Jetson Inference
DNN Vision Library
|
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. More...
Classes | |
class | tensorNet |
Abstract class for loading a tensor network with TensorRT. More... | |
Macros | |
#define | TENSORRT_VERSION_CHECK(major, minor, patch) (NV_TENSORRT_MAJOR > major || (NV_TENSORRT_MAJOR == major && NV_TENSORRT_MINOR > minor) || (NV_TENSORRT_MAJOR == major && NV_TENSORRT_MINOR == minor && NV_TENSORRT_PATCH >= patch)) |
Macro for checking the minimum version of TensorRT that is installed. More... | |
#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, MODEL_ENGINE } |
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... | |
modelType | modelTypeFromPath (const char *path) |
Parse the model format from a file path. More... | |
const char * | profilerQueryToStr (profilerQuery query) |
Stringize function that returns profilerQuery in text. More... | |
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.
class tensorNet |
Abstract class for loading a tensor network with TensorRT.
For example implementations,
Public Member Functions | |
virtual | ~tensorNet () |
Destory. More... | |
bool | LoadNetwork (const char *prototxt, const char *model, const char *mean=NULL, const char *input_blob="data", const char *output_blob="prob", uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL) |
Load a new network instance. More... | |
bool | LoadNetwork (const char *prototxt, const char *model, const char *mean, const char *input_blob, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL) |
Load a new network instance with multiple output layers. More... | |
bool | LoadNetwork (const char *prototxt, const char *model, const char *mean, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL) |
Load a new network instance with multiple input layers. More... | |
bool | LoadNetwork (const char *prototxt, const char *model, const char *mean, const char *input_blob, const Dims3 &input_dims, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL) |
Load a new network instance (this variant is used for UFF models) More... | |
bool | LoadNetwork (const char *prototxt, const char *model, const char *mean, const std::vector< std::string > &input_blobs, const std::vector< Dims3 > &input_dims, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL) |
Load a new network instance with multiple input layers (used for UFF models) More... | |
bool | LoadEngine (const char *engine_filename, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, nvinfer1::IPluginFactory *pluginFactory=NULL, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL) |
Load a network instance from a serialized engine plan file. More... | |
bool | LoadEngine (char *engine_stream, size_t engine_size, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, nvinfer1::IPluginFactory *pluginFactory=NULL, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL) |
Load a network instance from a serialized engine plan file. More... | |
bool | LoadEngine (nvinfer1::ICudaEngine *engine, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL) |
Load network resources from an existing TensorRT engine instance. More... | |
bool | LoadEngine (const char *filename, char **stream, size_t *size) |
Load a serialized engine plan file into memory. More... | |
void | EnableLayerProfiler () |
Manually enable layer profiling times. More... | |
void | EnableDebug () |
Manually enable debug messages and synchronization. More... | |
bool | AllowGPUFallback () const |
Return true if GPU fallback is enabled. More... | |
deviceType | GetDevice () const |
Retrieve the device being used for execution. More... | |
precisionType | GetPrecision () const |
Retrieve the type of precision being used. More... | |
bool | IsPrecision (precisionType type) const |
Check if a particular precision is being used. More... | |
cudaStream_t | GetStream () const |
Retrieve the stream that the device is operating on. More... | |
cudaStream_t | CreateStream (bool nonBlocking=true) |
Create and use a new stream for execution. More... | |
void | SetStream (cudaStream_t stream) |
Set the stream that the device is operating on. More... | |
