|
NVIDIA DeepStream SDK API Reference
|
7.1 Release
|
Go to the documentation of this file.
23 #ifndef __NVDSINFERSERVER_IBACKEND_H__
24 #define __NVDSINFERSERVER_IBACKEND_H__
138 const std::string& bindingName)
const = 0;
This is a header file for pre-processing cuda kernels with normalization and mean subtraction require...
InferDataType
Datatype of the tensor buffer.
std::vector< InputShapeTuple > InputShapes
virtual ~IBackend()=default
Destructor, default.
Header file for the data types used in the inference processing.
std::tuple< std::string, InferBatchDims > InputShapeTuple
Tuple of layer name and dimensions including batch size.
std::function< void(SharedBatchArray)> InputsConsumed
Function wrapper called after the input buffer is consumed.
InferTensorOrder
The type of tensor order.
Stores the information of a layer in the inference model.
std::tuple< const LayerDescription *, int > LayersTuple
Tuple containing pointer to layer descriptions and the number of layers.
bool isInput
True if the layer is an input layer.
std::string name
Name of the model layer.
virtual int32_t maxBatchSize() const =0
Get the configured maximum batch size for this backend.
IBackend()=default
Constructor, default.
virtual LayersTuple getInputLayers() const =0
Get the LayersTuple for input layers.
std::vector< LayerDescription > LayerDescriptionList
virtual NvDsInferStatus enqueue(SharedBatchArray inputs, SharedCuStream stream, InputsConsumed bufConsumed, InferenceDone inferenceDone)=0
Enqueue an array of input batches for inference.
Header file of the common declarations for the nvinferserver library.
virtual NvDsInferStatus specifyInputDims(const InputShapes &shapes)=0
Specify the input layers for the backend.
virtual LayersTuple getOutputLayers() const =0
Get the LayersTuple for output layers.
std::function< void(NvDsInferStatus, SharedBatchArray)> InferenceDone
Function wrapper for post inference processing.
virtual uint32_t getLayerSize() const =0
Get the number of layers (input and output) for the model.
std::shared_ptr< CudaStream > SharedCuStream
Cuda based pointers.
virtual uint32_t getInputLayerSize() const =0
Get the number of input layers.
InferDims inferDims
Dimensions of the layer.
Holds the information about the dimensions of a neural network layer.
virtual NvDsInferStatus initialize()=0
Initialize the backend for processing.
int bindingIndex
Index of the layer as per sequence in which the layer is added to the list of layers.
virtual InferTensorOrder getInputTensorOrder() const =0
Get the tensor order set for the input.
virtual bool isFirstDimBatch() const =0
Check if the flag for first dimension being batch is set.
InferDataType dataType
Data type of the layer.
virtual const LayerDescription * getLayerInfo(const std::string &bindingName) const =0
Get the layer description from the layer name.
std::shared_ptr< BaseBatchArray > SharedBatchArray
NvDsInferStatus
Enum for the status codes returned by NvDsInferContext.