensor with uninitilized values. More... | |
static Tensor | EmptyLike (const Tensor &other) |
template<typename T > | |
static Tensor | Full (const SizeVector &shape, T fill_value, Dtype dtype, const Device &device=Device("CPU:0")) |
Create a tensor fill with specified value. More... | |
static Tensor | Zeros (const SizeVector &shape, Dtype dtype, const Device &device=Device("CPU:0")) |
Create a tensor fill with zeros. More... | |
static Tensor | Ones (const SizeVector &shape, Dtype dtype, const Device &device=Device("CPU:0")) |
Create a tensor fill with ones. More... | |
static Tensor | Eye (int64_t n, Dtype dtype, const Device &device) |
Create a identity matrix of size n x n. More... | |
static Tensor | Diag (const Tensor &input) |
Create a square matrix with specified diagonal elements in input. More... | |
static SizeVector | DefaultStrides (const SizeVector &shape) |
static std::pair< bool, SizeVector > | ComputeNewStrides (const SizeVector &old_shape, const SizeVector &old_strides, const SizeVector &new_shape) |
static Tensor | FromDLPack (const DLManagedTensor *dlmt) |
Convert DLManagedTensor to Tensor. More... | |
Protected Member Functions | |
std::string | ScalarPtrToString (const void *ptr) const |
Protected Attributes | |
SizeVector | shape_ = {0} |
SizeVector | strides_ = {1} |
void * | data_ptr_ = nullptr |
Dtype | dtype_ = Dtype::Undefined |
Data type. More... | |
std::shared_ptr< Blob > | blob_ = nullptr |
Underlying memory buffer for Tensor. More... | |
A Tensor is a "view" of a data Blob with shape, stride, data_ptr. Tensor can also be used to perform numerical operations.
|
inline |
|
inline |
Constructor for creating a contiguous Tensor.
|
inline |
Constructor for creating a contiguous Tensor with initial values.
|
inline |
Constructor from raw host buffer. The memory will be copied.
|
inline |
|
default |
|
default |
|
inline |
Tensor open3d::core::Tensor::Abs | ( | ) | const |
Element-wise absolute value of a tensor, returning a new tensor.
Tensor open3d::core::Tensor::Abs_ | ( | ) |
Element-wise absolute value of a tensor, in-place.
Adds a tensor and returns the resulting tensor.
Inplace version of Tensor::Add. Adds a tensor to the current tensor and returns the current tensor.
bool open3d::core::Tensor::All | ( | ) | const |
Returns true if all elements in the tensor are true. Only works for boolean tensors. This function does not take reduction dimensions, and the reduction is apply to all dimensions.
bool open3d::core::Tensor::AllClose | ( | const Tensor & | other, |
double | rtol = 1e-5 , |
||
double | atol = 1e-8 |
||
) | const |
Returns true if the two tensors are element-wise equal within a tolerance.
The equation is not symmetrial, i.e. a.AllClose(b) might not be the same as b.AllClose(a). Also see Numpy's documentation: https://numpy.org/doc/stable/reference/generated/numpy.allclose.html.
TODO: support nan
other | The other tensor to compare with. |
rtol | Relative tolerance. |
atol | Absolute tolerance. |
bool open3d::core::Tensor::Any | ( | ) | const |
Returns true if any elements in the tensor are true. Only works for boolean tensors. This function does not take reduction dimensions, and the reduction is apply to all dimensions.
Tensor open3d::core::Tensor::ArgMax | ( | const SizeVector & | dims | ) | const |
Returns maximum index of the tensor along the given dim
. The returned tensor has dtype int64_t, and has the same shape as original tensor except that the reduced dimension is removed.
dims | dims can only contain a single dimension or all dimensions. If dims contains a single dimension, the index is along the specified dimension. If dims contains all dimensions, the index is into the flattend tensor. |
Tensor open3d::core::Tensor::ArgMin | ( | const SizeVector & | dims | ) | const |
Returns minimum index of the tensor along the given dim
. The returned tensor has dtype int64_t, and has the same shape as original tensor except that the reduced dimension is removed.
