Derivatives of this class wraps cv::Mat for different backends and targets.
More...
#include "dnn.hpp"
Derivatives of this class wraps cv::Mat for different backends and targets.
§ BackendWrapper() [1/3]
cv::dnn::BackendWrapper::BackendWrapper |
( |
int |
backendId, |
|
|
int |
targetId |
|
) |
| |
§ BackendWrapper() [2/3]
cv::dnn::BackendWrapper::BackendWrapper |
( |
int |
targetId, |
|
|
const cv::Mat & |
m |
|
) |
| |
Wrap cv::Mat for specific backend and target.
- Parameters
-
[in] | targetId | Target identifier. |
[in] | m | cv::Mat for wrapping. |
Make CPU->GPU data transfer if it's require for the target.
§ BackendWrapper() [3/3]
Make wrapper for reused cv::Mat.
- Parameters
-
[in] | base | Wrapper of cv::Mat that will be reused. |
[in] | shape | Specific shape. |
Initialize wrapper from another one. It'll wrap the same host CPU memory and mustn't allocate memory on device(i.e. GPU). It might has different shape. Use in case of CPU memory reusing for reuse associented memory on device too.
§ ~BackendWrapper()
virtual cv::dnn::BackendWrapper::~BackendWrapper |
( |
| ) |
|
|
virtual |
Virtual destructor to make polymorphism.
§ copyToHost()
virtual void cv::dnn::BackendWrapper::copyToHost |
( |
| ) |
|
|
pure virtual |
Transfer data to CPU host memory.
§ backendId
int cv::dnn::BackendWrapper::backendId |
§ targetId
int cv::dnn::BackendWrapper::targetId |
The documentation for this class was generated from the following file: