“IRuntime”: 未声明的标识符

x33g5p2x  于2022-07-26 转载在 其他  
字(9.1k)|赞(0)|评价(0)|浏览(351)

“IRuntime”: 未声明的标识符

完整用法:

TensorRT 系列 (1)模型推理_洪流之源的博客-CSDN博客_tensorrt 推理

// tensorRT include
#include <NvInfer.h>
#include <NvInferRuntime.h>
 
// cuda include
#include <cuda_runtime.h>
 
// system include
#include <stdio.h>
#include <math.h>
 
#include <iostream>
#include <fstream>
#include <vector>
 
using namespace std;
// 上一节的代码
 
class TRTLogger : public nvinfer1::ILogger
{
public:
    virtual void log(Severity severity, nvinfer1::AsciiChar const* msg) noexcept override
    {
        if(severity <= Severity::kINFO)
        {
            printf("%d: %s\n", severity, msg);
        }
    }
} logger;
 
nvinfer1::Weights make_weights(float* ptr, int n)
{
    nvinfer1::Weights w;
    w.count = n;
    w.type = nvinfer1::DataType::kFLOAT;
    w.values = ptr;
    return w;
}
 
 
bool build_model()
{
    TRTLogger logger;
 
    // 这是基本需要的组件
    nvinfer1::IBuilder* builder = nvinfer1::createInferBuilder(logger);
    nvinfer1::IBuilderConfig* config = builder->createBuilderConfig();
    nvinfer1::INetworkDefinition* network = builder->createNetworkV2(1);
 
    // 构建一个模型
    /*
        Network definition:
        image
          |
        linear (fully connected)  input = 3, output = 2, bias = True     w=[[1.0, 2.0, 0.5], [0.1, 0.2, 0.5]], b=[0.3, 0.8]
          |
        sigmoid
          |
        prob
    */
 
    const int num_input = 3;
    const int num_output = 2;
    float layer1_weight_values[] = {1.0, 2.0, 0.5, 0.1, 0.2, 0.5};
    float layer1_bias_values[]   = {0.3, 0.8};
 
    nvinfer1::ITensor* input = network->addInput("image", nvinfer1::DataType::kFLOAT, nvinfer1::Dims4(1, num_input, 1, 1));
    nvinfer1::Weights layer1_weight = make_weights(layer1_weight_values, 6);
    nvinfer1::Weights layer1_bias   = make_weights(layer1_bias_values, 2);
    auto layer1 = network->addFullyConnected(*input, num_output, layer1_weight, layer1_bias);
    auto prob = network->addActivation(*layer1->getOutput(0), nvinfer1::ActivationType::kSIGMOID);
    
    // 将我们需要的prob标记为输出
    network->markOutput(*prob->getOutput(0));
 
    printf("Workspace Size = %.2f MB\n", (1 << 28) / 1024.0f / 1024.0f);
    config->setMaxWorkspaceSize(1 << 28);
    builder->setMaxBatchSize(1);
 
    nvinfer1::ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config);
    if(engine == nullptr)
    {
        printf("Build engine failed.\n");
        return false;
    }
 
    // 将模型序列化,并储存为文件
    nvinfer1::IHostMemory* model_data = engine->serialize();
    FILE* f = fopen("engine.trtmodel", "wb");
    fwrite(model_data->data(), 1, model_data->size(), f);
    fclose(f);
 
    // 卸载顺序按照构建顺序倒序
    model_data->destroy();
    engine->destroy();
    network->destroy();
    config->destroy();
    builder->destroy();
    printf("Done.\n");
    return true;
}
 
 
 
vector<unsigned char> load_file(const string& file)
{
    ifstream in(file, ios::in | ios::binary);
    if (!in.is_open())
        return {};
 
    in.seekg(0, ios::end);
    size_t length = in.tellg();
 
    std::vector<uint8_t> data;
    if (length > 0){
        in.seekg(0, ios::beg);
        data.resize(length);
 
        in.read((char*)&data[0], length);
    }
    in.close();
    return data;
}
 
void inference(){
 
    // ------------------------------ 1. 准备模型并加载   ----------------------------
    TRTLogger logger;
    auto engine_data = load_file("engine.trtmodel");
    // 执行推理前,需要创建一个推理的runtime接口实例。与builer一样,runtime需要logger:
    nvinfer1::IRuntime* runtime   = nvinfer1::createInferRuntime(logger);
    // 将模型从读取到engine_data中,则可以对其进行反序列化以获得engine
    nvinfer1::ICudaEngine* engine = runtime->deserializeCudaEngine(engine_data.data(), engine_data.size());
    if(engine == nullptr){
        printf("Deserialize cuda engine failed.\n");
        runtime->destroy();
        return;
    }
 
    nvinfer1::IExecutionContext* execution_context = engine->createExecutionContext();
    cudaStream_t stream = nullptr;
    // 创建CUDA流,以确定这个batch的推理是独立的
    cudaStreamCreate(&stream);
 