dims | dims can only contain a single dimension or all dimensions. If dims contains a single dimension, the index is along the specified dimension. If dims contains all dimensions, the index is into the flattend tensor. |
|
inline |
Convert to rvalue such that the Tensor can be assigned. E.g. in numpy
void open3d::core::Tensor::AssertDevice | ( | const Device & | expected_device | ) | const |
Assert that the Tensor has the specified device.
void open3d::core::Tensor::AssertDtype | ( | const Dtype & | expected_dtype | ) | const |
Assert that the Tensor has the specified dtype.
void open3d::core::Tensor::AssertShape | ( | const SizeVector & | expected_shape | ) | const |
Assert that the Tensor has the specified shape.
void open3d::core::Tensor::AssertShapeCompatible | ( | const DynamicSizeVector & | expected_shape | ) | const |
Assert that Tensor's shape is compatible with a dynamic shape.
|
inline |
void open3d::core::Tensor::Assign | ( | const Tensor & | other | ) |
|
inline |
Assign an object to a tensor. The tensor being assigned to must be a scalr tensor of shape {}. The element byte size of the tensor must be the same as the size of the object. The object must be a POD.
Tensor open3d::core::Tensor::AsStrided | ( | const SizeVector & | new_shape, |
const SizeVector & | new_strides | ||
) | const |
Create a Tensor view of specified shape and strides. The underlying buffer and data_ptr offsets remain the same.
Tensor open3d::core::Tensor::Broadcast | ( | const SizeVector & | dst_shape | ) | const |
Broadcast Tensor to a new broadcastable shape.
|
static |
oldshape
into chunks of dimensions, where the dimensions are ``contiguous'' in each chunk, i.e., oldstride[i] = oldshape[i+1] * oldstride[i+1]newshape
must be able to be separated into same number of chunks as oldshape
was separated into, where each chunk of newshape has matching ``numel'', i.e., number of subspaces, as the corresponding chunk of oldshape
. Ref: aten/src/ATen/TensorUtils.cpp Tensor open3d::core::Tensor::Contiguous | ( | ) | const |
Returns a contiguous Tensor containing the same data in the same device. If self tensor is already contiguous, the same underlying memory will be used.
void open3d::core::Tensor::CopyFrom | ( | const Tensor & | other | ) |
Copy Tensor values to current tensor for source tensor.
Tensor open3d::core::Tensor::Cos | ( | ) | const |
Element-wise cosine of a tensor, returning a new tensor.
Tensor open3d::core::Tensor::Cos_ | ( | ) |
Element-wise cosine of a tensor, in-place.
|
static |
double open3d::core::Tensor::Det | ( | ) | const |
Expects input to be 3x3 Matrix.
Create a square matrix with specified diagonal elements in input.
Divides a tensor and returns the resulting tensor.
Inplace version of Tensor::Div. Divides a tensor to the current tensor and returns the current tensor.
|
static |
Create a tensor with uninitilized values.
Create a tensor with uninitilized values with the same dtype and device as the other tensor.
Element-wise equals-to of tensors, returning a new boolean tensor.
Element-wise equals-to of tensors, in-place. This operation won't change the tensor's dtype.
Tensor open3d::core::Tensor::Exp | ( | ) | const |
Element-wise exponential of a tensor, returning a new tensor.
Tensor open3d::core::Tensor::Exp_ | ( | ) |
Element-wise base-e exponential of a tensor, in-place.
Tensor open3d::core::Tensor::Expand | ( | const SizeVector & | dst_shape | ) | const |
Expand Tensor to a new broadcastable shape, returning a new view.
Tensors can be expanded to broadcastable shape by setting dimension of size 1 to have stride 0, without allocating new memory.
Create a identity matrix of size n x n.
|
inline |
|
inline |
|
static |
Convert DLManagedTensor to Tensor.
|
inlinestatic |
Create a tensor fill with specified value.
Element-wise greater-than-or-equals-to of tensors, returning a new boolean tensor.
Element-wise greater-than-or-equals-to of tensors, in-place. This operation won't change the tensor's dtype.
|
inline |
|
inline |
|
inline |
Device open3d::core::Tensor::GetDevice | ( | ) | const |
|
inline |
Pythonic getitem for tensor.