const char * | GetPrototxtPath () const |
Retrieve the path to the network prototxt file. More... | |
const char * | GetModelPath () const |
Retrieve the full path to model file, including the filename. More... | |
const char * | GetModelFilename () const |
Retrieve the filename of the file, excluding the directory. More... | |
modelType | GetModelType () const |
Retrieve the format of the network model. More... | |
bool | IsModelType (modelType type) const |
Return true if the model is of the specified format. More... | |
uint32_t | GetInputLayers () const |
Retrieve the number of input layers to the network. More... | |
uint32_t | GetOutputLayers () const |
Retrieve the number of output layers to the network. More... | |
Dims3 | GetInputDims (uint32_t layer=0) const |
Retrieve the dimensions of network input layer. More... | |
uint32_t | GetInputWidth (uint32_t layer=0) const |
Retrieve the width of network input layer. More... | |
uint32_t | GetInputHeight (uint32_t layer=0) const |
Retrieve the height of network input layer. More... | |
uint32_t | GetInputSize (uint32_t layer=0) const |
Retrieve the size (in bytes) of network input layer. More... | |
float * | GetInputPtr (uint32_t layer=0) const |
Get the CUDA pointer to the input layer's memory. More... | |
Dims3 | GetOutputDims (uint32_t layer=0) const |
Retrieve the dimensions of network output layer. More... | |
uint32_t | GetOutputWidth (uint32_t layer=0) const |
Retrieve the width of network output layer. More... | |
uint32_t | GetOutputHeight (uint32_t layer=0) const |
Retrieve the height of network output layer. More... | |
uint32_t | GetOutputSize (uint32_t layer=0) const |
Retrieve the size (in bytes) of network output layer. More... | |
float * | GetOutputPtr (uint32_t layer=0) const |
Get the CUDA pointer to the output memory. More... | |
float | GetNetworkFPS () |
Retrieve the network frames per second (FPS). More... | |
float | GetNetworkTime () |
Retrieve the network runtime (in milliseconds). More... | |
const char * | GetNetworkName () const |
Retrieve the network name (it's filename). More... | |
float2 | GetProfilerTime (profilerQuery query) |
Retrieve the profiler runtime (in milliseconds). More... | |
float | GetProfilerTime (profilerQuery query, profilerDevice device) |
Retrieve the profiler runtime (in milliseconds). More... | |
void | PrintProfilerTimes () |
Print the profiler times (in millseconds). More... | |
Static Public Member Functions | |
static bool | LoadClassLabels (const char *filename, std::vector< std::string > &descriptions, int expectedClasses=-1) |
Load class descriptions from a label file. More... | |
static bool | LoadClassLabels (const char *filename, std::vector< std::string > &descriptions, std::vector< std::string > &synsets, int expectedClasses=-1) |
Load class descriptions and synset strings from a label file. More... | |
static bool | LoadClassColors (const char *filename, float4 *colors, int expectedClasses, float defaultAlpha=255.0f) |
Load class colors from a text file. More... | |
static bool | LoadClassColors (const char *filename, float4 **colors, int expectedClasses, float defaultAlpha=255.0f) |
Load class colors from a text file. More... | |
static float4 | GenerateColor (uint32_t classID, float alpha=255.0f) |
Procedurally generate a color for a given class index with the specified alpha value. More... | |
static precisionType | SelectPrecision (precisionType precision, deviceType device=DEVICE_GPU, bool allowInt8=true) |
Resolve a desired precision to a specific one that's available. More... | |
static precisionType | FindFastestPrecision (deviceType device=DEVICE_GPU, bool allowInt8=true) |
Determine the fastest native precision on a device. More... | |
static std::vector< precisionType > | DetectNativePrecisions (deviceType device=DEVICE_GPU) |
Detect the precisions supported natively on a device. More... | |
static bool | DetectNativePrecision (const std::vector< precisionType > &nativeTypes, precisionType type) |
Detect if a particular precision is supported natively. More... | |
