クラス
class	cv::cuda::TargetArchs
	Class providing a set of static methods to check what NVIDIA* card architecture the CUDA module was built for. [詳解]

class	cv::cuda::DeviceInfo
	Class providing functionality for querying the specified GPU properties. [詳解]

列挙型
enum	cv::cuda::FeatureSet { FEATURE_SET_COMPUTE_10 = 10 , FEATURE_SET_COMPUTE_11 = 11 , FEATURE_SET_COMPUTE_12 = 12 , FEATURE_SET_COMPUTE_13 = 13 , FEATURE_SET_COMPUTE_20 = 20 , FEATURE_SET_COMPUTE_21 = 21 , FEATURE_SET_COMPUTE_30 = 30 , FEATURE_SET_COMPUTE_32 = 32 , FEATURE_SET_COMPUTE_35 = 35 , FEATURE_SET_COMPUTE_50 = 50 , GLOBAL_ATOMICS = FEATURE_SET_COMPUTE_11 , SHARED_ATOMICS = FEATURE_SET_COMPUTE_12 , NATIVE_DOUBLE = FEATURE_SET_COMPUTE_13 , WARP_SHUFFLE_FUNCTIONS = FEATURE_SET_COMPUTE_30 , DYNAMIC_PARALLELISM = FEATURE_SET_COMPUTE_35 }
	Enumeration providing CUDA computing features.

関数
CV_EXPORTS_W int	cv::cuda::getCudaEnabledDeviceCount ()
	Returns the number of installed CUDA-enabled devices. [詳解]

CV_EXPORTS_W void	cv::cuda::setDevice (int device)
	Sets a device and initializes it for the current thread. [詳解]

CV_EXPORTS_W int	cv::cuda::getDevice ()
	Returns the current device index set by cuda::setDevice or initialized by default.

CV_EXPORTS_W void	cv::cuda::resetDevice ()
	Explicitly destroys and cleans up all resources associated with the current device in the current process. [詳解]

CV_EXPORTS bool	cv::cuda::deviceSupports (FeatureSet feature_set)
	checks whether current device supports the given feature

CV_EXPORTS_W void	cv::cuda::printCudaDeviceInfo (int device)

CV_EXPORTS_W void	cv::cuda::printShortCudaDeviceInfo (int device)

CV_EXPORTS void	cv::cuda::convertFp16 (InputArray _src, OutputArray _dst, Stream &stream=Stream::Null())
	Converts an array to half precision floating number. [詳解]

詳解

関数詳解

◆ convertFp16()

CV_EXPORTS void cv::cuda::convertFp16	(	InputArray	_src,
		OutputArray	_dst,
		Stream &	stream = `Stream::Null()`
	)

Converts an array to half precision floating number.

引数

_src	input array.
_dst	output array.
stream	Stream for the asynchronous version.

参照: convertFp16

◆ getCudaEnabledDeviceCount()

CV_EXPORTS_W int cv::cuda::getCudaEnabledDeviceCount ( )

Returns the number of installed CUDA-enabled devices.

Use this function before any other CUDA functions calls. If OpenCV is compiled without CUDA support, this function returns 0. If the CUDA driver is not installed, or is incompatible, this function returns -1.

◆ resetDevice()

CV_EXPORTS_W void cv::cuda::resetDevice ( )

Explicitly destroys and cleans up all resources associated with the current device in the current process.

Any subsequent API call to this device will reinitialize the device.

◆ setDevice()

CV_EXPORTS_W void cv::cuda::setDevice ( int device )

Sets a device and initializes it for the current thread.