Data Structures
class	TargetArchs
	Class providing a set of static methods to check what NVIDIA\* card architecture the CUDA module was built for. More...
class	DeviceInfo
	Class providing functionality for querying the specified GPU properties. More...
Enumerations
enum	FeatureSet
	Enumeration providing CUDA computing features. More...
Functions
CV_EXPORTS int	getCudaEnabledDeviceCount ()
	Returns the number of installed CUDA-enabled devices.
CV_EXPORTS void	setDevice (int device)
	Sets a device and initializes it for the current thread.
CV_EXPORTS int	getDevice ()
	Returns the current device index set by cuda::setDevice or initialized by default.
CV_EXPORTS void	resetDevice ()
	Explicitly destroys and cleans up all resources associated with the current device in the current process.
CV_EXPORTS bool	deviceSupports (FeatureSet feature_set)
	checks whether current device supports the given feature
CV_EXPORTS void	convertFp16 (InputArray _src, OutputArray _dst, Stream &stream=Stream::Null())
	Converts an array to half precision floating number.

Enumeration Type Documentation

enum FeatureSet

Enumeration providing CUDA computing features.

Definition at line 592 of file core/cuda.hpp.

Function Documentation

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

Converts an array to half precision floating number.

Parameters:

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

CV_EXPORTS bool cv::cuda::deviceSupports ( FeatureSet feature_set )

checks whether current device supports the given feature

CV_EXPORTS 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.

CV_EXPORTS int cv::cuda::getDevice ( )

Returns the current device index set by cuda::setDevice or initialized by default.

CV_EXPORTS 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.

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

Sets a device and initializes it for the current thread.

Parameters:

device System index of a CUDA device starting with 0.

If the call of this function is omitted, a default device is initialized at the fist CUDA usage.