static bool | DetectNativePrecision (precisionType precision, deviceType device=DEVICE_GPU) |
Detect if a particular precision is supported natively. More... | |
Protected Member Functions | |
tensorNet () | |
Constructor. More... | |
bool | ProcessNetwork (bool sync=true) |
Execute processing of the network. More... | |
bool | ProfileModel (const std::string &deployFile, const std::string &modelFile, const std::vector< std::string > &inputs, const std::vector< Dims3 > &inputDims, const std::vector< std::string > &outputs, uint32_t maxBatchSize, precisionType precision, deviceType device, bool allowGPUFallback, nvinfer1::IInt8Calibrator *calibrator, char **engineStream, size_t *engineSize) |
Create and output an optimized network model. More... | |
bool | ConfigureBuilder (nvinfer1::IBuilder *builder, uint32_t maxBatchSize, uint32_t workspaceSize, precisionType precision, deviceType device, bool allowGPUFallback, nvinfer1::IInt8Calibrator *calibrator) |
Configure builder options. More... | |
bool | ValidateEngine (const char *model_path, const char *cache_path, const char *checksum_path) |
Validate that the model already has a built TensorRT engine that exists and doesn't need updating. More... | |
void | PROFILER_BEGIN (profilerQuery query) |
Begin a profiling query, before network is run. More... | |
void | PROFILER_END (profilerQuery query) |
End a profiling query, after the network is run. More... | |
bool | PROFILER_QUERY (profilerQuery query) |
Query the CUDA part of a profiler query. More... | |
Protected Attributes | |
tensorNet::Logger | gLogger |
tensorNet::Profiler | gProfiler |
std::string | mPrototxtPath |
std::string | mModelPath |
std::string | mModelFile |
std::string | mMeanPath |
std::string | mCacheEnginePath |
std::string | mCacheCalibrationPath |
std::string | mChecksumPath |
deviceType | mDevice |
precisionType | mPrecision |
modelType | mModelType |
cudaStream_t | mStream |
cudaEvent_t | mEventsGPU [PROFILER_TOTAL *2] |
timespec | mEventsCPU [PROFILER_TOTAL *2] |
nvinfer1::IRuntime * | mInfer |
nvinfer1::ICudaEngine * | mEngine |
nvinfer1::IExecutionContext * | mContext |
float2 | mProfilerTimes [PROFILER_TOTAL+1] |
uint32_t | mProfilerQueriesUsed |
uint32_t | mProfilerQueriesDone |
uint32_t | mWorkspaceSize |
uint32_t | mMaxBatchSize |
bool | mEnableProfiler |
bool | mEnableDebug |
bool | mAllowGPUFallback |
void ** | mBindings |
std::vector< layerInfo > | mInputs |
std::vector< layerInfo > | mOutputs |
|
virtual |
Destory.
|
protected |
Constructor.
|
inline |
Return true if GPU fallback is enabled.
|
protected |
Configure builder options.
cudaStream_t tensorNet::CreateStream | ( | bool | nonBlocking = true | ) |
Create and use a new stream for execution.
|
static |
Detect if a particular precision is supported natively.
|
static |
Detect if a particular precision is supported natively.
|
static |
Detect the precisions supported natively on a device.
void tensorNet::EnableDebug | ( | ) |
Manually enable debug messages and synchronization.
void tensorNet::EnableLayerProfiler | ( | ) |
Manually enable layer profiling times.
|
static |
Determine the fastest native precision on a device.
|
static |
Procedurally generate a color for a given class index with the specified alpha value.
This function can be used to generate a range of colors when a colors.txt file isn't available.
|
inline |
Retrieve the device being used for execution.
|
inline |
Retrieve the dimensions of network input layer.
|
inline |
Retrieve the height of network input layer.
|
inline |
Retrieve the number of input layers to the network.
|
inline |
Get the CUDA pointer to the input layer's memory.
|
inline |
Retrieve the size (in bytes) of network input layer.
|
inline |
Retrieve the width of network input layer.
|
inline |
Retrieve the filename of the file, excluding the directory.
|
inline |
Retrieve the full path to model file, including the filename.
|
inline |
Retrieve the format of the network model.
|
inline |
Retrieve the network frames per second (FPS).
|
inline |
Retrieve the network name (it's filename).
|
inline |
Retrieve the network runtime (in milliseconds).