    /*
        Network definition:
        image
          |
        linear (fully connected)  input = 3, output = 2, bias = True     w=[[1.0, 2.0, 0.5], [0.1, 0.2, 0.5]], b=[0.3, 0.8]
          |
        sigmoid
          |
        prob
    */
 
    // ------------------------------ 2. 准备好要推理的数据并搬运到GPU   ----------------------------
    float input_data_host[] = {1, 2, 3};
    float* input_data_device = nullptr;
 
    float output_data_host[2];
    float* output_data_device = nullptr;
    cudaMalloc(&input_data_device, sizeof(input_data_host));
    cudaMalloc(&output_data_device, sizeof(output_data_host));
    cudaMemcpyAsync(input_data_device, input_data_host, sizeof(input_data_host), cudaMemcpyHostToDevice, stream);
 
    // 用一个指针数组指定input和output在gpu中的指针。
    float* bindings[] = {input_data_device, output_data_device};
 
    // ------------------------------ 3. 推理并将结果搬运回CPU   ----------------------------
    bool success = execution_context->enqueueV2((void**)bindings, stream, nullptr);
    cudaMemcpyAsync(output_data_host, output_data_device, sizeof(output_data_host), cudaMemcpyDeviceToHost, stream);
    cudaStreamSynchronize(stream);
 
    printf("output_data_host = %f, %f\n", output_data_host[0], output_data_host[1]);
 
    // ------------------------------ 4. 释放内存 ----------------------------
    printf("Clean memory\n");
    cudaStreamDestroy(stream);
    execution_context->destroy();
    engine->destroy();
    runtime->destroy();
 
    // ------------------------------ 5. 手动推理进行验证 ----------------------------
    const int num_input = 3;
    const int num_output = 2;
    float layer1_weight_values[] = {1.0, 2.0, 0.5, 0.1, 0.2, 0.5};
    float layer1_bias_values[]   = {0.3, 0.8};
 
    printf("手动验证计算结果:\n");
    for(int io = 0; io < num_output; ++io)
    {
        float output_host = layer1_bias_values[io];
        for(int ii = 0; ii < num_input; ++ii)
        {
            output_host += layer1_weight_values[io * num_input + ii] * input_data_host[ii];
        }
 
        // sigmoid
        float prob = 1 / (1 + exp(-output_host));
        printf("output_prob[%d] = %f\n", io, prob);
    }
}
 
int main()
{
 
    if(!build_model())
    {
        return -1;
    }
    inference();
    return 0;
}

原文链接:https://blog.csdn.net/weicao1990/article/details/125034572

makefile:

cc        := g++
name      := pro
workdir   := workspace
srcdir    := src
objdir    := objs
stdcpp    := c++11
cuda_home := /home/liuhongyuan/miniconda3/envs/trtpy/lib/python3.8/site-packages/trtpy/trt8cuda112cudnn8
syslib    := /home/liuhongyuan/miniconda3/envs/trtpy/lib/python3.8/site-packages/trtpy/lib
cpp_pkg   := /home/liuhongyuan/miniconda3/envs/trtpy/lib/python3.8/site-packages/trtpy/cpp-packages
cuda_arch := 
nvcc      := $(cuda_home)/bin/nvcc -ccbin=$(cc)
 
# 定义cpp的路径查找和依赖项mk文件
cpp_srcs := $(shell find $(srcdir) -name "*.cpp")
cpp_objs := $(cpp_srcs:.cpp=.cpp.o)
cpp_objs := $(cpp_objs:$(srcdir)/%=$(objdir)/%)
cpp_mk   := $(cpp_objs:.cpp.o=.cpp.mk)
 
# 定义cu文件的路径查找和依赖项mk文件
cu_srcs := $(shell find $(srcdir) -name "*.cu")
cu_objs := $(cu_srcs:.cu=.cu.o)
cu_objs := $(cu_objs:$(srcdir)/%=$(objdir)/%)
cu_mk   := $(cu_objs:.cu.o=.cu.mk)
 
# 定义opencv和cuda需要用到的库文件
link_cuda      := cudart cudnn
link_trtpro    := 
link_tensorRT  := nvinfer
link_opencv    := 
link_sys       := stdc++ dl
link_librarys  := $(link_cuda) $(link_tensorRT) $(link_sys) $(link_opencv)
 
# 定义头文件路径,请注意斜杠后边不能有空格
# 只需要写路径,不需要写-I
include_paths := src              \
    $(cuda_home)/include/cuda     \
	$(cuda_home)/include/tensorRT \
	$(cpp_pkg)/opencv4.2/include
 
# 定义库文件路径,只需要写路径,不需要写-L
library_paths := $(cuda_home)/lib64 $(syslib) $(cpp_pkg)/opencv4.2/lib
 
# 把library path给拼接为一个字符串,例如a b c => a:b:c
# 然后使得LD_LIBRARY_PATH=a:b:c
empty := 
library_path_export := $(subst $(empty) $(empty),:,$(library_paths))
 
# 把库路径和头文件路径拼接起来成一个,批量自动加-I、-L、-l
run_paths     := $(foreach item,$(library_paths),-Wl,-rpath=$(item))
include_paths := $(foreach item,$(include_paths),-I$(item))
library_paths := $(foreach item,$(library_paths),-L$(item))
link_librarys := $(foreach item,$(link_librarys),-l$(item))
 
# 如果是其他显卡,请修改-gencode=arch=compute_75,code=sm_75为对应显卡的能力
# 显卡对应的号码参考这里:https://developer.nvidia.com/zh-cn/cuda-gpus#compute
# 如果是 jetson nano,提示找不到-m64指令,请删掉 -m64选项。不影响结果
cpp_compile_flags := -std=$(stdcpp) -w -g -O0 -m64 -fPIC -fopenmp -pthread
cu_compile_flags  := -std=$(stdcpp) -w -g -O0 -m64 $(cuda_arch) -Xcompiler "$(cpp_compile_flags)"
link_flags        := -pthread -fopenmp -Wl,-rpath='$$ORIGIN'
 
cpp_compile_flags += $(include_paths)
cu_compile_flags  += $(include_paths)
link_flags        += $(library_paths) $(link_librarys) $(run_paths)
 
# 如果头文件修改了,这里的指令可以让他自动编译依赖的cpp或者cu文件
ifneq ($(MAKECMDGOALS), clean)
-include $(cpp_mk) $(cu_mk)
endif
 
$(name)   : $(workdir)/$(name)
 
all       : $(name)
run       : $(name)
	@cd $(workdir) && ./$(name) $(run_args)
 
$(workdir)/$(name) : $(cpp_objs) $(cu_objs)
	@echo Link $@
	@mkdir -p $(dir $@)
	@$(cc) $^ -o $@ $(link_flags)
 
$(objdir)/%.cpp.o : $(srcdir)/%.cpp
	@echo Compile CXX $<
	@mkdir -p $(dir $@)
	@$(cc) -c $< -o $@ $(cpp_compile_flags)
 
$(objdir)/%.cu.o : $(srcdir)/%.cu
	@echo Compile CUDA $<
	@mkdir -p $(dir $@)
	@$(nvcc) -c $< -o $@ $(cu_compile_flags)
 
# 编译cpp依赖项,生成mk文件
$(objdir)/%.cpp.mk : $(srcdir)/%.cpp
	@echo Compile depends C++ $<
	@mkdir -p $(dir $@)
	@$(cc) -M $< -MF $@ -MT $(@:.cpp.mk=.cpp.o) $(cpp_compile_flags)
    
# 编译cu文件的依赖项,生成cumk文件
$(objdir)/%.cu.mk : $(srcdir)/%.cu
	@echo Compile depends CUDA $<
	@mkdir -p $(dir $@)
	@$(nvcc) -M $< -MF $@ -MT $(@:.cu.mk=.cu.o) $(cu_compile_flags)
 
# 定义清理指令
clean :
	@rm -rf $(objdir) $(workdir)/$(name) $(workdir)/*.trtmodel
 
# 防止符号被当做文件
.PHONY : clean run $(name)
 
# 导出依赖库路径,使得能够运行起来
export LD_LIBRARY_PATH:=$(library_path_export)

原文链接:https://blog.csdn.net/weicao1990/article/details/125034572

重点提炼:

  1. 必须使用createNetworkV2,并指定为1(表示显性batch),createNetwork已经废弃,非显性batch官方不推荐,这个方式直接影响推理时enqueue还是enqueueV2;

  2. builder、config等指针,记得释放,否则会有内存泄漏,使用ptr->destroy()释放;

  3. markOutput表示是该模型的输出节点,mark几次,就有几个输出,addInput几次就有几个输入;

  4. workspaceSize是工作空间大小,某些layer需要使用额外存储时,不会自己分配空间,而是为了内存复用,直接找tensorRT要workspace空间;

  5. 一定要记住,保存的模型只能适配编译时的trt版本、编译时指定的设备,也只能保证在这种配置下是最优的。如果用trt跨不同设备执行,有时候可以运行,但不是最优的,也不推荐;

  6. bindings是tensorRT对输入输出张量的描述,bindings = input-tensor + output-tensor。比如input有a,output有b, c, d,那么bindings = [a, b, c, d],bindings[0] = a,bindings[2] = c;

  7. enqueueV2是异步推理,加入到stream队列等待执行。输入的bindings则是tensors的指针(注意是device pointer);

  8. createExecutionContext可以执行多次,允许一个引擎具有多个执行上下文。
    ————————————————
    版权声明:本文为CSDN博主「洪流之源」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
    原文链接:https://blog.csdn.net/weicao1990/article/details/125034572

相关文章