|
NVIDIA DeepStream SDK API Reference
|
7.1 Release
|
Go to the documentation of this file.
19 #ifndef __NVDSINFER_TRTIS_UTILS_H__
20 #define __NVDSINFER_TRTIS_UTILS_H__
32 #include "model_config.pb.h"
40 #define CHECK_TRTIS_ERR_W_ACTION(trtisExpr, action, fmt, ...) \
42 UniqTritonT<TRITONSERVER_Error> errPtr( \
43 (trtisExpr), TRITONSERVER_ErrorDelete); \
46 "Triton: " fmt ", triton_err_str:%s, err_msg:%s", \
47 ##__VA_ARGS__, TRITONSERVER_ErrorCodeString(errPtr.get()), \
48 TRITONSERVER_ErrorMessage(errPtr.get())); \
57 #define RETURN_TRTIS_ERROR(trtisExpr, fmt, ...) \
58 CHECK_TRTIS_ERR_W_ACTION(trtisExpr, return NVDSINFER_TRITON_ERROR, fmt, ##__VA_ARGS__)
64 #define CONTINUE_TRTIS_ERROR(trtisExpr, fmt, ...) \
65 CHECK_TRTIS_ERR_W_ACTION(trtisExpr, , fmt, ##__VA_ARGS__)
67 namespace ni = inference;
129 template <
typename VecDims>
136 for (
const auto &v : shape) {
This is a header file for pre-processing cuda kernels with normalization and mean subtraction require...
InferMemType MemTypeFromTriton(TRITONSERVER_MemoryType type)
Maps the TRITONSERVER_MemoryType to the InferMemType.
InferDataType
Datatype of the tensor buffer.
InferDataType DataTypeFromTritonPb(ni::DataType type)
Maps the data type from Triton model configuration proto definition to InferDataType.
Header file for the data types used in the inference processing.
InferTensorOrder
The type of tensor order.
enum TRITONSERVER_memorytype_enum TRITONSERVER_MemoryType
TRITONSERVER_MemoryType.
TRITONSERVER_DataType DataTypeToTriton(InferDataType type)
Maps the InferDataType to TRITONSERVER_DataType.
void normalizeDims(InferDims &dims)
InferDataType DataTypeFromTriton(TRITONSERVER_DataType type)
Maps the TRITONSERVER_DataType to the InferDataType.
Header file containing utility functions and classes used by the nvinferserver low level library.
const char * TritonControlModeToStr(int32_t mode)
Returns a string describing the TRITONSERVER_ModelControlMode: none, explicit or poll.
Header file of the common declarations for the nvinferserver library.
InferDims DimsFromTriton(const VecDims &shape)
Converts the input shape vector from Triton to InferDims type.
#define NVDSINFER_MAX_DIMS
enum TRITONSERVER_datatype_enum TRITONSERVER_DataType
TRITONSERVER_DataType.
InferMemType
The memory types of inference buffers.
Holds the information about the dimensions of a neural network layer.
bool hasWildcard(const InferDims &dims)
Check if any of the InferDims dimensions are of dynamic size (-1 or negative values).
InferTensorOrder TensorOrderFromTritonPb(ni::ModelInput::Format order)
Maps the tensor order from Triton model configuration proto definition to the InferTensorOrder type.
InferTensorOrder TensorOrderFromTritonMeta(const std::string &format)
Maps the tensor order from Triton metadata string to the InferTensorOrder type.
TRITONSERVER_MemoryType MemTypeToTriton(InferMemType type)
Maps the InferMemType to the TRITONSERVER_MemoryType.