|
inline |
Retrieve the dimensions of network output layer.
|
inline |
Retrieve the height of network output layer.
|
inline |
Retrieve the number of output layers to the network.
|
inline |
Get the CUDA pointer to the output memory.
|
inline |
Retrieve the size (in bytes) of network output layer.
|
inline |
Retrieve the width of network output layer.
|
inline |
Retrieve the type of precision being used.
|
inline |
Retrieve the profiler runtime (in milliseconds).
|
inline |
Retrieve the profiler runtime (in milliseconds).
|
inline |
Retrieve the path to the network prototxt file.
|
inline |
Retrieve the stream that the device is operating on.
|
inline |
Return true if the model is of the specified format.
|
inline |
Check if a particular precision is being used.
|
static |
Load class colors from a text file.
If the number of expected colors aren't parsed, they will be generated. The float4 color array will automatically be allocated in shared CPU/GPU memory by cudaAllocMapped()
. If a line in the text file only has RGB, then the defaultAlpha value will be used for the alpha channel.
|
static |
Load class colors from a text file.
If the number of expected colors aren't parsed, they will be generated. The float4 color array should be expectedClasses
long, and would typically be in shared CPU/GPU memory. If a line in the text file only has RGB, then the defaultAlpha value will be used for the alpha channel.
|
static |
Load class descriptions from a label file.
Each line of the text file should include one class label (and optionally a synset). If the number of expected labels aren't parsed, they will be automatically generated.
|
static |
Load class descriptions and synset strings from a label file.
Each line of the text file should include one class label (and optionally a synset). If the number of expected labels aren't parsed, they will be automatically generated.
bool tensorNet::LoadEngine | ( | char * | engine_stream, |
size_t | engine_size, | ||
const std::vector< std::string > & | input_blobs, | ||
const std::vector< std::string > & | output_blobs, | ||
nvinfer1::IPluginFactory * | pluginFactory = NULL , |
||
deviceType | device = DEVICE_GPU , |
||
cudaStream_t | stream = NULL |
||
) |
Load a network instance from a serialized engine plan file.
engine_stream | Memory containing the serialized engine plan file. |
engine_size | Size of the serialized engine stream (in bytes). |
input_blobs | List of names of the inputs blob data to the network. |
output_blobs | List of names of the output blobs from the network. |
bool tensorNet::LoadEngine | ( | const char * | engine_filename, |
const std::vector< std::string > & | input_blobs, | ||
const std::vector< std::string > & | output_blobs, | ||
nvinfer1::IPluginFactory * | pluginFactory = NULL , |
||
deviceType | device = DEVICE_GPU , |
||
cudaStream_t | stream = NULL |
||
) |
Load a network instance from a serialized engine plan file.
engine_filename | path to the serialized engine plan file. |
input_blobs | List of names of the inputs blob data to the network. |
output_blobs | List of names of the output blobs from the network. |
bool tensorNet::LoadEngine | ( | const char * | filename, |
char ** | stream, | ||
size_t * | size | ||
) |
Load a serialized engine plan file into memory.
bool tensorNet::LoadEngine | ( | nvinfer1::ICudaEngine * | engine, |
const std::vector< std::string > & | input_blobs, | ||
const std::vector< std::string > & | output_blobs, | ||
deviceType | device = DEVICE_GPU , |
||
cudaStream_t | stream = NULL |
||
) |
Load network resources from an existing TensorRT engine instance.
