TensorWrap classes
- group NVCV_CPP_CUDATOOLS_TENSORWRAP
Typedefs
-
template<typename T, typename StrideT, StrideT... Strides>
class TensorWrapT - #include <TensorWrap.hpp>
TensorWrap class is a non-owning wrap of a N-D tensor used for easy access of its elements in CUDA device.
TensorWrap is a wrapper of a multi-dimensional tensor that can have one or more of its N dimension strides, or pitches, defined either at compile-time or at run-time. Each pitch in
Strides
represents the offset in bytes as a compile-time template parameter that will be applied from the first (slowest changing) dimension to the last (fastest changing) dimension of the tensor, in that order. Each dimension with run-time pitch is specified as -1 in theStrides
template parameter.Template arguments:
T type of the values inside the tensor
StrideT type of the stride used in the byte offset calculation
Strides sequence of compile- or run-time pitches (-1 indicates run-time)
Y compile-time pitches
X run-time pitches
N dimensions, where N = X + Y
For example, in the code below a wrap is defined for an NHWC 4D tensor where each sample image in N has a run-time image pitch (first -1 in template argument), and each row in H has a run-time row pitch (second -1), a pixel in W has a compile-time constant pitch as the size of the pixel type and a channel in C has also a compile-time constant pitch as the size of the channel type.
using DataType = ...; using ChannelType = BaseType<DataType>; using TensorWrap = TensorWrap<ChannelType, -1, -1, sizeof(DataType), sizeof(ChannelType)>; std::byte *imageData = ...; int imgStride = ...; int rowStride = ...; TensorWrap tensorWrap(imageData, imgStride, rowStride); // Elements may be accessed via operator[] using an int4 argument. They can also be accessed via pointer using // the ptr method with up to 4 integer arguments.
Tensor wrapper class specialized for non-constant value type.
See also
- Template Parameters:
T – Type (it can be const) of each element inside the tensor wrapper.
Strides – Each compile-time (use -1 for run-time) pitch in bytes from first to last dimension.
T – Type (non-const) of each element inside the tensor wrapper.
Strides – Each compile-time (use -1 for run-time) pitch in bytes from first to last dimension.
-
template<typename T, typename StrideT, StrideT... Strides>