Skip to content

GitLab

Commit 0ed76f01 authored by liucong's avatar liucong
Browse files

重新进行Cpp代码格式化

parent 061ca3e8
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 980 additions and 919 deletions
Src/Classifier.cpp
View file @ 0ed76f01
......@@ -12,23 +12,17 @@
namespace migraphxSamples
{
Classifier::Classifier()
{
}
Classifier::Classifier() {}
Classifier::~Classifier()
{
configurationFile.release();
}
Classifier::~Classifier() { configurationFile.release(); }
cv::Mat Classifier::Preprocess(const std::vector<cv::Mat> &srcImages)
cv::Mat Classifier::Preprocess(const std::vector<cv::Mat>& srcImages)
{
// 数据预处理
std::vector<cv::Mat> image;
for(int i =0;i<srcImages.size();++i)
for(int i = 0; i < srcImages.size(); ++i)
{
//BGR转换为RGB
// BGR转换为RGB
cv::Mat imgRGB;
cv::cvtColor(srcImages[i], imgRGB, cv::COLOR_BGR2RGB);
......@@ -45,8 +39,8 @@ cv::Mat Classifier::Preprocess(const std::vector<cv::Mat> &srcImages)
}
// 裁剪中心窗口为224*224
int start_x = shrink.cols/2 - 224/2;
int start_y = shrink.rows/2 - 224/2;
int start_x = shrink.cols / 2 - 224 / 2;
int start_y = shrink.rows / 2 - 224 / 2;
cv::Rect rect(start_x, start_y, 224, 224);
cv::Mat images = shrink(rect);
image.push_back(images);
......@@ -55,17 +49,18 @@ cv::Mat Classifier::Preprocess(const std::vector<cv::Mat> &srcImages)
// normalize并转换为NCHW
cv::Mat inputBlob;
Image2BlobParams image2BlobParams;
image2BlobParams.scalefactor=cv::Scalar(1/58.395, 1/57.12, 1/57.375);
image2BlobParams.mean=cv::Scalar(123.675, 116.28, 103.53);
image2BlobParams.swapRB=false;
blobFromImagesWithParams(image,inputBlob,image2BlobParams);
image2BlobParams.scalefactor = cv::Scalar(1 / 58.395, 1 / 57.12, 1 / 57.375);
image2BlobParams.mean = cv::Scalar(123.675, 116.28, 103.53);
image2BlobParams.swapRB = false;
blobFromImagesWithParams(image, inputBlob, image2BlobParams);
return inputBlob;
}
ErrorCode Classifier::Initialize(InitializationParameterOfClassifier initializationParameterOfClassifier)
ErrorCode
Classifier::Initialize(InitializationParameterOfClassifier initializationParameterOfClassifier)
{
// 读取配置文件
std::string configFilePath=initializationParameterOfClassifier.configFilePath;
std::string configFilePath = initializationParameterOfClassifier.configFilePath;
if(!Exists(configFilePath))
{
LOG_ERROR(stdout, "no configuration file!\n");
......@@ -73,39 +68,39 @@ ErrorCode Classifier::Initialize(InitializationParameterOfClassifier initializat
}
if(!configurationFile.open(configFilePath, cv::FileStorage::READ))
{
LOG_ERROR(stdout, "fail to open configuration file\n");
return FAIL_TO_OPEN_CONFIG_FILE;
LOG_ERROR(stdout, "fail to open configuration file\n");
return FAIL_TO_OPEN_CONFIG_FILE;
}
LOG_INFO(stdout, "succeed to open configuration file\n");
// 获取配置文件参数
cv::FileNode netNode = configurationFile["Classifier"];
std::string modelPath=(std::string)netNode["ModelPath"];
useInt8=(bool)(int)netNode["UseInt8"];
useFP16=(bool)(int)netNode["UseFP16"];
useoffloadcopy=(bool)(int)netNode["Useoffloadcopy"];
cv::FileNode netNode = configurationFile["Classifier"];
std::string modelPath = (std::string)netNode["ModelPath"];
useInt8 = (bool)(int)netNode["UseInt8"];
useFP16 = (bool)(int)netNode["UseFP16"];
useoffloadcopy = (bool)(int)netNode["Useoffloadcopy"];
// 加载模型
if(!Exists(modelPath))
{
LOG_ERROR(stdout,"%s not exist!\n",modelPath.c_str());
LOG_ERROR(stdout, "%s not exist!\n", modelPath.c_str());
return MODEL_NOT_EXIST;
}
net = migraphx::parse_onnx(modelPath);
LOG_INFO(stdout,"succeed to load model: %s\n",GetFileName(modelPath).c_str());
LOG_INFO(stdout, "succeed to load model: %s\n", GetFileName(modelPath).c_str());
// 获取模型输入/输出节点信息
std::unordered_map<std::string, migraphx::shape> inputs=net.get_inputs();
std::unordered_map<std::string, migraphx::shape> outputs=net.get_outputs();
inputName=inputs.begin()->first;
inputShape=inputs.begin()->second;
outputName=outputs.begin()->first;
outputShape=outputs.begin()->second;
int N=inputShape.lens()[0];
int C=inputShape.lens()[1];
int H=inputShape.lens()[2];
int W=inputShape.lens()[3];
inputSize=cv::Size(W,H);
std::unordered_map<std::string, migraphx::shape> inputs = net.get_inputs();
std::unordered_map<std::string, migraphx::shape> outputs = net.get_outputs();
inputName = inputs.begin()->first;
inputShape = inputs.begin()->second;
outputName = outputs.begin()->first;
outputShape = outputs.begin()->second;
int N = inputShape.lens()[0];
int C = inputShape.lens()[1];
int H = inputShape.lens()[2];
int W = inputShape.lens()[3];
inputSize = cv::Size(W, H);
// 设置模型为GPU模式
migraphx::target gpuTarget = migraphx::gpu::target{};
......@@ -114,9 +109,9 @@ ErrorCode Classifier::Initialize(InitializationParameterOfClassifier initializat
if(useInt8)
{