engine_stream | Memory containing the serialized engine plan file. |
engine_size | Size of the serialized engine stream (in bytes). |
input_blobs | List of names of the inputs blob data to the network. |
output_blobs | List of names of the output blobs from the network. |
bool tensorNet::LoadNetwork | ( | const char * | prototxt, |
const char * | model, | ||
const char * | mean, | ||
const char * | input_blob, | ||
const Dims3 & | input_dims, | ||
const std::vector< std::string > & | output_blobs, | ||
uint32_t | maxBatchSize = DEFAULT_MAX_BATCH_SIZE , |
||
precisionType | precision = TYPE_FASTEST , |
||
deviceType | device = DEVICE_GPU , |
||
bool | allowGPUFallback = true , |
||
nvinfer1::IInt8Calibrator * | calibrator = NULL , |
||
cudaStream_t | stream = NULL |
||
) |
Load a new network instance (this variant is used for UFF models)
prototxt | File path to the deployable network prototxt |
model | File path to the caffemodel |
mean | File path to the mean value binary proto (NULL if none) |
input_blob | The name of the input blob data to the network. |
input_dims | The dimensions of the input blob (used for UFF). |
output_blobs | List of names of the output blobs from the network. |
maxBatchSize | The maximum batch size that the network will be optimized for. |
bool tensorNet::LoadNetwork | ( | const char * | prototxt, |
const char * | model, | ||
const char * | mean, | ||
const char * | input_blob, | ||
const std::vector< std::string > & | output_blobs, | ||
uint32_t | maxBatchSize = DEFAULT_MAX_BATCH_SIZE , |
||
precisionType | precision = TYPE_FASTEST , |
||
deviceType | device = DEVICE_GPU , |
||
bool | allowGPUFallback = true , |
||
nvinfer1::IInt8Calibrator * | calibrator = NULL , |
||
cudaStream_t | stream = NULL |
||
) |
Load a new network instance with multiple output layers.
prototxt | File path to the deployable network prototxt |
model | File path to the caffemodel |
mean | File path to the mean value binary proto (NULL if none) |
input_blob | The name of the input blob data to the network. |
output_blobs | List of names of the output blobs from the network. |
maxBatchSize | The maximum batch size that the network will be optimized for. |
bool tensorNet::LoadNetwork | ( | const char * | prototxt, |
const char * | model, | ||
const char * | mean, | ||
const std::vector< std::string > & | input_blobs, | ||
const std::vector< Dims3 > & | input_dims, | ||
const std::vector< std::string > & | output_blobs, | ||
uint32_t | maxBatchSize = DEFAULT_MAX_BATCH_SIZE , |
||
precisionType | precision = TYPE_FASTEST , |
||
deviceType | device = DEVICE_GPU , |
||
bool | allowGPUFallback = true , |
||
nvinfer1::IInt8Calibrator * | calibrator = NULL , |
||
cudaStream_t | stream = NULL |
||
) |
Load a new network instance with multiple input layers (used for UFF models)
prototxt | File path to the deployable network prototxt |
model | File path to the caffemodel |
mean | File path to the mean value binary proto (NULL if none) |
input_blobs | List of names of the inputs blob data to the network. |
input_dims | List of the dimensions of the input blobs (used for UFF). |
output_blobs | List of names of the output blobs from the network. |
maxBatchSize | The maximum batch size that the network will be optimized for. |
bool tensorNet::LoadNetwork | ( | const char * | prototxt, |
const char * | model, | ||
const char * | mean, | ||
const std::vector< std::string > & | input_blobs, | ||
const std::vector< std::string > & | output_blobs, | ||
uint32_t | maxBatchSize = DEFAULT_MAX_BATCH_SIZE , |
||
precisionType | precision = TYPE_FASTEST , |
||
deviceType | device = DEVICE_GPU , |
||
bool | allowGPUFallback = true , |
||
nvinfer1::IInt8Calibrator * | calibrator = NULL , |
||
cudaStream_t | stream = NULL |
||
) |
Load a new network instance with multiple input layers.
