aclmdlSetAIPPByInputIndex

Description

Sets the dynamic AIPP attributes for model inference based on a model input index.

Dynamic AIPP provides the following functions and they are executed in the exact sequence: Cropping -> CSC -> Resizing (not supported currently) -> Mean subtraction/Normalization -> Padding

Restrictions

The image size after dynamic AIPP processing must be the same as that defined by the input shape required by the original model.
In batched inference scenarios, the image size after dynamic AIPP is calculated based on the configuration of each batch. After dynamic AIPP, the output image size must be consistent across batches. Table 1 describes the formulas for calculating the result image size.

After image cropping, resizing, or padding, the rules for verifying the image size after dynamic AIPP are as follows. aippOutputW and aippOutputH indicate the width and height of the AIPP output image, respectively. Other parameters are the input parameters of the aclmdlSetAIPPSrcImageSize, aclmdlSetAIPPScfParams, aclmdlSetAIPPCropParams, and aclmdlSetAIPPPaddingParams APIs.

**Table 1** Formulas for calculating the image size after dynamic AIPP
Cropping	Resizing	Padding	Output Width and Height
×	×	×	aippOutputW = srcImageSizeW, aippOutputH = srcImageSizeH
√	×	×	aippOutputW = cropSizeW, aippOutputH = cropSizeH
√	√	×	aippOutputW = scfOutputSizeW, aippOutputH = scfOutputSizeH
√	×	√	aippOutputW = cropSizeW + paddingSizeLeft + paddingSizeRight, aippOutputH = cropSizeH + paddingSizeTop + paddingSizeBottom
×	×	√	aippOutputW = srcImageSizeW + paddingSizeLeft + paddingSizeRight, aippOutputH = srcImageSizeH + paddingSizeTop + paddingSizeBottom
×	√	√	aippOutputW = scfOutputSizeW + paddingSizeLeft + paddingSizeRight, aippOutputH = scfOutputSizeH + paddingSizeTop + paddingSizeBottom
×	√	×	aippOutputW = scfOutputSizeW, aippOutputH = scfOutputSizeH
√	√	√	aippOutputW = scfOutputSizeW + paddingSizeLeft + paddingSizeRight, aippOutputH = scfOutputSizeH + paddingSizeTop + paddingSizeBottom

Prototype

aclError aclmdlSetAIPPByInputIndex(uint32_t modelId, aclmdlDataset *dataset, size_t index, const aclmdlAIPP *aippParmsSet)

Parameters

Parameter	Input/Output	Description
modelId	Input	Model ID. A successful aclmdlLoadFromFile, aclmdlLoadFromMem, aclmdlLoadFromFileWithMem, or aclmdlLoadFromMemWithMem call returns a model ID.
dataset	Input	Pointer to the input data for model inference. Data of type aclmdlDataset describes the input data for model inference, while data of type aclDataBuffer describes the input buffer size and address.
index	Input	Index of the dynamic AIPP input. If the input is not associated with a dynamic AIPP input, an error is reported. Call aclmdlGetAippType to query whether a specified model input has an associated dynamic AIPP input. If yes, the index argument passed to this API call is the same as that of aclmdlGetAippType. If no, you do not need to set dynamic AIPP attributes.
aippParmsSet	Input	Pointer to the dynamic AIPP parameter object. Call aclmdlCreateAIPP in advance to create data of the aclmdlAIPP type.

Returns