WarpAffine Class Reference

WarpAffine Class Reference#

2 min read time

Applies to Linux

rocCV: roccv::WarpAffine Class Reference

#include <op_warp_affine.hpp>

Inheritance diagram for roccv::WarpAffine:

Public Member Functions
void	operator() (hipStream_t stream, const Tensor &input, const Tensor &output, const AffineTransform xform, const bool isInverted, const eInterpolationType interp, const eBorderType borderMode, const float4 borderValue, const eDeviceType device=eDeviceType::GPU) const
	Executes the WarpAffine operation on the given HIP stream. WarpAffine applies an affine transformation to a given input image. More...

	WarpAffine ()
	Construct a new WarpAffine object. More...

	~WarpAffine ()
	Destroy the WarpAffine object. More...

Public Member Functions inherited from roccv::IOperator
virtual	~IOperator ()

Constructor & Destructor Documentation

◆ WarpAffine()

roccv::WarpAffine::WarpAffine ( )

inline

Construct a new WarpAffine object.

◆ ~WarpAffine()

roccv::WarpAffine::~WarpAffine ( )

inline

Destroy the WarpAffine object.

Member Function Documentation

◆ operator()()

void roccv::WarpAffine::operator()	(	hipStream_t	stream,
		const Tensor &	input,
		const Tensor &	output,
		const AffineTransform	xform,
		const bool	isInverted,
		const eInterpolationType	interp,
		const eBorderType	borderMode,
		const float4	borderValue,
		const eDeviceType	device = `eDeviceType::GPU`
	)		const

Executes the WarpAffine operation on the given HIP stream. WarpAffine applies an affine transformation to a given input image.

Limitations:

Input: Supported TensorLayout(s): [NHWC, HWC] Channels: [1, 3, 4] Supported DataType(s): [U8, S8, U16, S16, U32, S32, F32, F64]

Output: Supported TensorLayout(s): [NHWC, HWC] Channels: [1, 3, 4] Supported DataTypes(s) [U8, S8, U16, S16, U32, S32, F32, F64]

Input/Output dependency:

  Property      |  Input == Output
 -------------- | -------------
  TensorLayout  | Yes
  DataType      | Yes
  Channels      | Yes
  Width         | No
  Height        | No
  Batch size    | Yes

Parameters

[in]	stream	The HIP stream to run this operator on.
[in]	input	Input tensor with image data.
[out]	output	Output tensor for storing modified image data.
[in]	xform	Affine transformation matrix in row-major order.
[in]	isInverted	Flag defining whether the xform (transformation matrix) is the inverted transformation or not.
[in]	interp	Interpolation method used for warp affine.
[in]	borderMode	The border mode to use for the affine transformation.
[in]	borderValue	The border value to use in the case of a CONSTANT border mode.
[in]	device	The device to run this operator on. (Default: GPU)

The documentation for this class was generated from the following file:

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-roccv/checkouts/latest/include/op_warp_affine.hpp