prototxt | File path to the deployable network prototxt |
model | File path to the caffemodel |
mean | File path to the mean value binary proto (NULL if none) |
input_blobs | List of names of the inputs blob data to the network. |
output_blobs | List of names of the output blobs from the network. |
maxBatchSize | The maximum batch size that the network will be optimized for. |
bool tensorNet::LoadNetwork | ( | const char * | prototxt, |
const char * | model, | ||
const char * | mean = NULL , |
||
const char * | input_blob = "data" , |
||
const char * | output_blob = "prob" , |
||
uint32_t | maxBatchSize = DEFAULT_MAX_BATCH_SIZE , |
||
precisionType | precision = TYPE_FASTEST , |
||
deviceType | device = DEVICE_GPU , |
||
bool | allowGPUFallback = true , |
||
nvinfer1::IInt8Calibrator * | calibrator = NULL , |
||
cudaStream_t | stream = NULL |
||
) |
Load a new network instance.
prototxt | File path to the deployable network prototxt |
model | File path to the caffemodel |
mean | File path to the mean value binary proto (NULL if none) |
input_blob | The name of the input blob data to the network. |
output_blob | The name of the output blob data from the network. |
maxBatchSize | The maximum batch size that the network will be optimized for. |
|
inline |
Print the profiler times (in millseconds).
|
protected |
Execute processing of the network.
sync | if true (default), the device will be synchronized after processing and the thread/function will block until processing is complete. if false, the function will return immediately after the processing has been enqueued to the CUDA stream indicated by GetStream(). |
|
protected |
Create and output an optimized network model.
deployFile | name for network prototxt |
modelFile | name for model |
outputs | network outputs |
maxBatchSize | maximum batch size |
modelStream | output model stream |
|
inlineprotected |
Begin a profiling query, before network is run.
|
inlineprotected |
End a profiling query, after the network is run.
|
inlineprotected |
Query the CUDA part of a profiler query.
|
static |
Resolve a desired precision to a specific one that's available.
void tensorNet::SetStream | ( | cudaStream_t | stream | ) |
Set the stream that the device is operating on.
|
protected |
Validate that the model already has a built TensorRT engine that exists and doesn't need updating.
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
|
protected |
#define DEFAULT_MAX_BATCH_SIZE 1 |
Default maximum batch size.
#define LOG_TRT "[TRT] " |
Prefix used for tagging printed log output from TensorRT.
#define TENSORRT_VERSION_CHECK | ( | major, | |
minor, | |||
patch | |||
) | (NV_TENSORRT_MAJOR > major || (NV_TENSORRT_MAJOR == major && NV_TENSORRT_MINOR > minor) || (NV_TENSORRT_MAJOR == major && NV_TENSORRT_MINOR == minor && NV_TENSORRT_PATCH >= patch)) |
Macro for checking the minimum version of TensorRT that is installed.
This evaluates to true if TensorRT is newer or equal to the provided version.
enum deviceType |
Enumeration for indicating the desired device that the network should run on, if available in hardware.
enum modelType |
enum precisionType |
Enumeration for indicating the desired precision that the network should run in, if available in hardware.
enum profilerDevice |
enum profilerQuery |
Profiling queries.
Enumerator | |
---|---|
PROFILER_PREPROCESS | |
PROFILER_NETWORK | |
PROFILER_POSTPROCESS | |
PROFILER_VISUALIZE | |
PROFILER_TOTAL |
deviceType deviceTypeFromStr | ( | const char * | str | ) |
Parse the device type from a string.
const char* deviceTypeToStr | ( | deviceType | type | ) |
Stringize function that returns deviceType in text.
modelType modelTypeFromPath | ( | const char * | path | ) |
Parse the model format from a file path.
modelType modelTypeFromStr | ( | const char * | str | ) |
Parse the model format from a string.
const char* modelTypeToStr | ( | modelType | type | ) |
Stringize function that returns modelType in text.
precisionType precisionTypeFromStr | ( | const char * | str | ) |
Parse the precision type from a string.
const char* precisionTypeToStr | ( | precisionType | type | ) |
Stringize function that returns precisionType in text.
const char* profilerQueryToStr | ( | profilerQuery | query | ) |
Stringize function that returns profilerQuery in text.