// 创建量化校准数据,建议使用测试集中的多张典型图像
cv::Mat srcImage=cv::imread("../Resource/Images/ImageNet_test.jpg",1);
cv::Mat srcImage = cv::imread("../Resource/Images/ImageNet_test.jpg", 1);
std::vector<cv::Mat> srcImages;
for(int i=0;i<inputShape.lens()[0];++i)
for(int i = 0; i < inputShape.lens()[0]; ++i)
{
srcImages.push_back(srcImage);
}
......@@ -124,8 +119,9 @@ ErrorCode Classifier::Initialize(InitializationParameterOfClassifier initializat
// 数据预处理
cv::Mat inputBlob = Preprocess(srcImages);
std::unordered_map<std::string, migraphx::argument> inputData;
inputData[inputName]= migraphx::argument{inputShape, (float*)inputBlob.data};
std::vector<std::unordered_map<std::string, migraphx::argument>> calibrationData = {inputData};
inputData[inputName] = migraphx::argument{inputShape, (float*)inputBlob.data};
std::vector<std::unordered_map<std::string, migraphx::argument>> calibrationData = {
inputData};
// INT8量化
migraphx::quantize_int8(net, gpuTarget, calibrationData);
......@@ -137,66 +133,67 @@ ErrorCode Classifier::Initialize(InitializationParameterOfClassifier initializat
// 编译模型
migraphx::compile_options options;
options.device_id=0; // 设置GPU设备，默认为0号设备
options.device_id = 0; // 设置GPU设备，默认为0号设备
if(useoffloadcopy)
{
options.offload_copy=true;
options.offload_copy = true;
}
else
{
options.offload_copy=false;
options.offload_copy = false;
}
net.compile(gpuTarget,options);
LOG_INFO(stdout,"succeed to compile model: %s\n",GetFileName(modelPath).c_str());
net.compile(gpuTarget, options);
LOG_INFO(stdout, "succeed to compile model: %s\n", GetFileName(modelPath).c_str());
// offloadcopy为false的时候，分配输入和输出内存
if(!useoffloadcopy)
{
// 分配device输入内存
inputBuffer_Device=nullptr;
inputBuffer_Device = nullptr;
hipMalloc(&inputBuffer_Device, inputShape.bytes());
programParameters[inputName] = migraphx::argument{inputShape, inputBuffer_Device};
// 分配device和host输出内存
outputBuffer_Device=nullptr;
outputBuffer_Device = nullptr;
hipMalloc(&outputBuffer_Device, outputShape.bytes());
programParameters[outputName] = migraphx::argument{outputShape, outputBuffer_Device};
outputBuffer_Host=nullptr; // host内存
outputBuffer_Host=malloc(outputShape.bytes());
outputBuffer_Host = nullptr; // host内存
outputBuffer_Host = malloc(outputShape.bytes());
}
// warm up
if(useoffloadcopy)
{
std::unordered_map<std::string, migraphx::argument> inputData;
inputData[inputName]=migraphx::argument{inputShape};
inputData[inputName] = migraphx::argument{inputShape};
net.eval(inputData);
}
else
{
migraphx::argument inputData= migraphx::argument{inputShape};
migraphx::argument inputData = migraphx::argument{inputShape};
hipMemcpy(inputBuffer_Device, inputData.data(), inputShape.bytes(), hipMemcpyHostToDevice);
net.eval(programParameters);
}
// log
LOG_INFO(stdout,"InputSize:%dx%d\n",inputSize.width,inputSize.height);
LOG_INFO(stdout,"InputName:%s\n",inputName.c_str());
LOG_INFO(stdout,"UseInt8:%d\n",(int)useInt8);
LOG_INFO(stdout,"UseFP16:%d\n",(int)useFP16);
LOG_INFO(stdout,"Useoffloadcopy:%d\n",(int)useoffloadcopy);
LOG_INFO(stdout, "InputSize:%dx%d\n", inputSize.width, inputSize.height);
LOG_INFO(stdout, "InputName:%s\n", inputName.c_str());
LOG_INFO(stdout, "UseInt8:%d\n", (int)useInt8);
LOG_INFO(stdout, "UseFP16:%d\n", (int)useFP16);
LOG_INFO(stdout, "Useoffloadcopy:%d\n", (int)useoffloadcopy);
return SUCCESS;
}
ErrorCode Classifier::Classify(const std::vector<cv::Mat> &srcImages,std::vector<std::vector<ResultOfPrediction>> &predictions)
ErrorCode Classifier::Classify(const std::vector<cv::Mat>& srcImages,
std::vector<std::vector<ResultOfPrediction>>& predictions)
{
if(srcImages.size()==0||srcImages[0].empty()||srcImages[0].depth()!=CV_8U)
if(srcImages.size() == 0 || srcImages[0].empty() || srcImages[0].depth() != CV_8U)
{
LOG_ERROR(stdout, "image error!\n");
return IMAGE_ERROR;
}
// 数据预处理
cv::Mat inputBlob = Preprocess(srcImages);
......@@ -204,36 +201,37 @@ ErrorCode Classifier::Classify(const std::vector<cv::Mat> &srcImages,std::vector
if(useoffloadcopy)
{
std::unordered_map<std::string, migraphx::argument> inputData;
inputData[inputName]= migraphx::argument{inputShape, (float*)inputBlob.data};
inputData[inputName] = migraphx::argument{inputShape, (float*)inputBlob.data};
// 推理
std::vector<migraphx::argument> results = net.eval(inputData);
// 获取输出节点的属性
migraphx::argument result = results[0]; // 获取第一个输出节点的数据
migraphx::shape outputShapes=result.get_shape(); // 输出节点的shape
std::vector<std::size_t> outputSize=outputShapes.lens(); // 每一维大小，维度顺序为(N,C,H,W)
int numberOfOutput=outputShapes.elements(); // 输出节点元素的个数
float *logits=(float *)result.data(); // 输出节点数据指针
migraphx::argument result = results[0]; // 获取第一个输出节点的数据
migraphx::shape outputShapes = result.get_shape(); // 输出节点的shape
std::vector<std::size_t> outputSize =
outputShapes.lens(); // 每一维大小，维度顺序为(N,C,H,W)
int numberOfOutput = outputShapes.elements(); // 输出节点元素的个数
float* logits = (float*)result.data(); // 输出节点数据指针
// 获取每张图像的预测结果
int numberOfClasses=numberOfOutput/srcImages.size();
for(int i=0;i<srcImages.size();++i)
int numberOfClasses = numberOfOutput / srcImages.size();
for(int i = 0; i < srcImages.size(); ++i)
{
int startIndex=numberOfClasses*i;
int startIndex = numberOfClasses * i;
std::vector<float> logit;
for(int j=0;j<numberOfClasses;++j)
for(int j = 0; j < numberOfClasses; ++j)
{
logit.push_back(logits[startIndex+j]);
logit.push_back(logits[startIndex + j]);
}
std::vector<ResultOfPrediction> resultOfPredictions;
for(int j=0;j<numberOfClasses;++j)
for(int j = 0; j < numberOfClasses; ++j)
{
ResultOfPrediction prediction;
prediction.label=j;
prediction.confidence=logit[j];
prediction.label = j;
prediction.confidence = logit[j];
resultOfPredictions.push_back(prediction);
}
......@@ -241,7 +239,7 @@ ErrorCode Classifier::Classify(const std::vector<cv::Mat> &srcImages,std::vector
predictions.push_back(resultOfPredictions);
}
}
else // 当offload为false时，需要内存拷贝
else // 当offload为false时，需要内存拷贝
{
migraphx::argument inputData = migraphx::argument{inputShape, (float*)inputBlob.data};
......@@ -253,31 +251,35 @@ ErrorCode Classifier::Classify(const std::vector<cv::Mat> &srcImages,std::vector
std::vector<migraphx::argument> results = net.eval(programParameters);
// 获取输出节点的属性
migraphx::argument result = results[0]; // 获取第一个输出节点的数据
migraphx::shape outputShapes=result.get_shape(); // 输出节点的shape
std::vector<std::size_t> outputSize=outputShapes.lens(); // 每一维大小，维度顺序为(N,C,H,W)
int numberOfOutput=outputShapes.elements(); // 输出节点元素的个数
migraphx::argument result = results[0]; // 获取第一个输出节点的数据
migraphx::shape outputShapes = result.get_shape(); // 输出节点的shape
std::vector<std::size_t> outputSize =
outputShapes.lens(); // 每一维大小，维度顺序为(N,C,H,W)
int numberOfOutput = outputShapes.elements(); // 输出节点元素的个数
// 将device输出数据拷贝到分配好的host输出内存
hipMemcpy(outputBuffer_Host, outputBuffer_Device, outputShapes.bytes(), hipMemcpyDeviceToHost); // 直接使用事先分配好的输出内存拷贝
hipMemcpy(outputBuffer_Host,
outputBuffer_Device,
outputShapes.bytes(),
hipMemcpyDeviceToHost); // 直接使用事先分配好的输出内存拷贝
// 获取每张图像的预测结果
int numberOfClasses=numberOfOutput/srcImages.size();
int numberOfClasses = numberOfOutput / srcImages.size();
std::vector<float> logit;
for(int i=0;i<srcImages.size();++i)
for(int i = 0; i < srcImages.size(); ++i)
{
int startIndex=numberOfClasses*i;
for(int j=0;j<numberOfClasses;++j)
int startIndex = numberOfClasses * i;
for(int j = 0; j < numberOfClasses; ++j)
{
logit.push_back(((float *)outputBuffer_Host)[startIndex+j]);
logit.push_back(((float*)outputBuffer_Host)[startIndex + j]);
}
std::vector<ResultOfPrediction> resultOfPredictions;
for(int j=0;j<numberOfClasses;++j)
for(int j = 0; j < numberOfClasses; ++j)
{
ResultOfPrediction prediction;
prediction.label=j;
prediction.confidence=logit[j];
prediction.label = j;
prediction.confidence = logit[j];
resultOfPredictions.push_back(prediction);
}
......@@ -292,7 +294,6 @@ ErrorCode Classifier::Classify(const std::vector<cv::Mat> &srcImages,std::vector
}
return SUCCESS;
}
}
} // namespace migraphxSamples
Src/Classifier.h
View file @ 0ed76f01
......@@ -8,22 +8,23 @@
namespace migraphxSamples
{
class Classifier
class Classifier
{
public:
public:
Classifier();
~Classifier();
ErrorCode Initialize(InitializationParameterOfClassifier initializationParameterOfClassifier);
cv::Mat Preprocess(const std::vector<cv::Mat> &srcImages);
cv::Mat Preprocess(const std::vector<cv::Mat>& srcImages);
ErrorCode Classify(const std::vector<cv::Mat> &srcImages,std::vector<std::vector<ResultOfPrediction>> &predictions);
ErrorCode Classify(const std::vector<cv::Mat>& srcImages,
std::vector<std::vector<ResultOfPrediction>>& predictions);
private:
private:
cv::FileStorage configurationFile;
migraphx::program net;
cv::Size inputSize;
std::string inputName;
......@@ -32,18 +33,15 @@ private:
migraphx::shape outputShape;
std::unordered_map<std::string, migraphx::argument> programParameters;
void *inputBuffer_Device;
void *outputBuffer_Device;
void *outputBuffer_Host;
void* inputBuffer_Device;
void* outputBuffer_Device;
void* outputBuffer_Host;
bool useInt8;
bool useFP16;
bool useoffloadcopy;
};
}
} // namespace migraphxSamples
#endif
Src/Utility/CommonDefinition.h
View file @ 0ed76f01
......@@ -7,41 +7,40 @@
namespace migraphxSamples
{
// 路径分隔符(Linux:‘/’,Windows:’\\’)
#ifdef _WIN32
#define PATH_SEPARATOR '\\'
#define PATH_SEPARATOR '\\'
#else
#define PATH_SEPARATOR '/'
#define PATH_SEPARATOR '/'
#endif
#define CONFIG_FILE "../Resource/Configuration.xml"
