#include <CUDATexture.h>
◆ CUDATexture2D() [1/2]
| reg23::CUDATexture2D::CUDATexture2D |
( |
const at::Tensor & |
tensor, |
|
|
const std::string & |
addressModeX, |
|
|
const std::string & |
addressModeY |
|
) |
| |
◆ CUDATexture2D() [2/2]
◆ CleanUp()
| void reg23::CUDATexture2D::CleanUp |
( |
| ) |
|
|
noexcept |
Cleans up the underlying PyTorch tensor, CUDA texture and CUDA array.
This is effectively the destructor, but it is defined separately so it can be called independently. This is because it doesn't seem to be possible to have the destructor of this class called automatically on destruction when used via Python bindings.
◆ Handle()
◆ SizeTensor()
| at::Tensor reg23::CUDATexture2D::SizeTensor |
( |
| ) |
const |
The documentation for this class was generated from the following file:
- /home/runner/work/grangeat-2d-3d-register-pytorch/grangeat-2d-3d-register-pytorch/reg23/src/backend/include/reg23/CUDATexture.h