tensorNet

DNN abstract base class that provides TensorRT functionality underneath. More...

Classes
class	tensorNet
	Abstract class for loading a tensor network with TensorRT. More...

Macros
#define	DEFAULT_MAX_BATCH_SIZE   1
	Default maximum batch size. More...
#define	LOG_TRT   "[TRT] "
	Prefix used for tagging printed log output from TensorRT. More...

Enumerations
enum	precisionType {   TYPE_DISABLED = 0, TYPE_FASTEST, TYPE_FP32, TYPE_FP16,   TYPE_INT8, NUM_PRECISIONS }
	Enumeration for indicating the desired precision that the network should run in, if available in hardware. More...
enum	deviceType {   DEVICE_GPU = 0, DEVICE_DLA, DEVICE_DLA_0 = DEVICE_DLA, DEVICE_DLA_1,   NUM_DEVICES }
	Enumeration for indicating the desired device that the network should run on, if available in hardware. More...
enum	modelType { MODEL_CUSTOM = 0, MODEL_CAFFE, MODEL_ONNX, MODEL_UFF }
	Enumeration indicating the format of the model that's imported in TensorRT (either caffe, ONNX, or UFF). More...
enum	profilerQuery {   PROFILER_PREPROCESS = 0, PROFILER_NETWORK, PROFILER_POSTPROCESS, PROFILER_VISUALIZE,   PROFILER_TOTAL }
	Profiling queries. More...
enum	profilerDevice { PROFILER_CPU = 0, PROFILER_CUDA }
	Profiler device. More...

Functions
const char *	precisionTypeToStr (precisionType type)
	Stringize function that returns precisionType in text. More...
precisionType	precisionTypeFromStr (const char *str)
	Parse the precision type from a string. More...
const char *	deviceTypeToStr (deviceType type)
	Stringize function that returns deviceType in text. More...
deviceType	deviceTypeFromStr (const char *str)
	Parse the device type from a string. More...
const char *	modelTypeToStr (modelType type)
	Stringize function that returns modelType in text. More...
modelType	modelTypeFromStr (const char *str)
	Parse the model format from a string. More...
const char *	profilerQueryToStr (profilerQuery query)
	Stringize function that returns profilerQuery in text. More...

Detailed Description

DNN abstract base class that provides TensorRT functionality underneath.

These functions aren't typically accessed by end users unless they are implementing their own DNN class like imageNet or detectNet.

Macro Definition Documentation

DEFAULT_MAX_BATCH_SIZE

#define DEFAULT_MAX_BATCH_SIZE   1

Default maximum batch size.

LOG_TRT

#define LOG_TRT   "[TRT] "

Prefix used for tagging printed log output from TensorRT.

Enumeration Type Documentation

deviceType

enum deviceType

Enumeration for indicating the desired device that the network should run on, if available in hardware.

Enumerator
DEVICE_GPU	GPU (if multiple GPUs are present, a specific GPU can be selected with cudaSetDevice()
DEVICE_DLA	Deep Learning Accelerator (DLA) Core 0 (only on Jetson Xavier)
DEVICE_DLA_0	Deep Learning Accelerator (DLA) Core 0 (only on Jetson Xavier)
DEVICE_DLA_1	Deep Learning Accelerator (DLA) Core 1 (only on Jetson Xavier)
NUM_DEVICES	Number of device types defined.

modelType

enum modelType

Enumeration indicating the format of the model that's imported in TensorRT (either caffe, ONNX, or UFF).

Enumerator
MODEL_CUSTOM	Created directly with TensorRT API.
MODEL_CAFFE	caffemodel
MODEL_ONNX	ONNX.
MODEL_UFF	UFF.

precisionType

enum precisionType

Enumeration for indicating the desired precision that the network should run in, if available in hardware.

Enumerator
TYPE_DISABLED	Unknown, unspecified, or disabled type.
TYPE_FASTEST	The fastest detected precision should be use (i.e. try INT8, then FP16, then FP32)
TYPE_FP32	32-bit floating-point precision (FP32)
TYPE_FP16	16-bit floating-point half precision (FP16)
TYPE_INT8	8-bit integer precision (INT8)
NUM_PRECISIONS	Number of precision types defined.

profilerDevice

enum profilerDevice

Profiler device.

Enumerator
PROFILER_CPU	CPU walltime.
PROFILER_CUDA	CUDA kernel time.

profilerQuery

enum profilerQuery

Profiling queries.

See also

tensorNet::GetProfilerTime()

Enumerator
PROFILER_PREPROCESS
PROFILER_NETWORK
PROFILER_POSTPROCESS
PROFILER_VISUALIZE
PROFILER_TOTAL

Function Documentation

deviceTypeFromStr()

deviceType deviceTypeFromStr

(

const char *

str

)

Parse the device type from a string.

deviceTypeToStr()

const char* deviceTypeToStr

(

deviceType

type

)

Stringize function that returns deviceType in text.

modelTypeFromStr()

modelType modelTypeFromStr

(

const char *

str

)

Parse the model format from a string.

modelTypeToStr()

const char* modelTypeToStr

(

modelType

type

)

Stringize function that returns modelType in text.

precisionTypeFromStr()

precisionType precisionTypeFromStr

(

const char *

str

)

Parse the precision type from a string.

precisionTypeToStr()

const char* precisionTypeToStr

(

precisionType

type

)

Stringize function that returns precisionType in text.

profilerQueryToStr()

const char* profilerQueryToStr

(

profilerQuery

query

)

Stringize function that returns profilerQuery in text.