#define CONFIG_FILE "../Resource/Configuration.xml"
typedef enum _ErrorCode
{
SUCCESS=0, // 0
MODEL_NOT_EXIST, // 模型不存在
CONFIG_FILE_NOT_EXIST, // 配置文件不存在
FAIL_TO_LOAD_MODEL, // 加载模型失败
SUCCESS = 0, // 0
MODEL_NOT_EXIST, // 模型不存在
CONFIG_FILE_NOT_EXIST, // 配置文件不存在
FAIL_TO_LOAD_MODEL, // 加载模型失败
FAIL_TO_OPEN_CONFIG_FILE, // 加载配置文件失败
IMAGE_ERROR, // 图像错误
}ErrorCode;
IMAGE_ERROR, // 图像错误
} ErrorCode;
typedef struct _ResultOfPrediction
{
float confidence;
int label;
_ResultOfPrediction():confidence(0.0f),label(0){}
_ResultOfPrediction() : confidence(0.0f), label(0) {}
}ResultOfPrediction;
} ResultOfPrediction;
typedef struct _InitializationParameterOfClassifier
{
std::string parentPath;
std::string configFilePath;
}InitializationParameterOfClassifier;
} InitializationParameterOfClassifier;
}
} // namespace migraphxSamples
#endif
Src/Utility/CommonUtility.cpp
View file @ 0ed76f01
......@@ -6,37 +6,44 @@ using namespace cv::dnn;
namespace migraphxSamples
{
void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, const Image2BlobParams& param)
void blobFromImagesWithParams(InputArrayOfArrays images_,
OutputArray blob_,
const Image2BlobParams& param)
{
if (images_.kind() != _InputArray::STD_VECTOR_MAT && images_.kind() != _InputArray::STD_ARRAY_MAT &&
images_.kind() != _InputArray::STD_VECTOR_VECTOR) {
if(images_.kind() != _InputArray::STD_VECTOR_MAT &&
images_.kind() != _InputArray::STD_ARRAY_MAT &&
images_.kind() != _InputArray::STD_VECTOR_VECTOR)
{
String error_message = "The data is expected as vectors of vectors or vectors of matrices.";
CV_Error(Error::StsBadArg, error_message);
}
CV_CheckType(param.ddepth, param.ddepth == CV_32F || param.ddepth == CV_8U,
CV_CheckType(param.ddepth,
param.ddepth == CV_32F || param.ddepth == CV_8U,
"Blob depth should be CV_32F or CV_8U");
Size size = param.size;
std::vector<Mat> images;
images_.getMatVector(images);
CV_Assert(!images.empty());
int nch = images[0].channels();
int nch = images[0].channels();
Scalar scalefactor = param.scalefactor;
if (param.ddepth == CV_8U)
if(param.ddepth == CV_8U)
{
CV_Assert(scalefactor == Scalar::all(1.0) && "Scaling is not supported for CV_8U blob depth");
CV_Assert(param.mean == Scalar() && "Mean subtraction is not supported for CV_8U blob depth");
CV_Assert(scalefactor == Scalar::all(1.0) &&
"Scaling is not supported for CV_8U blob depth");
CV_Assert(param.mean == Scalar() &&
"Mean subtraction is not supported for CV_8U blob depth");
}
for (size_t i = 0; i < images.size(); i++)
for(size_t i = 0; i < images.size(); i++)
{
Size imgSize = images[i].size();
if (size == Size())
if(size == Size())
size = imgSize;
if (size != imgSize)
if(size != imgSize)
{
if (param.paddingmode == DNN_PMODE_CROP_CENTER)
if(param.paddingmode == DNN_PMODE_CROP_CENTER)
{
float resizeFactor = std::max(size.width / (float)imgSize.width,
size.height / (float)imgSize.height);
......@@ -48,18 +55,18 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
}
else
{
if (param.paddingmode == DNN_PMODE_LETTERBOX)
if(param.paddingmode == DNN_PMODE_LETTERBOX)
{
float resizeFactor = std::min(size.width / (float)imgSize.width,
size.height / (float)imgSize.height);
int rh = int(imgSize.height * resizeFactor);
int rw = int(imgSize.width * resizeFactor);
int rh = int(imgSize.height * resizeFactor);
int rw = int(imgSize.width * resizeFactor);
resize(images[i], images[i], Size(rw, rh), INTER_LINEAR);
int top = (size.height - rh)/2;
int top = (size.height - rh) / 2;
int bottom = size.height - top - rh;
int left = (size.width - rw)/2;
int right = size.width - left - rw;
int left = (size.width - rw) / 2;
int right = size.width - left - rw;
copyMakeBorder(images[i], images[i], top, bottom, left, right, BORDER_CONSTANT);
}
else
......@@ -68,13 +75,13 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
}
Scalar mean = param.mean;
if (param.swapRB)
if(param.swapRB)
{
std::swap(mean[0], mean[2]);
std::swap(scalefactor[0], scalefactor[2]);
}
if (images[i].depth() == CV_8U && param.ddepth == CV_32F)
if(images[i].depth() == CV_8U && param.ddepth == CV_32F)
images[i].convertTo(images[i], CV_32F);
images[i] -= mean;
......@@ -82,19 +89,19 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
}
size_t nimages = images.size();
Mat image0 = images[0];
Mat image0 = images[0];
CV_Assert(image0.dims == 2);
if (param.datalayout == DNN_LAYOUT_NCHW)
if(param.datalayout == DNN_LAYOUT_NCHW)
{
if (nch == 3 || nch == 4)
if(nch == 3 || nch == 4)
{
int sz[] = { (int)nimages, nch, image0.rows, image0.cols };
int sz[] = {(int)nimages, nch, image0.rows, image0.cols};
blob_.create(4, sz, param.ddepth);
Mat blob = blob_.getMat();
Mat ch[4];
for (size_t i = 0; i < nimages; i++)
for(size_t i = 0; i < nimages; i++)
