NVIDIA DeepStream SDK API Reference

7.1 Release
_NvDsPostProcessContextInitParams Struct Reference

Detailed Description

Holds the initialization parameters required for the NvDsPostProcessContext interface.

Definition at line 262 of file post_processor_struct.h.

Collaboration diagram for _NvDsPostProcessContextInitParams:

Data Fields

unsigned int uniqueID
 Holds a unique identifier for the instance. More...
 
unsigned int maxBatchSize
 Holds the maximum number of frames to be inferred together in a batch. More...
 
char labelsFilePath [_PATH_MAX]
 Holds the pathname of the labels file containing strings for the class labels. More...
 
NvDsPostProcessNetworkType networkType
 Holds the network type. More...
 
unsigned int numDetectedClasses
 Holds the number of classes detected by a detector network. More...
 
NvDsPostProcessDetectionParamsperClassDetectionParams
 Holds per-class detection parameters. More...
 
float classifierThreshold
 Holds the minimum confidence threshold for the classifier to consider a label valid. More...
 
float segmentationThreshold
 
char ** outputLayerNames
 Holds a pointer to an array of pointers to output layer names. More...
 
unsigned int numOutputLayers
 Holds the number of output layer names. More...
 
unsigned int gpuID
 Holds the ID of the GPU which is to run the inference. More...
 
NvDsInferDimsCHW inferInputDims
 Inference input dimensions for runtime engine. More...
 
NvDsPostProcessClusterMode clusterMode
 Holds the type of clustering mode. More...
 
char customBBoxInstanceMaskParseFuncName [_MAX_STR_LENGTH]
 Holds the name of the bounding box and instance mask parse function in the custom library. More...
 
char customBBoxParseFuncName [_MAX_STR_LENGTH]
 Holds the name of the custom bounding box function in the custom library. More...
 
char customClassifierParseFuncName [_MAX_STR_LENGTH]
 Name of the custom classifier attribute parsing function in the custom library. More...
 
NvDsPostProcessTensorOrder segmentationOutputOrder
 Holds output order for segmentation network. More...
 
char * classifier_type
 
gboolean preprocessor_support = FALSE
 Holds boolean value to show whether preprocessor support is there. More...
 

Field Documentation

◆ classifier_type

char* _NvDsPostProcessContextInitParams::classifier_type

Definition at line 323 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ classifierThreshold

float _NvDsPostProcessContextInitParams::classifierThreshold

Holds the minimum confidence threshold for the classifier to consider a label valid.

Definition at line 291 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ clusterMode

NvDsPostProcessClusterMode _NvDsPostProcessContextInitParams::clusterMode

Holds the type of clustering mode.

Definition at line 307 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ customBBoxInstanceMaskParseFuncName

char _NvDsPostProcessContextInitParams::customBBoxInstanceMaskParseFuncName[_MAX_STR_LENGTH]

Holds the name of the bounding box and instance mask parse function in the custom library.

Definition at line 311 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ customBBoxParseFuncName

char _NvDsPostProcessContextInitParams::customBBoxParseFuncName[_MAX_STR_LENGTH]

Holds the name of the custom bounding box function in the custom library.

Definition at line 315 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ customClassifierParseFuncName

char _NvDsPostProcessContextInitParams::customClassifierParseFuncName[_MAX_STR_LENGTH]

Name of the custom classifier attribute parsing function in the custom library.

Definition at line 318 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ gpuID

unsigned int _NvDsPostProcessContextInitParams::gpuID

Holds the ID of the GPU which is to run the inference.

Definition at line 301 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ inferInputDims

NvDsInferDimsCHW _NvDsPostProcessContextInitParams::inferInputDims

Inference input dimensions for runtime engine.

Definition at line 304 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ labelsFilePath

char _NvDsPostProcessContextInitParams::labelsFilePath[_PATH_MAX]

Holds the pathname of the labels file containing strings for the class labels.

The labels file is optional. The file format is described in the custom models section of the DeepStream SDK documentation.

Definition at line 276 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ maxBatchSize

unsigned int _NvDsPostProcessContextInitParams::maxBatchSize

Holds the maximum number of frames to be inferred together in a batch.

The number of input frames in a batch must be less than or equal to this.

Definition at line 271 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ networkType

NvDsPostProcessNetworkType _NvDsPostProcessContextInitParams::networkType

Holds the network type.

Definition at line 280 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ numDetectedClasses

unsigned int _NvDsPostProcessContextInitParams::numDetectedClasses

Holds the number of classes detected by a detector network.

Definition at line 283 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ numOutputLayers

unsigned int _NvDsPostProcessContextInitParams::numOutputLayers

Holds the number of output layer names.

Definition at line 298 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ outputLayerNames

char** _NvDsPostProcessContextInitParams::outputLayerNames

Holds a pointer to an array of pointers to output layer names.

Definition at line 296 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ perClassDetectionParams

NvDsPostProcessDetectionParams* _NvDsPostProcessContextInitParams::perClassDetectionParams

Holds per-class detection parameters.

The array's size must be equal to numDetectedClasses.

Definition at line 287 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ preprocessor_support

gboolean _NvDsPostProcessContextInitParams::preprocessor_support = FALSE

Holds boolean value to show whether preprocessor support is there.

Definition at line 325 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ segmentationOutputOrder

NvDsPostProcessTensorOrder _NvDsPostProcessContextInitParams::segmentationOutputOrder

Holds output order for segmentation network.

Definition at line 321 of file post_processor_struct.h.

◆ segmentationThreshold

float _NvDsPostProcessContextInitParams::segmentationThreshold

Definition at line 293 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().

◆ uniqueID

unsigned int _NvDsPostProcessContextInitParams::uniqueID

Holds a unique identifier for the instance.

This can be used to identify the instance that is generating log and error messages.

Definition at line 266 of file post_processor_struct.h.

Referenced by PostProcessAlgorithm::PostProcessAlgorithm().


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