DNN.h

Go to the documentation of this file.

 
//
// Notice
// ALL NVIDIA DESIGN SPECIFICATIONS AND CODE ("MATERIALS") ARE PROVIDED "AS IS" NVIDIA MAKES
// NO REPRESENTATIONS, WARRANTIES, EXPRESSED, IMPLIED, STATUTORY, OR OTHERWISE WITH RESPECT TO
// THE MATERIALS, AND EXPRESSLY DISCLAIMS ANY IMPLIED WARRANTIES OF NONINFRINGEMENT,
// MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
//
// NVIDIA CORPORATION & AFFILIATES assumes no responsibility for the consequences of use of such
// information or for any infringement of patents or other rights of third parties that may
// result from its use. No license is granted by implication or otherwise under any patent
// or patent rights of NVIDIA CORPORATION & AFFILIATES. No third party distribution is allowed unless
// expressly authorized by NVIDIA. Details are subject to change without notice.
// This code supersedes and replaces all information previously supplied.
// NVIDIA CORPORATION & AFFILIATES products are not authorized for use as critical
// components in life support devices or systems without express written approval of
// NVIDIA CORPORATION & AFFILIATES.
//
// SPDX-FileCopyrightText: Copyright (c) 2016-2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
// SPDX-License-Identifier: LicenseRef-NvidiaProprietary
//
// NVIDIA CORPORATION, its affiliates and licensors retain all intellectual
// property and proprietary rights in and to this material, related
// documentation and any modifications thereto. Any use, reproduction,
// disclosure or distribution of this material and related documentation
// without an express license agreement from NVIDIA CORPORATION or
// its affiliates is strictly prohibited.
//
 
#ifndef DW_DNN_H_
#define DW_DNN_H_
 
#include <dw/dnn/DataConditioner.h>
#include <dw/core/base/Config.h>
#include <dw/core/base/Status.h>
#include <dw/core/context/Context.h>
#include <dw/dnn/tensor/Tensor.h>
#include <driver_types.h>
 
#ifdef __cplusplus
extern "C" {
#endif
 
typedef struct dwDNNObject* dwDNNHandle_t;
typedef struct dwDNNObject const* dwConstDNNHandle_t;
 
typedef struct
{
    dwDataConditionerParams dataConditionerParams; 
} dwDNNMetaData;
 
typedef struct
{
    const char8_t* pluginLibraryPath; 
    const char8_t* layerName;         
} dwDNNCustomLayer;
 
typedef struct
{
    const dwDNNCustomLayer* customLayers; 
    size_t numCustomLayers;               
} dwDNNPluginConfiguration;
 
DW_API_PUBLIC
dwStatus dwDNN_initializeTensorRTFromFile(dwDNNHandle_t* const network, const char8_t* const modelFilename,
                                          const dwDNNPluginConfiguration* const pluginConfiguration,
                                          dwProcessorType const processorType, dwContextHandle_t const context);
 
DW_API_PUBLIC
dwStatus dwDNN_initializeTensorRTFromFileWithEngineId(dwDNNHandle_t* const network, const char8_t* const modelFilename,
                                                      const dwDNNPluginConfiguration* const pluginConfiguration,
                                                      dwProcessorType const processorType, uint32_t engineId,
                                                      dwContextHandle_t const context);
 
DW_API_PUBLIC
dwStatus dwDNN_initializeTensorRTFromMemory(dwDNNHandle_t* const network,
                                            const char8_t* const modelContent,
                                            uint32_t const modelContentSize,
                                            const dwDNNPluginConfiguration* const pluginConfiguration,
                                            dwProcessorType const processorType, dwContextHandle_t const context);
 
DW_API_PUBLIC
dwStatus dwDNN_initializeTensorRTFromMemoryWithEngineId(dwDNNHandle_t* const network,
                                                        const char8_t* const modelContent,
                                                        uint32_t const modelContentSize,
                                                        const dwDNNPluginConfiguration* const pluginConfiguration,
                                                        dwProcessorType const processorType, uint32_t engineId,
                                                        dwContextHandle_t const context);
DW_API_PUBLIC
dwStatus dwDNN_reset(dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_release(dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_inferSIO(float32_t* const dOutput, const float32_t* const dInput, uint32_t const batchsize,
                        dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_inferRaw(float32_t* const* const dOutput, const float32_t* const* const dInput,
                        uint32_t const batchsize, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_setCUDAStream(cudaStream_t const stream, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getCUDAStream(cudaStream_t* const stream, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getInputSize(dwBlobSize* const blobSize, uint32_t const blobIndex, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getOutputSize(dwBlobSize* const blobSize, uint32_t const blobIndex, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getInputTensorProperties(dwDNNTensorProperties* const tensorProps, uint32_t const blobIndex, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getOutputTensorProperties(dwDNNTensorProperties* const tensorProps, uint32_t const blobIndex, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getInputBlobCount(uint32_t* const count, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getOutputBlobCount(uint32_t* const count, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getInputIndex(uint32_t* const blobIndex, const char8_t* const blobName, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getOutputIndex(uint32_t* const blobIndex, const char8_t* const blobName, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_getMetaData(dwDNNMetaData* const metaData, dwDNNHandle_t const network);
 
DW_API_PUBLIC
dwStatus dwDNN_infer(dwDNNTensorHandle_t* const outputTensors, uint32_t const outputTensorCount,
                     dwConstDNNTensorHandle_t* const inputTensors, uint32_t const inputTensorCount, dwDNNHandle_t const network);
 
#ifdef __cplusplus
}
#endif
#endif // DW_DNN_H_