ONNX Runtime
Loading...
Searching...
No Matches
Ort::detail::ValueImpl< T > Struct Template Reference

#include <onnxruntime_cxx_api.h>

Inheritance diagram for Ort::detail::ValueImpl< T >:
Ort::detail::ConstValueImpl< T > Ort::detail::Base< T >

Public Types

using B = ConstValueImpl< T >
 
using B = Base< T >
 
- Public Types inherited from Ort::detail::ConstValueImpl< T >
using B = Base< T >
 
- Public Types inherited from Ort::detail::Base< T >
using contained_type = T
 

Public Member Functions

template<typename R >
R * GetTensorMutableData ()
 Returns a non-const typed pointer to an OrtValue/Tensor contained buffer No type checking is performed, the caller must ensure the type matches the tensor type.
 
void * GetTensorMutableRawData ()
 Returns a non-typed non-const pointer to a tensor contained data.
 
template<typename R >
R & At (const std::vector< int64_t > &location)
 
void FillStringTensor (const char *const *s, size_t s_len)
 Set all strings at once in a string tensor.
 
void FillStringTensorElement (const char *s, size_t index)
 Set a single string in a string tensor.
 
char * GetResizedStringTensorElementBuffer (size_t index, size_t buffer_length)
 Allocate if necessary and obtain a pointer to a UTF-8 encoded string element buffer indexed by the flat element index, of the specified length.
 
void UseCooIndices (int64_t *indices_data, size_t indices_num)
 Supplies COO format specific indices and marks the contained sparse tensor as being a COO format tensor. Values are supplied with a CreateSparseTensor() API. The supplied indices are not copied and the user allocated buffers lifespan must eclipse that of the OrtValue. The location of the indices is assumed to be the same as specified by OrtMemoryInfo argument at the creation time.
 
void UseCsrIndices (int64_t *inner_data, size_t inner_num, int64_t *outer_data, size_t outer_num)
 Supplies CSR format specific indices and marks the contained sparse tensor as being a CSR format tensor. Values are supplied with a CreateSparseTensor() API. The supplied indices are not copied and the user allocated buffers lifespan must eclipse that of the OrtValue. The location of the indices is assumed to be the same as specified by OrtMemoryInfo argument at the creation time.
 
void UseBlockSparseIndices (const Shape &indices_shape, int32_t *indices_data)
 Supplies BlockSparse format specific indices and marks the contained sparse tensor as being a BlockSparse format tensor. Values are supplied with a CreateSparseTensor() API. The supplied indices are not copied and the user allocated buffers lifespan must eclipse that of the OrtValue. The location of the indices is assumed to be the same as specified by OrtMemoryInfo argument at the creation time.
 
void FillSparseTensorCoo (const OrtMemoryInfo *data_mem_info, const OrtSparseValuesParam &values_param, const int64_t *indices_data, size_t indices_num)
 The API will allocate memory using the allocator instance supplied to the CreateSparseTensor() API and copy the values and COO indices into it. If data_mem_info specifies that the data is located at difference device than the allocator, a X-device copy will be performed if possible.
 
void FillSparseTensorCsr (const OrtMemoryInfo *data_mem_info, const OrtSparseValuesParam &values, const int64_t *inner_indices_data, size_t inner_indices_num, const int64_t *outer_indices_data, size_t outer_indices_num)
 The API will allocate memory using the allocator instance supplied to the CreateSparseTensor() API and copy the values and CSR indices into it. If data_mem_info specifies that the data is located at difference device than the allocator, a X-device copy will be performed if possible.
 
void FillSparseTensorBlockSparse (const OrtMemoryInfo *data_mem_info, const OrtSparseValuesParam &values, const Shape &indices_shape, const int32_t *indices_data)
 The API will allocate memory using the allocator instance supplied to the CreateSparseTensor() API and copy the values and BlockSparse indices into it. If data_mem_info specifies that the data is located at difference device than the allocator, a X-device copy will be performed if possible.
 
