sTIDL_DataParams_t Struct Reference

Detailed Description

This structure define the parameters of data or kernel buffer used by TIDL layers (In,Out)

Data Fields
int32_t	dataId
int32_t	elementType
int32_t	numDim
int32_t	dataQ
int32_t	minValue
int32_t	maxValue
float32_tidl	minTensorValue
float32_tidl	maxTensorValue
float32_tidl	tensorScale
int32_t	tensorZeroPoint
int32_t	tensorType
int32_t	padW
int32_t	padH
int32_t	batchPadW
int32_t	batchPadH
int32_t	numBatchW
int32_t	numBatchH
int32_t	roundBits
int32_t	pitch [TIDL_DIM_MAX-1U]
int32_t	dimValues [TIDL_DIM_MAX]

Field Documentation

dataId

int32_t sTIDL_DataParams_t::dataId

Unique Data ID for the tensor holding feature vector

elementType

int32_t sTIDL_DataParams_t::elementType

Element type of the feature vector as defined in eTIDL_ElementType

numDim

int32_t sTIDL_DataParams_t::numDim

Number of dimensions supported by the tensor

dataQ

int32_t sTIDL_DataParams_t::dataQ

Q factor used for fixed point : NOT used now

minValue

int32_t sTIDL_DataParams_t::minValue

Minimum value of Accumulator in fixed point : NOT used now

maxValue

int32_t sTIDL_DataParams_t::maxValue

Maximum value of Accumulator in fixed point : NOT used now

minTensorValue

float32_tidl sTIDL_DataParams_t::minTensorValue

Minimum value of Accumulator in floating point

maxTensorValue

float32_tidl sTIDL_DataParams_t::maxTensorValue

Maximum value of Accumulator in floating point

tensorScale

float32_tidl sTIDL_DataParams_t::tensorScale

Scale value applied on the tensor for final fixed point

tensorZeroPoint

int32_t sTIDL_DataParams_t::tensorZeroPoint

Zero point value used in conjunction with the tensor scale to quantize/dequantize tensors

tensorType

int32_t sTIDL_DataParams_t::tensorType

Is the tensor symmetric (zero point = 0) or asymmetric

padW

int32_t sTIDL_DataParams_t::padW

Horizontal Padding

padH

int32_t sTIDL_DataParams_t::padH

Vertical Padding

batchPadW

int32_t sTIDL_DataParams_t::batchPadW

Padding between horizontal Batches in stitched image

batchPadH

int32_t sTIDL_DataParams_t::batchPadH

Padding between vertical Batches in the stitched image

numBatchW

int32_t sTIDL_DataParams_t::numBatchW

Number of Batches stitched in the width direction for batch processing

numBatchH

int32_t sTIDL_DataParams_t::numBatchH

Number of Batches stitched in the height direction for batch processing

roundBits

int32_t sTIDL_DataParams_t::roundBits

Rounding bit used while converting to small bit depth (8 or 16 bit)

pitch

int32_t sTIDL_DataParams_t::pitch[TIDL_DIM_MAX-1U]

Pitch for each dimension as defined by eTIDL_PitchDimIndex

dimValues

int32_t sTIDL_DataParams_t::dimValues[TIDL_DIM_MAX]

Values of dimensions as defined by eTIDL_DataDimIndex