Struct TensorRef 

pub struct TensorRef<H, M>
where
    H: HalideType,
    M: TensorMachine,
{ /* private fields */ }

This is modeled as a reference to a tensor, you should never be able to dereference this. At any point you should only have &TensorRef or &mut TensorRef, never an owned TensorRef.

Implementations

impl<H: HalideType, M: TensorMachine> TensorRef<H, M>

pub fn copy_from_host_tensor( &mut self, tensor: &TensorRef<H, Host>, ) -> Result<()>

Copies the data from a host tensor to the self.as_ptr()

The tensors must have the same logical shape; MNN converts between layouts (e.g. NCHW <-> NC4HW4) as part of the copy.

pub fn copy_to_host_tensor(&self, tensor: &mut TensorRef<H, Host>) -> Result<()>

Copies the data from the self.as_ptr() to a host tensor

The tensors must have the same logical shape; MNN converts between layouts (e.g. NCHW <-> NC4HW4) as part of the copy.

impl<T> TensorRef<T, Device>

where T: HalideType,

pub fn wait(&self, map_type: MapType, finish: bool)

Try to wait for the device tensor to finish processing

pub fn create_host_tensor_from_device( &self, copy_data: bool, ) -> Tensor<Owned<T>, Host>

Create a host tensor from the device tensor with same dimensions and data type and optionally copy the data from the device tensor

The host tensor uses the unpacked layout (NCHW / NHWC) even when the device tensor is stored as NC4HW4, so host() yields the elements in logical order.

impl<T, M> TensorRef<T, M>

where T: HalideType, M: TensorMachine,

pub fn fill(&mut self, value: T) -> Result<()>

where T: Copy,

Fill the tensor with the specified value

Fails if the tensor has a different element type, has not been resized yet (dynamic shape) or, for device tensors, if MNN refuses the copy (e.g. no backend is attached).

impl<T> TensorRef<T, Host>

where T: HalideType,

pub fn try_host(&self) -> Result<&[T]>

Try to map the device tensor to the host memory and get the slice

pub fn try_host_mut(&mut self) -> Result<&mut [T]>

Try to map the device tensor to the host memory and get the mutable slice

pub fn host(&self) -> &[T]

Get the host memory slice of the tensor

pub fn host_mut(&mut self) -> &mut [T]

Get the mutable host memory slice of the tensor

Methods from Deref<Target = AnyTensorRef>

pub fn device_id(&self) -> u64

Get the device id of the tensor

pub fn shape(&self) -> TensorShape

Get the shape of the tensor

pub fn dimensions(&self) -> usize

Get the dimensions of the tensor

pub fn width(&self) -> u32

Get the width of the tensor

pub fn height(&self) -> u32

Get the height of the tensor

pub fn channel(&self) -> u32

Get the channel size of the tensor

pub fn batch(&self) -> u32

Get the batch size of the tensor

pub fn size(&self) -> usize

Get the size of the tensor when counted by bytes

Note that for packed layouts (NC4HW4) this includes the padding MNN adds to the channel dimension, so it can be larger than the product of the shape.

pub fn element_size(&self) -> usize

Get the size of the tensor when counted by elements

Note that for packed layouts (NC4HW4) this includes the padding MNN adds to the channel dimension, so it can be larger than the product of the shape.

pub fn get_type(&self) -> halide_type_t

Get the halide data type of the tensor

pub fn is_type_of<Ha: HalideType>(&self) -> bool

Check if the tensor is of the specified data type

pub fn is_same_type(&self, other: &AnyTensorRef) -> bool

Check if both tensors have the same halide data type

pub fn get_dimension_type(&self) -> DimensionType

Get the dimension type of the tensor

pub fn is_dynamic_unsized(&self) -> bool

Check if the tensor is dynamic and needs resizing

pub fn copy_from_host_tensor(&mut self, tensor: &AnyTensorRef) -> Result<()>

Copies the data from a host tensor to the self.as_ptr()

pub fn copy_to_host_tensor(&self, tensor: &mut AnyTensorRef) -> Result<()>

Copies the data from the self.as_ptr() to a host tensor

pub fn create_host_tensor_from_device<T: HalideType + Copy>( &self, copy_data: bool, ) -> Tensor<Owned<T>, Host>

Create a host tensor from the device tensor with same dimensions and data type and optionally copy the data from the device tensor

Panics

Panics if the tensor’s element type is not T or the copy fails.

Trait Implementations

impl<H, M> Debug for TensorRef<H, M>

where H: HalideType, M: TensorMachine,

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<H, M> Deref for TensorRef<H, M>

where H: HalideType, M: TensorMachine,

type Target = AnyTensorRef

The resulting type after dereferencing.

fn deref(&self) -> &Self::Target

Dereferences the value.

impl<H, M> DerefMut for TensorRef<H, M>

where H: HalideType, M: TensorMachine,

fn deref_mut(&mut self) -> &mut Self::Target

Mutably dereferences the value.