Softmax

Enumerations | Functions

Softmax

Enumerations
enum	miopenSoftmaxAlgorithm_t {   MIOPEN_SOFTMAX_FAST = 0 ,   MIOPEN_SOFTMAX_ACCURATE = 1 ,   MIOPEN_SOFTMAX_LOG = 2 }
enum	miopenSoftmaxMode_t {   MIOPEN_SOFTMAX_MODE_INSTANCE = 0 ,   MIOPEN_SOFTMAX_MODE_CHANNEL }

Functions
	MIOPEN_DECLARE_OBJECT (miopenSoftmaxDescriptor)
	Creates the miopenSoftmaxDescriptor_t type. More...
miopenStatus_t	miopenSoftmaxForward (miopenHandle_t handle, const void *alpha, const miopenTensorDescriptor_t xDesc, const void *x, const void *beta, const miopenTensorDescriptor_t yDesc, void *y)
	Execute a softmax forward layer. More...
miopenStatus_t	miopenSoftmaxBackward (miopenHandle_t handle, const void *alpha, const miopenTensorDescriptor_t yDesc, const void *y, const miopenTensorDescriptor_t dyDesc, const void *dy, const void *beta, const miopenTensorDescriptor_t dxDesc, void *dx)
	Execute a softmax backwards layer. More...
miopenStatus_t	miopenSoftmaxForward_V2 (miopenHandle_t handle, const void *alpha, const miopenTensorDescriptor_t xDesc, const void *x, const void *beta, const miopenTensorDescriptor_t yDesc, void *y, miopenSoftmaxAlgorithm_t algorithm, miopenSoftmaxMode_t mode)
	Execute a softmax forward layer with expanded modes and algorithms. More...
miopenStatus_t	miopenSoftmaxBackward_V2 (miopenHandle_t handle, const void *alpha, const miopenTensorDescriptor_t yDesc, const void *y, const miopenTensorDescriptor_t dyDesc, const void *dy, const void *beta, const miopenTensorDescriptor_t dxDesc, void *dx, miopenSoftmaxAlgorithm_t algorithm, miopenSoftmaxMode_t mode)
	Execute a softmax backwards layer with expanded modes and algorithms. More...

Detailed Description

Enumeration Type Documentation

◆ miopenSoftmaxAlgorithm_t

enum miopenSoftmaxAlgorithm_t

Softmax implementation algorithms

Enumerator
MIOPEN_SOFTMAX_FAST	straightforward softmax
MIOPEN_SOFTMAX_ACCURATE	scaled softmax by maximum value in input domain
MIOPEN_SOFTMAX_LOG	log softmax

Examples

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h.

◆ miopenSoftmaxMode_t

enum miopenSoftmaxMode_t

Softmax modes

Enumerator
MIOPEN_SOFTMAX_MODE_INSTANCE	compute per image (N) across C, H, W
MIOPEN_SOFTMAX_MODE_CHANNEL	compute per spatial location (H, W) per image (N) across C

Examples

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h.

Function Documentation

◆ MIOPEN_DECLARE_OBJECT()

MIOPEN_DECLARE_OBJECT

(

miopenSoftmaxDescriptor

)

Creates the miopenSoftmaxDescriptor_t type.

◆ miopenSoftmaxBackward()

miopenStatus_t miopenSoftmaxBackward	(	miopenHandle_t	handle,
		const void *	alpha,
		const miopenTensorDescriptor_t	yDesc,
		const void *	y,
		const miopenTensorDescriptor_t	dyDesc,
		const void *	dy,
		const void *	beta,
		const miopenTensorDescriptor_t	dxDesc,
		void *	dx
	)

Execute a softmax backwards layer.

This API only implements the SOFTMAX_MODE_CHANNEL in SOFTMAX_ACCURATE path.

Parameters

handle	MIOpen handle (input)
alpha	Floating point scaling factor, allocated on the host (input)
yDesc	Tensor descriptor for input data tensor y (input)
y	Data tensor y (input)
dyDesc	Tensor descriptor for input data tensor dy (input)
dy	Data delta tensor dy (input)
beta	Floating point shift factor, allocated on the host (input)
dxDesc	Tensor descriptor for data output tensor dx (input)
dx	Output data delta tensor dx (output)

Returns

miopenStatus_t

Examples

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h.

◆ miopenSoftmaxBackward_V2()

miopenStatus_t miopenSoftmaxBackward_V2	(	miopenHandle_t	handle,
		const void *	alpha,
		const miopenTensorDescriptor_t	yDesc,
		const void *	y,
		const miopenTensorDescriptor_t	dyDesc,
		const void *	dy,
		const void *	beta,
		const miopenTensorDescriptor_t	dxDesc,
		void *	dx,
		miopenSoftmaxAlgorithm_t	algorithm,
		miopenSoftmaxMode_t	mode
	)

Execute a softmax backwards layer with expanded modes and algorithms.

Parameters

handle	MIOpen handle (input)
alpha	Floating point scaling factor, allocated on the host (input)
yDesc	Tensor descriptor for input data tensor y (input)
y	Data tensor y (input)
dyDesc	Tensor descriptor for input data tensor dy (input)
dy	Data delta tensor dy (input)
beta	Floating point shift factor, allocated on the host (input)
dxDesc	Tensor descriptor for data output tensor dx (input)
dx	Output data delta tensor dx (output)
algorithm	Softmax implementation algorithm (input)
mode	Softmax mode (input)

Returns

miopenStatus_t

Examples

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h.

◆ miopenSoftmaxForward()

miopenStatus_t miopenSoftmaxForward	(	miopenHandle_t	handle,
		const void *	alpha,
		const miopenTensorDescriptor_t	xDesc,
		const void *	x,
		const void *	beta,
		const miopenTensorDescriptor_t	yDesc,
		void *	y
	)

Execute a softmax forward layer.

This API only implements the SOFTMAX_MODE_CHANNEL in SOFTMAX_ACCURATE path.

Parameters

handle	MIOpen handle (input)
alpha	Floating point scaling factor, allocated on the host (input)
xDesc	Tensor descriptor for data input tensor x (input)
x	Data tensor x (input)
beta	Floating point shift factor, allocated on the host (input)
yDesc	Tensor descriptor for output data tensor y (input)
y	Data tensor y (output)

Returns

miopenStatus_t

Examples

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h.

◆ miopenSoftmaxForward_V2()

miopenStatus_t miopenSoftmaxForward_V2	(	miopenHandle_t	handle,
		const void *	alpha,
		const miopenTensorDescriptor_t	xDesc,
		const void *	x,
		const void *	beta,
		const miopenTensorDescriptor_t	yDesc,
		void *	y,
		miopenSoftmaxAlgorithm_t	algorithm,
		miopenSoftmaxMode_t	mode
	)

Execute a softmax forward layer with expanded modes and algorithms.

Parameters

handle	MIOpen handle (input)
alpha	Floating point scaling factor, allocated on the host (input)
xDesc	Tensor descriptor for data input tensor x (input)
x	Data tensor x (input)
beta	Floating point shift factor, allocated on the host (input)
yDesc	Tensor descriptor for output data tensor y (input)
y	Data tensor y (output)
algorithm	Softmax implementation algorithm (input)
mode	Softmax mode (input)

Returns

miopenStatus_t

Examples

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h.