Returns a view of the original tensor, if TensorKey is TensorKeyMode::Index or TensorKeyMode::Slice. Returns a copy if the TensorKey contains TensorKeyMode::IndexTensor (advanced indexing).
For example, in numpy:
The equivalent Open3D C++ calls:
Pythonic getitem for tensor.
Returns a view of the original tensor, if TensorKey only contains TensorKeyMode::Index or TensorKeyMode::Slice. Returns a copy if the TensorKey contains IndexTensor (advanced indexing).
For example, in numpy:
The equivalent Open3D C++ calls:
|
inline |
Returns the size of the first dimension. If NumDims() == 0, an exception will be thrown.
|
inline |
|
inline |
|
inline |
|
inline |
|
inline |
|
inline |
Element-wise greater-than of tensors, returning a new boolean tensor.
Element-wise greater-than of tensors, in-place. This operation won't change the tensor's dtype.
Tensor open3d::core::Tensor::IndexExtract | ( | int64_t | dim, |
int64_t | idx | ||
) | const |
Extract the idx
-th sub-tensor in dimension dim
. After IndexExtract, the dimension dim
will be removed.
Advanced indexing getter.
We use the Numpy advanced indexing symnatics, see: https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
void open3d::core::Tensor::IndexSet | ( | const std::vector< Tensor > & | index_tensors, |
const Tensor & | src_tensor | ||
) |
Advanced indexing getter.
We use the Numpy advanced indexing symnatics, see: https://docs.scipy.org/doc/numpy/reference/arrays.indexing.html
Note: Only support 1D index tensors. Note: Only support advanced indices are all next to each other.
Tensor open3d::core::Tensor::Inverse | ( | ) | const |
Computes the matrix inversion of the square matrix *this with LU factorization and returns the result.
Tensor open3d::core::Tensor::IsClose | ( | const Tensor & | other, |
double | rtol = 1e-5 , |
||
double | atol = 1e-8 |
||
) | const |
Element-wise version of Tensor::AllClose.
The equation is not symmetrial, i.e. a.AllClose(b) might not be the same as b.AllClose(a). Also see Numpy's documentation: https://numpy.org/doc/stable/reference/generated/numpy.allclose.html.
TODO: support nan
other | The other tensor to compare with. |
rtol | Relative tolerance. |
atol | Absolute tolerance. |
|
inline |
Returns True if the underlying memory buffer is contiguous. A contiguous Tensor's data_ptr_ does not need to point to the beginning of blob_.
bool open3d::core::Tensor::IsNonZero | ( | ) | const |
Evaluate a single-element Tensor as a boolean value. This can be used to implement Tensor.__bool__() in Python, e.g.
bool open3d::core::Tensor::IsSame | ( | const Tensor & | other | ) | const |
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.
|
inline |
|
inline |
Element-wise less-than-or-equals-to of tensors, returning a new boolean tensor.
Element-wise less-than-or-equals-to of tensors, in-place. This operation won't change the tensor's dtype.
Solves the linear system AX = B with QR decomposition and returns X. A is a (m, n) matrix with m >= n.
Element-wise logical and of a tensor, returning a new boolean tensor.
If the tensor is not boolean, zero will be treated as False, while non-zero values will be treated as True.
Element-wise logical and of tensors, in-place. This operation won't change the tensor's dtype.
If the tensor is not boolean, 0 will be treated as False, while non-zero will be treated as True. The tensor will be filled with 0 or 1 casted to the tensor's dtype.
Tensor open3d::core::Tensor::LogicalNot | ( | ) | const |
Element-wise logical not of a tensor, returning a new boolean tensor.
If the tensor is not boolean, 0 will be treated as False, while non-zero will be treated as True.
Tensor open3d::core::Tensor::LogicalNot_ | ( | ) |
Element-wise logical not of a tensor, in-place. This operation won't change the tensor's dtype.
If the tensor is not boolean, 0 will be treated as False, while non-zero will be treated as True. The tensor will be filled with 0 or 1 casted to the tensor's dtype.
Element-wise logical or of tensors, returning a new boolean tensor.