{
const Mat& image = images[i];
CV_Assert(image.depth() == blob_.depth());
......@@ -102,9 +109,9 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
CV_Assert(image.dims == 2 && (nch == 3 || nch == 4));
CV_Assert(image.size() == image0.size());
for (int j = 0; j < nch; j++)
for(int j = 0; j < nch; j++)
ch[j] = Mat(image.rows, image.cols, param.ddepth, blob.ptr((int)i, j));
if (param.swapRB)
if(param.swapRB)
std::swap(ch[0], ch[2]);
split(image, ch);
}
......@@ -112,11 +119,11 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
else
{
CV_Assert(nch == 1);
int sz[] = { (int)nimages, 1, image0.rows, image0.cols };
int sz[] = {(int)nimages, 1, image0.rows, image0.cols};
blob_.create(4, sz, param.ddepth);
Mat blob = blob_.getMat();
for (size_t i = 0; i < nimages; i++)
for(size_t i = 0; i < nimages; i++)
{
const Mat& image = images[i];
CV_Assert(image.depth() == blob_.depth());
......@@ -128,19 +135,19 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
}
}
}
else if (param.datalayout == DNN_LAYOUT_NHWC)
else if(param.datalayout == DNN_LAYOUT_NHWC)
{
int sz[] = { (int)nimages, image0.rows, image0.cols, nch};
int sz[] = {(int)nimages, image0.rows, image0.cols, nch};
blob_.create(4, sz, param.ddepth);
Mat blob = blob_.getMat();
Mat blob = blob_.getMat();
int subMatType = CV_MAKETYPE(param.ddepth, nch);
for (size_t i = 0; i < nimages; i++)
for(size_t i = 0; i < nimages; i++)
{
const Mat& image = images[i];
CV_Assert(image.depth() == blob_.depth());
CV_Assert(image.channels() == image0.channels());
CV_Assert(image.size() == image0.size());
if (param.swapRB)
if(param.swapRB)
{
Mat tmpRB;
cvtColor(image, tmpRB, COLOR_BGR2RGB);
......@@ -151,7 +158,8 @@ void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, con
}
}
else
CV_Error(Error::StsUnsupportedFormat, "Unsupported data layout in blobFromImagesWithParams function.");
CV_Error(Error::StsUnsupportedFormat,
"Unsupported data layout in blobFromImagesWithParams function.");
}
}
} // namespace migraphxSamples
Src/Utility/CommonUtility.h
View file @ 0ed76f01
......@@ -12,46 +12,69 @@ namespace migraphxSamples
{
enum DataLayout
{
DNN_LAYOUT_UNKNOWN = 0,
DNN_LAYOUT_ND = 1, //!< OpenCV data layout for 2D data.
DNN_LAYOUT_NCHW = 2, //!< OpenCV data layout for 4D data.
DNN_LAYOUT_NCDHW = 3, //!< OpenCV data layout for 5D data.
DNN_LAYOUT_NHWC = 4, //!< Tensorflow-like data layout for 4D data.
DNN_LAYOUT_NDHWC = 5, //!< Tensorflow-like data layout for 5D data.
DNN_LAYOUT_PLANAR =
6, //!< Tensorflow-like data layout, it should only be used at tf or tflite model parsing.
};
enum ImagePaddingMode
{
DNN_PMODE_NULL = 0, // !< Default. Resize to required input size without extra processing.
DNN_PMODE_CROP_CENTER = 1, // !< Image will be cropped after resize.
DNN_PMODE_LETTERBOX = 2, // !< Resize image to the desired size while preserving the aspect
// ratio of original image.
};
struct Image2BlobParams
{
Image2BlobParams()
: scalefactor(Scalar::all(1.0)),
size(Size()),
mean(Scalar()),
swapRB(false),
ddepth(CV_32F),
datalayout(DNN_LAYOUT_NCHW),
paddingmode(DNN_PMODE_NULL)
{
DNN_LAYOUT_UNKNOWN = 0,
DNN_LAYOUT_ND = 1, //!< OpenCV data layout for 2D data.
DNN_LAYOUT_NCHW = 2, //!< OpenCV data layout for 4D data.
DNN_LAYOUT_NCDHW = 3, //!< OpenCV data layout for 5D data.
DNN_LAYOUT_NHWC = 4, //!< Tensorflow-like data layout for 4D data.
DNN_LAYOUT_NDHWC = 5, //!< Tensorflow-like data layout for 5D data.
DNN_LAYOUT_PLANAR = 6, //!< Tensorflow-like data layout, it should only be used at tf or tflite model parsing.
};
enum ImagePaddingMode
{
DNN_PMODE_NULL = 0, // !< Default. Resize to required input size without extra processing.
DNN_PMODE_CROP_CENTER = 1, // !< Image will be cropped after resize.
DNN_PMODE_LETTERBOX = 2, // !< Resize image to the desired size while preserving the aspect ratio of original image.
};
}
struct Image2BlobParams
Image2BlobParams(const Scalar& scalefactor_,
const Size& size_,
const Scalar& mean_,
bool swapRB_,
int ddepth_,
DataLayout datalayout_,
ImagePaddingMode mode_)
: scalefactor(scalefactor_),
size(size_),
mean(mean_),
swapRB(swapRB_),
ddepth(ddepth_),
datalayout(datalayout_),
paddingmode(mode_)
{
Image2BlobParams():scalefactor(Scalar::all(1.0)), size(Size()), mean(Scalar()), swapRB(false), ddepth(CV_32F),
datalayout(DNN_LAYOUT_NCHW), paddingmode(DNN_PMODE_NULL)
{}
Image2BlobParams(const Scalar& scalefactor_, const Size& size_, const Scalar& mean_, bool swapRB_,
int ddepth_, DataLayout datalayout_, ImagePaddingMode mode_):
scalefactor(scalefactor_), size(size_), mean(mean_), swapRB(swapRB_), ddepth(ddepth_),
datalayout(datalayout_), paddingmode(mode_)
{}
Scalar scalefactor; //!< scalefactor multiplier for input image values.