- Public Member Functions inherited from Ort::detail::ConstValueImpl< T >
template<typename R >
void GetOpaqueData (const char *domain, const char *type_name, R &) const
 Obtains a pointer to a user defined data for experimental purposes.
 
bool IsTensor () const
 Returns true if Value is a tensor, false for other types like map/sequence/etc.
 
bool HasValue () const
 
size_t GetCount () const
 < Return true if OrtValue contains data and returns false if the OrtValue is a None
 
Value GetValue (int index, OrtAllocator *allocator) const
 
size_t GetStringTensorDataLength () const
 This API returns a full length of string data contained within either a tensor or a sparse Tensor. For sparse tensor it returns a full length of stored non-empty strings (values). The API is useful for allocating necessary memory and calling GetStringTensorContent().
 
void GetStringTensorContent (void *buffer, size_t buffer_length, size_t *offsets, size_t offsets_count) const
 The API copies all of the UTF-8 encoded string data contained within a tensor or a sparse tensor into a supplied buffer. Use GetStringTensorDataLength() to find out the length of the buffer to allocate. The user must also allocate offsets buffer with the number of entries equal to that of the contained strings.
 
template<typename R >
const R * GetTensorData () const
 Returns a const typed pointer to the tensor contained data. No type checking is performed, the caller must ensure the type matches the tensor type.
 
const void * GetTensorRawData () const
 Returns a non-typed pointer to a tensor contained data.
 
TypeInfo GetTypeInfo () const
 The API returns type information for data contained in a tensor. For sparse tensors it returns type information for contained non-zero values. It returns dense shape for sparse tensors.
 
TensorTypeAndShapeInfo GetTensorTypeAndShapeInfo () const
 The API returns type information for data contained in a tensor. For sparse tensors it returns type information for contained non-zero values. It returns dense shape for sparse tensors.
 
ConstMemoryInfo GetTensorMemoryInfo () const
 This API returns information about the memory allocation used to hold data.
 
void GetStringTensorElement (size_t buffer_length, size_t element_index, void *buffer) const
 The API copies UTF-8 encoded bytes for the requested string element contained within a tensor or a sparse tensor into a provided buffer. Use GetStringTensorElementLength() to obtain the length of the buffer to allocate.
 
std::string GetStringTensorElement (size_t element_index) const
 Returns string tensor UTF-8 encoded string element. Use of this API is recommended over GetStringTensorElement() that takes void* buffer pointer.
 
size_t GetStringTensorElementLength (size_t element_index) const
 The API returns a byte length of UTF-8 encoded string element contained in either a tensor or a spare tensor values.
 
OrtSparseFormat GetSparseFormat () const
 The API returns the sparse data format this OrtValue holds in a sparse tensor. If the sparse tensor was not fully constructed, i.e. Use*() or Fill*() API were not used the value returned is ORT_SPARSE_UNDEFINED.
 
TensorTypeAndShapeInfo GetSparseTensorValuesTypeAndShapeInfo () const
 The API returns type and shape information for stored non-zero values of the sparse tensor. Use GetSparseTensorValues() to obtain values buffer pointer.
 
TensorTypeAndShapeInfo GetSparseTensorIndicesTypeShapeInfo (OrtSparseIndicesFormat format) const
 The API returns type and shape information for the specified indices. Each supported indices have their own enum values even if a give format has more than one kind of indices. Use GetSparseTensorIndicesData() to obtain pointer to indices buffer.
 
template<typename R >
const R * GetSparseTensorIndicesData (OrtSparseIndicesFormat indices_format, size_t &num_indices) const
 The API retrieves a pointer to the internal indices buffer. The API merely performs a convenience data type casting on the return type pointer. Make sure you are requesting the right type, use GetSparseTensorIndicesTypeShapeInfo();.
 
bool IsSparseTensor () const
 Returns true if the OrtValue contains a sparse tensor.
 
template<typename R >
const R * GetSparseTensorValues () const
 The API returns a pointer to an internal buffer of the sparse tensor containing non-zero values. The API merely does casting. Make sure you are requesting the right data type by calling GetSparseTensorValuesTypeAndShapeInfo() first.
 
- Public Member Functions inherited from Ort::detail::Base< T >
constexpr Base ()=default
 
constexpr Base (contained_type *p) noexcept
 
 ~Base ()
 
 Base (const Base &)=delete
 
Baseoperator= (const Base &)=delete
 
 Base (Base &&v) noexcept
 
Baseoperator= (Base &&v) noexcept
 
constexpr operator contained_type * () const noexcept
 
contained_typerelease ()
 Relinquishes ownership of the contained C object pointer The underlying object is not destroyed.
 

Additional Inherited Members

- Protected Attributes inherited from Ort::detail::Base< T >
contained_typep_ {}
 

Member Typedef Documentation

◆ B [1/2]

template<typename T >
using Ort::detail::ValueImpl< T >::B = ConstValueImpl<T>

◆ B [2/2]

template<typename T >
using Ort::detail::ConstValueImpl< T >::B = Base<T>

Member Function Documentation

◆ At()

template<typename T >
template<typename R >
R & Ort::detail::ValueImpl< T >::At ( const std::vector< int64_t > &  location)

by the vector of dims.

Template Parameters
R
Parameters
location[in] expressed by a vecotr of dimensions offsets
Returns

◆ FillSparseTensorBlockSparse()

template<typename T >
void Ort::detail::ValueImpl< T >::FillSparseTensorBlockSparse ( const OrtMemoryInfo data_mem_info,
const OrtSparseValuesParam values,
const Shape indices_shape,
const int32_t *  indices_data 
)

The API will allocate memory using the allocator instance supplied to the CreateSparseTensor() API and copy the values and BlockSparse indices into it. If data_mem_info specifies that the data is located at difference device than the allocator, a X-device copy will be performed if possible.

Parameters
data_mem_infospecified buffer memory description
valuesvalues buffer information
indices_shapeindices shape. use {0} for fully sparse tensors
indices_datapointer to indices data or nullptr for fully sparse tensors

◆ FillSparseTensorCoo()

template<typename T >
void Ort::detail::ValueImpl< T >::FillSparseTensorCoo ( const OrtMemoryInfo data_mem_info,
const OrtSparseValuesParam values_param,
const int64_t *  indices_data,
size_t  indices_num 
)

The API will allocate memory using the allocator instance supplied to the CreateSparseTensor() API and copy the values and COO indices into it. If data_mem_info specifies that the data is located at difference device than the allocator, a X-device copy will be performed if possible.

Parameters
data_mem_infospecified buffer memory description
values_paramvalues buffer information.
indices_datacoo indices buffer or nullptr for fully sparse data
indices_numnumber of COO indices or 0 for fully sparse data

◆ FillSparseTensorCsr()

template<typename T >
void Ort::detail::ValueImpl< T >::FillSparseTensorCsr ( const OrtMemoryInfo data_mem_info,
const OrtSparseValuesParam values,
const int64_t *  inner_indices_data,
size_t  inner_indices_num,
const int64_t *  outer_indices_data,
size_t  outer_indices_num 
)

The API will allocate memory using the allocator instance supplied to the CreateSparseTensor() API and copy the values and CSR indices into it. If data_mem_info specifies that the data is located at difference device than the allocator, a X-device copy will be performed if possible.

Parameters
data_mem_infospecified buffer memory description
valuesvalues buffer information
inner_indices_datacsr inner indices pointer or nullptr for fully sparse tensors
inner_indices_numnumber of csr inner indices or 0 for fully sparse tensors
outer_indices_datapointer to csr indices data or nullptr for fully sparse tensors
outer_indices_numnumber of csr outer indices or 0

◆ FillStringTensor()

template<typename T >
void Ort::detail::ValueImpl< T >::FillStringTensor ( const char *const *  s,
size_t  s_len 
)

Set all strings at once in a string tensor.

Parameters
s[in] An array of strings. Each string in this array must be null terminated.
s_len[in] Count of strings in s (Must match the size of value's tensor shape)

◆ FillStringTensorElement()

template<typename T >
void Ort::detail::ValueImpl< T >::FillStringTensorElement ( const char *  s,
size_t  index 
)

Set a single string in a string tensor.

Parameters
s[in] A null terminated UTF-8 encoded string
index[in] Index of the string in the tensor to set

◆ GetResizedStringTensorElementBuffer()

template<typename T >
char * Ort::detail::ValueImpl< T >::GetResizedStringTensorElementBuffer ( size_t  index,
size_t  buffer_length 
)

Allocate if necessary and obtain a pointer to a UTF-8 encoded string element buffer indexed by the flat element index, of the specified length.

This API is for advanced usage. It avoids a need to construct an auxiliary array of string pointers, and allows to write data directly (do not zero terminate).

Parameters
index
buffer_length
Returns
a pointer to a writable buffer

◆ GetTensorMutableData()

template<typename T >
template<typename R >
R * Ort::detail::ValueImpl< T >::GetTensorMutableData ( )

Returns a non-const typed pointer to an OrtValue/Tensor contained buffer No type checking is performed, the caller must ensure the type matches the tensor type.

Returns
non-const pointer to data, no copies made

◆ GetTensorMutableRawData()

template<typename T >
void * Ort::detail::ValueImpl< T >::GetTensorMutableRawData ( )

Returns a non-typed non-const pointer to a tensor contained data.

Returns
pointer to data, no copies made

◆ UseBlockSparseIndices()

template<typename T >
void Ort::detail::ValueImpl< T >::UseBlockSparseIndices ( const Shape indices_shape,
int32_t *  indices_data 
)

Supplies BlockSparse format specific indices and marks the contained sparse tensor as being a BlockSparse format tensor. Values are supplied with a CreateSparseTensor() API. The supplied indices are not copied and the user allocated buffers lifespan must eclipse that of the OrtValue. The location of the indices is assumed to be the same as specified by OrtMemoryInfo argument at the creation time.

Parameters
indices_shapeindices shape or a {0} for fully sparse
indices_datauser allocated buffer with indices or nullptr for fully spare tensors

◆ UseCooIndices()

template<typename T >
void Ort::detail::ValueImpl< T >::UseCooIndices ( int64_t *  indices_data,
size_t  indices_num 
)

Supplies COO format specific indices and marks the contained sparse tensor as being a COO format tensor. Values are supplied with a CreateSparseTensor() API. The supplied indices are not copied and the user allocated buffers lifespan must eclipse that of the OrtValue. The location of the indices is assumed to be the same as specified by OrtMemoryInfo argument at the creation time.

Parameters
indices_datapointer to the user allocated buffer with indices. Use nullptr for fully sparse tensors.
indices_numnumber of indices entries. Use 0 for fully sparse tensors

◆ UseCsrIndices()

template<typename T >
void Ort::detail::ValueImpl< T >::UseCsrIndices ( int64_t *  inner_data,
size_t  inner_num,
int64_t *  outer_data,
size_t  outer_num 
)

Supplies CSR format specific indices and marks the contained sparse tensor as being a CSR format tensor. Values are supplied with a CreateSparseTensor() API. The supplied indices are not copied and the user allocated buffers lifespan must eclipse that of the OrtValue. The location of the indices is assumed to be the same as specified by OrtMemoryInfo argument at the creation time.

Parameters
inner_datapointer to the user allocated buffer with inner indices or nullptr for fully sparse tensors
inner_numnumber of csr inner indices or 0 for fully sparse tensors
outer_datapointer to the user allocated buffer with outer indices or nullptr for fully sparse tensors
outer_numnumber of csr outer indices or 0 for fully sparse tensors