If the tensor is not boolean, zero will be treated as False, while non-zero values will be treated as True.
Element-wise logical or of tensors, in-place. This operation won't change the tensor's dtype.
If the tensor is not boolean, 0 will be treated as False, while non-zero will be treated as True. The tensor will be filled with 0 or 1 casted to the tensor's dtype.
Element-wise logical exclusive-or of tensors, returning a new boolean tensor.
If the tensor is not boolean, zero will be treated as False, while non-zero values will be treated as True.
Element-wise logical exclusive-or of tensors, in-place. This operation won't change the tensor's dtype.
If the tensor is not boolean, zero will be treated as False, while non-zero values will be treated as True. The tensor will be filled with 0 or 1 casted to the tensor's dtype.
Element-wise less-than of tensors, returning a new boolean tensor.
Element-wise less-than of tensors, in-place. This operation won't change the tensor's dtype.
Computes matrix multiplication with *this and rhs and returns the result.
Tensor open3d::core::Tensor::Max | ( | const SizeVector & | dims, |
bool | keepdim = false |
||
) | const |
Returns max of the tensor along the given dims
.
dims | A list of dimensions to be reduced. |
keepdim | If true, the reduced dims will be retained as size 1. |
Tensor open3d::core::Tensor::Mean | ( | const SizeVector & | dims, |
bool | keepdim = false |
||
) | const |
Returns the mean of the tensor along the given dims
.
dims | A list of dimensions to be reduced. |
keepdim | If true, the reduced dims will be retained as size 1. |
Tensor open3d::core::Tensor::Min | ( | const SizeVector & | dims, |
bool | keepdim = false |
||
) | const |
Returns min of the tensor along the given dims
.
dims | A list of dimensions to be reduced. |
keepdim | If true, the reduced dims will be retained as size 1. |
Multiplies a tensor and returns the resulting tensor.
Inplace version of Tensor::Mul. Multiplies a tensor to the current tensor and returns the current tensor.
Element-wise not-equals-to of tensors, returning a new boolean tensor.
Element-wise equals-to of tensors, in-place. This operation won't change the tensor's dtype.
Tensor open3d::core::Tensor::Neg | ( | ) | const |
Element-wise negation of a tensor, returning a new tensor.
Tensor open3d::core::Tensor::Neg_ | ( | ) |
Element-wise negation of a tensor, in-place.
Tensor open3d::core::Tensor::NonZero | ( | ) | const |
Find the indices of the elements that are non-zero. 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.
std::vector< Tensor > open3d::core::Tensor::NonZeroNumpy | ( | ) | const |
Find the indices of the elements that are non-zero. Returns a vector of int64 Tensors, each containing the indices of the non-zero elements in each dimension.
|
inline |
|
inline |
|
static |
Create a tensor fill with ones.
Tensor assignment lvalue = lvalue, e.g. tensor_a = tensor_b
. This results in a "shallow" copy.
Tensor assignment lvalue = rvalue, e.g. tensor_a = tensor_b[0]
. This results in a "shallow" copy.
Tensor open3d::core::Tensor::operator[] | ( | int64_t | i | ) | const |
Extract the i-th Tensor along the first axis, returning a new view.
Tensor open3d::core::Tensor::Permute | ( | const SizeVector & | dims | ) | const |
Tensor open3d::core::Tensor::Prod | ( | const SizeVector & | dims, |
bool | keepdim = false |
||
) | const |
Returns the product of the tensor along the given dims
.
dims | A list of dimensions to be reduced. |
keepdim | If true, the reduced dims will be retained as size 1. |
Tensor open3d::core::Tensor::Reshape | ( | const SizeVector & | dst_shape | ) | const |
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
|
protected |
Set all items. Equivalent to tensor[:] = value
in Python.
Pythonic setitem for tensor.
For example, in numpy:
The equivalent Open3D C++ calls:
Pythonic setitem for tensor.
For example, in numpy:
The equivalent Open3D C++ calls:
void open3d::core::Tensor::ShallowCopyFrom | ( | const Tensor & | other | ) |
Shallow copy a tensor, returning a tensor sharing the same memory.
Tensor open3d::core::Tensor::Sin | ( | ) | const |
Element-wise sine of a tensor, returning a new tensor.
Tensor open3d::core::Tensor::Sin_ | ( | ) |
Element-wise sine of a tensor, in-place.
Tensor open3d::core::Tensor::Slice | ( | int64_t | dim, |
int64_t | start, | ||
int64_t | stop, | ||
int64_t | step = 1 |
||
) | const |
Slice Tensor.
dim | The dimension to slice. |
start | The start index (inclusive). |
stop | The end index (exclusive). |
step | Pick one eleemnt for every step elements. |
Solves the linear system AX = B with QR decomposition and returns X. A must be a square matrix.
Tensor open3d::core::Tensor::Sqrt | ( | ) | const |
Element-wise square root of a tensor, returns a new tensor.
Tensor open3d::core::Tensor::Sqrt_ | ( | ) |
Element-wise square root of a tensor, in-place.
Substracts a tensor and returns the resulting tensor.
Inplace version of Tensor::Sub. Substracts a tensor to the current tensor and returns the current tensor.
Tensor open3d::core::Tensor::Sum | ( | const SizeVector & | dims, |
bool | keepdim = false |
||
) | const |
Returns the sum of the tensor along the given dims
.
dims | A list of dimensions to be reduced. |
keepdim | If true, the reduced dims will be retained as size 1. |
Computes the matrix SVD decomposition A = U S VT and returns the result. Note VT (V transpose) is returned instead of V.
Tensor open3d::core::Tensor::T | ( | ) | const |
Returns a tensor with the specified dtype
.
dtype | The targeted dtype to convert to. |
copy | If true, a new tensor is always created; if false, the copy is avoided when the original tensor already have the targeted dtype. |
DLManagedTensor * open3d::core::Tensor::ToDLPack | ( | ) | const |
Convert the Tensor to DLManagedTensor.
|
inline |
Retrive all values as an std::vector, for debugging and testing.
|
inline |
std::string open3d::core::Tensor::ToString | ( | bool | with_suffix = true , |
const std::string & | indent = "" |
||
) | const |
Tensor open3d::core::Tensor::Transpose | ( | int64_t | dim0, |
int64_t | dim1 | ||
) | const |
Transpose a Tensor by swapping dimension dim0
and dim1
.
dim0 | The first dimension to be transposed. |
dim1 | The second dimension to be transposed. |
Tensor open3d::core::Tensor::View | ( | const SizeVector & | dst_shape | ) | const |
Returns a new tensor view with the same data but of a different shape.
The returned tensor shares the same data and must have the same number of elements, but may have a different size. For a tensor to be viewed, the new view size must be compatible with its original size and stride, i.e., each new view dimension must either be a subspace of an original dimension, or only span across original dimensions d, d+1, ..., d+kd,d+1, ..., d+k that satisfy the following contiguity-like condition that for all i = 0, ..., k-1, strides[i] = stride[i + 1] * shape[i + 1].
Otherwise, contiguous() needs to be called before the tensor can be viewed. See also: reshape(), which returns a view if the shapes are compatible, and copies (equivalent to calling contiguous()) otherwise.
Ref: https://pytorch.org/docs/stable/tensors.html aten/src/ATen/native/TensorShape.cpp aten/src/ATen/TensorUtils.cpp
|
static |
Create a tensor fill with zeros.
|
protected |
Underlying memory buffer for Tensor.
|
protected |
Data pointer pointing to the beginning element of the Tensor.
Note that this is not necessarily the same as blob_.GetDataPtr(). When this happens, it means that the beginning element of the Tensor is not located a the beginning of the underlying blob. This could happen, for instance, at slicing:
|
protected |
Data type.
|
protected |
SizeVector of the Tensor. SizeVector[i] is the legnth of dimension i.
|
protected |
Stride of a Tensor. The stride of a n-dimensional tensor is also n-dimensional. Stride(i) is the number of elements (not bytes) to jump in a continuous memory space before eaching the next element in dimension i. For example, a 2x3x4 float32 dense tensor has shape(2, 3, 4) and stride(12, 4, 1). A slicing operation performed on the tensor can change the shape and stride.