Size size; //!< Spatial size for output image.
Scalar mean; //!< Scalar with mean values which are subtracted from channels.
bool swapRB; //!< Flag which indicates that swap first and last channels
int ddepth; //!< Depth of output blob. Choose CV_32F or CV_8U.
DataLayout datalayout; //!< Order of output dimensions. Choose DNN_LAYOUT_NCHW or DNN_LAYOUT_NHWC.
ImagePaddingMode paddingmode; //!< Image padding mode. @see ImagePaddingMode.
};
void blobFromImagesWithParams(InputArrayOfArrays images_, OutputArray blob_, const Image2BlobParams& param);
}
}
Scalar scalefactor; //!< scalefactor multiplier for input image values.
Size size; //!< Spatial size for output image.
Scalar mean; //!< Scalar with mean values which are subtracted from channels.
bool swapRB; //!< Flag which indicates that swap first and last channels
int ddepth; //!< Depth of output blob. Choose CV_32F or CV_8U.
DataLayout
datalayout; //!< Order of output dimensions. Choose DNN_LAYOUT_NCHW or DNN_LAYOUT_NHWC.
ImagePaddingMode paddingmode; //!< Image padding mode. @see ImagePaddingMode.
};
void blobFromImagesWithParams(InputArrayOfArrays images_,
OutputArray blob_,
const Image2BlobParams& param);
} // namespace migraphxSamples
#endif
Src/Utility/Filesystem.cpp
View file @ 0ed76f01
This diff is collapsed.
Src/Utility/Filesystem.h
View file @ 0ed76f01
......@@ -5,27 +5,27 @@
#include <string>
#include <vector>
namespace migraphxSamples
{
// 路径是否存在
bool Exists(const std::string &path);
bool Exists(const std::string& path);
// 路径是否为目录
bool IsDirectory(const std::string &path);
bool IsDirectory(const std::string& path);
// 是否是路径分隔符(Linux:‘/’,Windows:’\\’)
bool IsPathSeparator(char c);
// 路径拼接
std::string JoinPath(const std::string &base, const std::string &path);
std::string JoinPath(const std::string& base, const std::string& path);
// 创建多级目录,注意：创建多级目录的时候，目标目录是不能有文件存在的
bool CreateDirectories(const std::string &directoryPath);
bool CreateDirectories(const std::string& directoryPath);
/** 生成符合指定模式的文件名列表(支持递归遍历)
*
*
* pattern: 模式,比如"*.jpg","*.png","*.jpg,*.png"
* addPath：是否包含父路径
* 注意：
......@@ -36,35 +36,43 @@ bool CreateDirectories(const std::string &directoryPath);
5. 不能返回子目录名
*
*/
void GetFileNameList(const std::string &directory, const std::string &pattern, std::vector<std::string> &result, bool recursive, bool addPath);
void GetFileNameList(const std::string& directory,
const std::string& pattern,
std::vector<std::string>& result,
bool recursive,
bool addPath);
// 与GetFileNameList的区别在于如果有子目录，在addPath为true的时候会返回子目录路径(目录名最后有"/")
void GetFileNameList2(const std::string &directory, const std::string &pattern, std::vector<std::string> &result, bool recursive, bool addPath);
void GetFileNameList2(const std::string& directory,
const std::string& pattern,
std::vector<std::string>& result,
bool recursive,
bool addPath);
// 删除文件或者目录,支持递归删除
void Remove(const std::string &directory, const std::string &extension="");
void Remove(const std::string& directory, const std::string& extension = "");
/** 获取路径的文件名和扩展名
*
*
* 示例：path为D:/1/1.txt,则GetFileName()为1.txt,GetFileName_NoExtension()为1,GetExtension()为.txt,GetParentPath()为D:/1/
*/
std::string GetFileName(const std::string &path);
std::string GetFileName_NoExtension(const std::string &path);
std::string GetExtension(const std::string &path);
std::string GetParentPath(const std::string &path);
*/
std::string GetFileName(const std::string& path);
std::string GetFileName_NoExtension(const std::string& path);
std::string GetExtension(const std::string& path);
std::string GetParentPath(const std::string& path);
// 拷贝文件
bool CopyFile(const std::string srcPath,const std::string dstPath);
bool CopyFile(const std::string srcPath, const std::string dstPath);
/** 拷贝目录
*
*
* 示例：CopyDirectories("D:/0/1/2/","E:/3/");实现把D:/0/1/2/目录拷贝到E:/3/目录中(即拷贝完成后的目录结构为E:/3/2/)
* 注意：
1.第一个参数的最后不能加”/”
2.不能拷贝隐藏文件
*/
bool CopyDirectories(std::string srcPath,const std::string dstPath);
bool CopyDirectories(std::string srcPath, const std::string dstPath);
}
} // namespace migraphxSamples
#endif
Src/Utility/SimpleLog.h
View file @ 0ed76f01
......@@ -8,7 +8,7 @@
#include <map>
#include <thread>
#include <mutex>
#if (defined WIN32 || defined _WIN32)
#if(defined WIN32 || defined _WIN32)
#include <Windows.h>
#else
#include <sys/time.h>
......@@ -16,13 +16,13 @@
using namespace std;
/** 简易日志
*
*
* 不依赖于其他第三方库，只需要包含一个头文件就可以使用。提供了4种日志级别，包括INFO,DEBUG,WARN和ERROR。
*
*
* 示例1:
// 初始化日志，在./Log/目录下创建两个日志文件log1.log和log2.log(注意：目录./Log/需要存在，否则日志创建失败)
//
初始化日志，在./Log/目录下创建两个日志文件log1.log和log2.log(注意：目录./Log/需要存在，否则日志创建失败)
LogManager::GetInstance()->Initialize("./Log/","log1");
LogManager::GetInstance()->Initialize("./Log/","log2");
......@@ -34,11 +34,11 @@ using namespace std;
// 关闭日志
LogManager::GetInstance()->Close("log1");
LogManager::GetInstance()->Close("log2");
* 示例2:
// 将日志输出到控制台
string log = "Hello World";
LOG_INFO(stdout, "%s\n", log.c_str());
LOG_INFO(stdout, "%s\n", log.c_str());
* 注意：
1. 需要C++11
......@@ -50,44 +50,43 @@ using namespace std;
class LogManager
{
private:
LogManager(){}
private:
LogManager() {}
public:
~LogManager(){}
inline void Initialize(const string &parentPath,const string &logName)
public:
~LogManager() {}
inline void Initialize(const string& parentPath, const string& logName)
{
// 日志名为空表示输出到控制台
if(logName.size()==0)
if(logName.size() == 0)
return;
// 查找该日志文件，如果没有则创建
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if (iter == logMap.end())
if(iter == logMap.end())
{
string pathOfLog = parentPath+ logName + ".log";
FILE *logFile = fopen(pathOfLog.c_str(), "a"); // w:覆盖原有文件,a:追加
if(logFile!=NULL)
string pathOfLog = parentPath + logName + ".log";
FILE* logFile = fopen(pathOfLog.c_str(), "a"); // w:覆盖原有文件,a:追加
if(logFile != NULL)
{
logMap.insert(std::make_pair(logName, logFile));
}
}
}
inline FILE* GetLogFile(const string &logName)
inline FILE* GetLogFile(const string& logName)
{
std::map<string, FILE*>::const_iterator iter=logMap.find(logName);
if(iter==logMap.end())
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if(iter == logMap.end())
{
return NULL;
}
return (*iter).second;
}
inline void Close(const string &logName)
inline void Close(const string& logName)
{
std::map<string, FILE*>::const_iterator iter=logMap.find(logName);
if(iter==logMap.end())
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if(iter == logMap.end())
{
return;
}
......@@ -95,10 +94,7 @@ public:
fclose((*iter).second);
logMap.erase(iter);
}
inline std::mutex &GetLogMutex()
{
return logMutex;
}
inline std::mutex& GetLogMutex() { return logMutex; }
// Singleton
static LogManager* GetInstance()
......@@ -106,21 +102,22 @@ public:
static LogManager logManager;
return &logManager;
}
private:
private:
std::map<string, FILE*> logMap;
std::mutex logMutex;
};
#ifdef LOG_MUTEX
#define LOCK LogManager::GetInstance()->GetLogMutex().lock()
#define UNLOCK LogManager::GetInstance()->GetLogMutex().unlock()
#define LOCK LogManager::GetInstance()->GetLogMutex().lock()
#define UNLOCK LogManager::GetInstance()->GetLogMutex().unlock()
#else
#define LOCK
#define UNLOCK
#define LOCK
#define UNLOCK
#endif
// log time
typedef struct _LogTime
typedef struct _LogTime
{
string year;
string month;
......@@ -131,53 +128,53 @@ typedef struct _LogTime
string millisecond; // ms
string microsecond; // us
string weekDay;
}LogTime;
} LogTime;
inline LogTime GetTime()
{
LogTime currentTime;
#if (defined WIN32 || defined _WIN32)
#if(defined WIN32 || defined _WIN32)
SYSTEMTIME systemTime;
GetLocalTime(&systemTime);
char temp[8] = { 0 };
char temp[8] = {0};
sprintf(temp, "%04d", systemTime.wYear);
currentTime.year=string(temp);
currentTime.year = string(temp);
sprintf(temp, "%02d", systemTime.wMonth);
currentTime.month=string(temp);
currentTime.month = string(temp);
sprintf(temp, "%02d", systemTime.wDay);
currentTime.day=string(temp);
currentTime.day = string(temp);
sprintf(temp, "%02d", systemTime.wHour);
currentTime.hour=string(temp);
currentTime.hour = string(temp);
sprintf(temp, "%02d", systemTime.wMinute);
currentTime.minute=string(temp);
currentTime.minute = string(temp);
sprintf(temp, "%02d", systemTime.wSecond);
currentTime.second=string(temp);
currentTime.second = string(temp);
sprintf(temp, "%03d", systemTime.wMilliseconds);
currentTime.millisecond=string(temp);
currentTime.millisecond = string(temp);
sprintf(temp, "%d", systemTime.wDayOfWeek);
currentTime.weekDay=string(temp);
currentTime.weekDay = string(temp);
#else
struct timeval tv;
struct tm *p;
struct timeval tv;
struct tm* p;
gettimeofday(&tv, NULL);
p = localtime(&tv.tv_sec);
char temp[8]={0};
sprintf(temp,"%04d",1900+p->tm_year);
currentTime.year=string(temp);
sprintf(temp,"%02d",1+p->tm_mon);
currentTime.month=string(temp);
sprintf(temp,"%02d",p->tm_mday);
currentTime.day=string(temp);
sprintf(temp,"%02d",p->tm_hour);
currentTime.hour=string(temp);
sprintf(temp,"%02d",p->tm_min);
currentTime.minute=string(temp);
sprintf(temp,"%02d",p->tm_sec);
currentTime.second=string(temp);
sprintf(temp,"%03d",(int)(tv.tv_usec/1000));
char temp[8] = {0};
sprintf(temp, "%04d", 1900 + p->tm_year);
currentTime.year = string(temp);
sprintf(temp, "%02d", 1 + p->tm_mon);
currentTime.month = string(temp);
sprintf(temp, "%02d", p->tm_mday);
currentTime.day = string(temp);
sprintf(temp, "%02d", p->tm_hour);
currentTime.hour = string(temp);
sprintf(temp, "%02d", p->tm_min);
currentTime.minute = string(temp);
sprintf(temp, "%02d", p->tm_sec);
currentTime.second = string(temp);
sprintf(temp, "%03d", (int)(tv.tv_usec / 1000));
currentTime.millisecond = string(temp);
sprintf(temp, "%03d", (int)(tv.tv_usec % 1000));
currentTime.microsecond = string(temp);
......@@ -187,61 +184,83 @@ inline LogTime GetTime()
