fastdeploy::FDTensor Struct Reference

FDTensor object used to represend data matrix. More...

#include <fd_tensor.h>

Public Member Functions
void	SetData (const std::vector< int64_t > &tensor_shape, const FDDataType &data_type, void *data_buffer, bool copy=false, const Device &data_device=Device::CPU, int data_device_id=-1)
	Set data buffer for a FDTensor, e.g std::vector<float> buffer(1 * 3 * 224 * 224, 0); FDTensor tensor; tensor.SetData({1, 3, 224, 224}, FDDataType::FLOAT, buffer.data()); . More...
void *	GetData ()
	Get data pointer of tensor.
const void *	GetData () const
	Get data pointer of tensor.
void	ExpandDim (int64_t axis=0)
	Expand the shape of tensor, it will not change the data memory, just modify its attribute shape
void	Squeeze (int64_t axis=0)
	Squeeze the shape of tensor, it will not change the data memory, just modify its attribute shape
bool	Reshape (const std::vector< int64_t > &new_shape)
	Reshape the tensor, it will not change the data memory, just modify its attribute shape
int	Nbytes () const
	Total size of tensor memory buffer in bytes.
int	Numel () const
	Total number of elements in tensor.
std::vector< int64_t >	Shape () const
	Get shape of tensor.
FDDataType	Dtype () const
	Get dtype of tensor.
void	Allocate (const FDDataType &data_type, const std::vector< int64_t > &data_shape)
	Allocate cpu data buffer for a FDTensor, e.g FDTensor tensor; tensor.Allocate(FDDataType::FLOAT, {1, 3, 224, 224}; . More...
void	PrintInfo (const std::string &prefix="Debug TensorInfo: ") const
	Debug function, print shape, dtype, mean, max, min of tensor.
bool	IsShared ()
	Whether the tensor is owned the data buffer or share the data buffer from outside.
void	StopSharing ()
	If the tensor is share the data buffer from outside, StopSharing will copy to its own structure; Otherwise, do nothing.

Public Attributes
std::string	name = ""
	Name of tensor, while feed to runtime, this need be defined.

Detailed Description

FDTensor object used to represend data matrix.

Member Function Documentation

Allocate()

void fastdeploy::FDTensor::Allocate ( const FDDataType &  data_type, const std::vector< int64_t > &  data_shape  )

inline

Allocate cpu data buffer for a FDTensor, e.g

FDTensor tensor;
tensor.Allocate(FDDataType::FLOAT, {1, 3, 224, 224};

.

Parameters

[in]	data_type	The data type of tensor
[in]	tensor_shape	The shape of tensor

SetData()

void fastdeploy::FDTensor::SetData ( const std::vector< int64_t > &  tensor_shape, const FDDataType &  data_type, void *  data_buffer, bool  copy = false, const Device &  data_device = Device::CPU, int  data_device_id = -1  )

inline

Set data buffer for a FDTensor, e.g

std::vector<float> buffer(1 * 3 * 224 * 224, 0);
FDTensor tensor;
tensor.SetData({1, 3, 224, 224}, FDDataType::FLOAT, buffer.data());

.

Parameters

[in]	tensor_shape	The shape of tensor
[in]	data_type	The data type of tensor
[in]	data_buffer	The pointer of data buffer memory
[in]	copy	Whether to copy memory from data_buffer to tensor, if false, this tensor will share memory with data_buffer, and the data is managed by userself
[in]	data_device	The device of data_buffer, e.g if data_buffer is a pointer to GPU data, the device should be Device::GPU
[in]	data_device_id	The device id of data_buffer

---

The documentation for this struct was generated from the following files:

• /fastdeploy/my_work/FastDeploy/fastdeploy/core/fd_tensor.h
• /fastdeploy/my_work/FastDeploy/fastdeploy/core/fd_tensor.cc