return currentTime;
}
#define LOG_TIME(logFile) \
do\
{\
LogTime currentTime=GetTime(); \
fprintf(((logFile == NULL) ? stdout : logFile), "%s-%s-%s %s:%s:%s.%s\t",currentTime.year.c_str(),currentTime.month.c_str(),currentTime.day.c_str(),currentTime.hour.c_str(),currentTime.minute.c_str(),currentTime.second.c_str(),currentTime.millisecond.c_str()); \
}while (0)
#define LOG_INFO(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "INFO\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_DEBUG(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile);\
fprintf(((logFile==NULL)?stdout:logFile), "DEBUG\t"); \
fprintf(((logFile==NULL)?stdout:logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile==NULL)?stdout:logFile),logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_ERROR(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile);\
fprintf(((logFile==NULL)?stdout:logFile), "ERROR\t"); \
fprintf(((logFile==NULL)?stdout:logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile==NULL)?stdout:logFile),logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_WARN(logFile,logInfo, ...) \
do\
{\
LOCK; \
LOG_TIME(logFile);\
fprintf(((logFile==NULL)?stdout:logFile), "WARN\t"); \
fprintf(((logFile==NULL)?stdout:logFile), "[%s:%d (%s) ]: ", __FILE__, __LINE__, __FUNCTION__); \
fprintf(((logFile==NULL)?stdout:logFile),logInfo, ## __VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while (0)
#define LOG_TIME(logFile) \
do \
{ \
LogTime currentTime = GetTime(); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"%s-%s-%s %s:%s:%s.%s\t", \
currentTime.year.c_str(), \
currentTime.month.c_str(), \
currentTime.day.c_str(), \
currentTime.hour.c_str(), \
currentTime.minute.c_str(), \
currentTime.second.c_str(), \
currentTime.millisecond.c_str()); \
} while(0)
#endif // __SIMPLE_LOG_H__
#define LOG_INFO(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "INFO\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#define LOG_DEBUG(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "DEBUG\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#define LOG_ERROR(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "ERROR\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#define LOG_WARN(logFile, logInfo, ...) \
do \
{ \
LOCK; \
LOG_TIME(logFile); \
fprintf(((logFile == NULL) ? stdout : logFile), "WARN\t"); \
fprintf(((logFile == NULL) ? stdout : logFile), \
"[%s:%d (%s) ]: ", \
__FILE__, \
__LINE__, \
__FUNCTION__); \
fprintf(((logFile == NULL) ? stdout : logFile), logInfo, ##__VA_ARGS__); \
fflush(logFile); \
UNLOCK; \
} while(0)
#endif // __SIMPLE_LOG_H__
Src/main.cpp
View file @ 0ed76f01
......@@ -10,9 +10,9 @@ int main()
// 创建分类器
migraphxSamples::Classifier classifier;
migraphxSamples::InitializationParameterOfClassifier initParamOfClassifier;
initParamOfClassifier.configFilePath=CONFIG_FILE;
migraphxSamples::ErrorCode errorCode=classifier.Initialize(initParamOfClassifier);
if(errorCode!=migraphxSamples::SUCCESS)
initParamOfClassifier.configFilePath = CONFIG_FILE;
migraphxSamples::ErrorCode errorCode = classifier.Initialize(initParamOfClassifier);
if(errorCode != migraphxSamples::SUCCESS)
{
LOG_ERROR(stdout, "fail to initialize ResNet50!\n");
exit(-1);
......@@ -20,33 +20,32 @@ int main()
LOG_INFO(stdout, "succeed to initialize ResNet50\n");
// 读取测试图片
cv::Mat srcImage=cv::imread("../Resource/Images/ImageNet_01.jpg",1);
cv::Mat srcImage = cv::imread("../Resource/Images/ImageNet_01.jpg", 1);
// 设置batchsize
int batchsize=1;
int batchsize = 1;
std::vector<cv::Mat> srcImages;
for(int i=0;i<batchsize;++i)
for(int i = 0; i < batchsize; ++i)
{
srcImages.push_back(srcImage);
}
// 推理
std::vector<std::vector<migraphxSamples::ResultOfPrediction>> predictions;
classifier.Classify(srcImages,predictions);
classifier.Classify(srcImages, predictions);
// 获取推理结果
LOG_INFO(stdout,"========== Classification Results ==========\n");
for(int i=0;i<predictions.size();++i)
LOG_INFO(stdout, "========== Classification Results ==========\n");
for(int i = 0; i < predictions.size(); ++i)
{
// 一个batch中第i幅图像的结果
LOG_INFO(stdout,"========== %d result ==========\n",i);
std::vector<migraphxSamples::ResultOfPrediction> resultOfPredictions=predictions[i];
for(int j=0;j<resultOfPredictions.size();++j)
LOG_INFO(stdout, "========== %d result ==========\n", i);
std::vector<migraphxSamples::ResultOfPrediction> resultOfPredictions = predictions[i];
for(int j = 0; j < resultOfPredictions.size(); ++j)
{
migraphxSamples::ResultOfPrediction prediction=resultOfPredictions[j];
LOG_INFO(stdout,"label:%d,confidence:%f\n",prediction.label,prediction.confidence);
migraphxSamples::ResultOfPrediction prediction = resultOfPredictions[j];
LOG_INFO(stdout, "label:%d,confidence:%f\n", prediction.label, prediction.confidence);
}
}
return 0;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment