Commit 22b7c574 authored by liuhy's avatar liuhy
Browse files

paddleOcr v5

parents
This diff is collapsed.
// 常用定义
#ifndef __COMMON_DEFINITION_H__
#define __COMMON_DEFINITION_H__
//#include <opencv2/opencv.hpp>
namespace migraphxSamples
{
// 路径分隔符(Linux:‘/’,Windows:’\\’)
#ifdef _WIN32
#define PATH_SEPARATOR '\\'
#else
#define PATH_SEPARATOR '/'
#endif
#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
FAIL_TO_OPEN_CONFIG_FILE, // 加载配置文件失败
IMAGE_ERROR, // 图像错误
} ErrorCode;
typedef struct _ResultOfPrediction
{
float confidence;
int label;
_ResultOfPrediction() : confidence(0.0f), label(0) {}
} ResultOfPrediction;
typedef struct _InitializationParameterOfClassifier
{
std::string parentPath;
std::string configFilePath;
} InitializationParameterOfClassifier;
} // namespace migraphxSamples
#endif
#include <Filesystem.h>
#include <algorithm>
#include <sys/stat.h>
#include <sys/types.h>
#include <fstream>
#ifdef _WIN32
#include <io.h>
#include <direct.h>
#include <Windows.h>
#else
#include <unistd.h>
#include <dirent.h>
#endif
// 路径分隔符(Linux:‘/’,Windows:’\\’)
#ifdef _WIN32
#define PATH_SEPARATOR '\\'
#else
#define PATH_SEPARATOR '/'
#endif
using namespace std;
namespace migraphxSamples
{
static std::vector<std::string> SplitString(std::string str, std::string separator)
{
std::string::size_type pos;
std::vector<std::string> result;
str += separator; // 扩展字符串以方便操作
int size = str.size();
for(int i = 0; i < size; i++)
{
pos = str.find(separator, i);
if(pos < size)
{
std::string s = str.substr(i, pos - i);
result.push_back(s);
i = pos + separator.size() - 1;
}
}
return result;
}
#if defined _WIN32 || defined WINCE
const char dir_separators[] = "/\\";
struct dirent
{
const char* d_name;
};
struct DIR
{
#ifdef WINRT
WIN32_FIND_DATAW data;
#else
WIN32_FIND_DATAA data;
#endif
HANDLE handle;
dirent ent;
#ifdef WINRT
DIR() {}
~DIR()
{
if(ent.d_name)
delete[] ent.d_name;
}
#endif
};
DIR* opendir(const char* path)
{
DIR* dir = new DIR;
dir->ent.d_name = 0;
#ifdef WINRT
string full_path = string(path) + "\\*";
wchar_t wfull_path[MAX_PATH];
size_t copied = mbstowcs(wfull_path, full_path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
dir->handle = ::FindFirstFileExW(
wfull_path, FindExInfoStandard, &dir->data, FindExSearchNameMatch, NULL, 0);
#else
dir->handle = ::FindFirstFileExA((string(path) + "\\*").c_str(),
FindExInfoStandard,
&dir->data,
FindExSearchNameMatch,
NULL,
0);
#endif
if(dir->handle == INVALID_HANDLE_VALUE)
{
/*closedir will do all cleanup*/
delete dir;
return 0;
}
return dir;
}
dirent* readdir(DIR* dir)
{
#ifdef WINRT
if(dir->ent.d_name != 0)
{
if(::FindNextFileW(dir->handle, &dir->data) != TRUE)
return 0;
}
size_t asize = wcstombs(NULL, dir->data.cFileName, 0);
CV_Assert((asize != 0) && (asize != (size_t)-1));
char* aname = new char[asize + 1];
aname[asize] = 0;
wcstombs(aname, dir->data.cFileName, asize);
dir->ent.d_name = aname;
#else
if(dir->ent.d_name != 0)
{
if(::FindNextFileA(dir->handle, &dir->data) != TRUE)
return 0;
}
dir->ent.d_name = dir->data.cFileName;
#endif
return &dir->ent;
}
void closedir(DIR* dir)
{
::FindClose(dir->handle);
delete dir;
}
#else
#include <dirent.h>
#include <sys/stat.h>
const char dir_separators[] = "/";
#endif
static bool isDir(const string& path, DIR* dir)
{
#if defined _WIN32 || defined WINCE
DWORD attributes;
BOOL status = TRUE;
if(dir)
attributes = dir->data.dwFileAttributes;
else
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
#else
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
#endif
attributes = all_attrs.dwFileAttributes;
}
return status && ((attributes & FILE_ATTRIBUTE_DIRECTORY) != 0);
#else
(void)dir;
struct stat stat_buf;
if(0 != stat(path.c_str(), &stat_buf))
return false;
int is_dir = S_ISDIR(stat_buf.st_mode);
return is_dir != 0;
#endif
}
bool IsDirectory(const string& path) { return isDir(path, NULL); }
bool Exists(const string& path)
{
#if defined _WIN32 || defined WINCE
BOOL status = TRUE;
{
WIN32_FILE_ATTRIBUTE_DATA all_attrs;
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
status = ::GetFileAttributesExW(wpath, GetFileExInfoStandard, &all_attrs);
#else
status = ::GetFileAttributesExA(path.c_str(), GetFileExInfoStandard, &all_attrs);
#endif
}
return !!status;
#else
struct stat stat_buf;
return (0 == stat(path.c_str(), &stat_buf));
#endif
}
bool IsPathSeparator(char c) { return c == '/' || c == '\\'; }
string JoinPath(const string& base, const string& path)
{
if(base.empty())
return path;
if(path.empty())
return base;
bool baseSep = IsPathSeparator(base[base.size() - 1]);
bool pathSep = IsPathSeparator(path[0]);
string result;
if(baseSep && pathSep)
{
result = base + path.substr(1);
}
else if(!baseSep && !pathSep)
{
result = base + PATH_SEPARATOR + path;
}
else
{
result = base + path;
}
return result;
}
static bool wildcmp(const char* string, const char* wild)
{
const char *cp = 0, *mp = 0;
while((*string) && (*wild != '*'))
{
if((*wild != *string) && (*wild != '?'))
{
return false;
}
wild++;
string++;
}
while(*string)
{
if(*wild == '*')
{
if(!*++wild)
{
return true;
}
mp = wild;
cp = string + 1;
}
else if((*wild == *string) || (*wild == '?'))
{
wild++;
string++;
}
else
{
wild = mp;
string = cp++;
}
}
while(*wild == '*')
{
wild++;
}
return *wild == 0;
}
static void glob_rec(const string& directory,
const string& wildchart,
std::vector<string>& result,
bool recursive,
bool includeDirectories,
const string& pathPrefix)
{
DIR* dir;
if((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent* ent;
while((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if((name[0] == 0) || (name[0] == '.' && name[1] == 0) ||
(name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
string entry = JoinPath(pathPrefix, name);
if(isDir(path, dir))
{
if(recursive)
glob_rec(path, wildchart, result, recursive, includeDirectories, entry);
if(!includeDirectories)
continue;
}
if(wildchart.empty() || wildcmp(name, wildchart.c_str()))
result.push_back(entry);
}
}
catch(...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
printf("could not open directory: %s", directory.c_str());
}
}
void GetFileNameList(const string& directory,
const string& pattern,
std::vector<string>& result,
bool recursive,
bool addPath)
{
// split pattern
vector<string> patterns = SplitString(pattern, ",");
result.clear();
for(int i = 0; i < patterns.size(); ++i)
{
string eachPattern = patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for(int j = 0; j < eachResult.size(); ++j)
{
if(IsDirectory(eachResult[j]))
continue;
if(addPath)
{
result.push_back(eachResult[j]);
}
else
{
result.push_back(GetFileName(eachResult[j]));
}
}
}
std::sort(result.begin(), result.end());
}
void GetFileNameList2(const string& directory,
const string& pattern,
std::vector<string>& result,
bool recursive,
bool addPath)
{
// split pattern
vector<string> patterns = SplitString(pattern, ",");
result.clear();
for(int i = 0; i < patterns.size(); ++i)
{
string eachPattern = patterns[i];
std::vector<string> eachResult;
glob_rec(directory, eachPattern, eachResult, recursive, true, directory);
for(int j = 0; j < eachResult.size(); ++j)
{
string filePath = eachResult[j];
if(IsDirectory(filePath))
{
filePath = filePath + "/";
for(int k = 0; k < filePath.size(); ++k)
{
if(IsPathSeparator(filePath[k]))
{
filePath[k] = '/';
}
}
}
if(addPath)
{
result.push_back(filePath);
}
else
{
if(!IsDirectory(filePath))
{
result.push_back(GetFileName(filePath));
}
}
}
}
std::sort(result.begin(), result.end());
}
void RemoveAll(const string& path)
{
if(!Exists(path))
return;
if(IsDirectory(path))
{
std::vector<string> entries;
GetFileNameList2(path, string(), entries, false, true);
for(size_t i = 0; i < entries.size(); i++)
{
const string& e = entries[i];
RemoveAll(e);
}
#ifdef _MSC_VER
bool result = _rmdir(path.c_str()) == 0;
#else
bool result = rmdir(path.c_str()) == 0;
#endif
if(!result)
{
printf("can't remove directory: %s\n", path.c_str());
}
}
else
{
#ifdef _MSC_VER
bool result = _unlink(path.c_str()) == 0;
#else
bool result = unlink(path.c_str()) == 0;
#endif
if(!result)
{
printf("can't remove file: %s\n", path.c_str());
}
}
}
void Remove(const string& directory, const string& extension)
{
DIR* dir;
static int numberOfFiles = 0;
if((dir = opendir(directory.c_str())) != 0)
{
/* find all the files and directories within directory */
try
{
struct dirent* ent;
while((ent = readdir(dir)) != 0)
{
const char* name = ent->d_name;
if((name[0] == 0) || (name[0] == '.' && name[1] == 0) ||
(name[0] == '.' && name[1] == '.' && name[2] == 0))
continue;
string path = JoinPath(directory, name);
if(isDir(path, dir))
{
Remove(path, extension);
}
// �ж���չ��
if(extension.empty() || wildcmp(name, extension.c_str()))
{
RemoveAll(path);
++numberOfFiles;
printf("%s deleted! number of deleted files:%d\n", path.c_str(), numberOfFiles);
}
}
}
catch(...)
{
closedir(dir);
throw;
}
closedir(dir);
}
else
{
printf("could not open directory: %s", directory.c_str());
}
// ����RemoveAllɾ��Ŀ¼
RemoveAll(directory);
}
string GetFileName(const string& path)
{
string fileName;
int indexOfPathSeparator = -1;
for(int i = path.size() - 1; i >= 0; --i)
{
if(IsPathSeparator(path[i]))
{
fileName = path.substr(i + 1, path.size() - i - 1);
indexOfPathSeparator = i;
break;
}
}
if(indexOfPathSeparator == -1)
{
fileName = path;
}
return fileName;
}
string GetFileName_NoExtension(const string& path)
{
string fileName = GetFileName(path);
string fileName_NoExtension;
for(int i = fileName.size() - 1; i > 0; --i)
{
if(fileName[i] == '.')
{
fileName_NoExtension = fileName.substr(0, i);
break;
}
}
return fileName_NoExtension;
}
string GetExtension(const string& path)
{
string fileName;
for(int i = path.size() - 1; i >= 0; --i)
{
if(path[i] == '.')
{
fileName = path.substr(i, path.size() - i);
break;
}
}
return fileName;
}
string GetParentPath(const string& path)
{
string fileName;
for(int i = path.size() - 1; i >= 0; --i)
{
if(IsPathSeparator(path[i]))
{
fileName = path.substr(0, i + 1);
break;
}
}
return fileName;
}
static bool CreateDirectory(const string& path)
{
#if defined WIN32 || defined _WIN32 || defined WINCE
#ifdef WINRT
wchar_t wpath[MAX_PATH];
size_t copied = mbstowcs(wpath, path.c_str(), MAX_PATH);
CV_Assert((copied != MAX_PATH) && (copied != (size_t)-1));
int result = CreateDirectoryA(wpath, NULL) ? 0 : -1;
#else
int result = _mkdir(path.c_str());
#endif
#elif defined __linux__ || defined __APPLE__
int result = mkdir(path.c_str(), 0777);
#else
int result = -1;
#endif
if(result == -1)
{
return IsDirectory(path);
}
return true;
}
bool CreateDirectories(const string& directoryPath)
{
string path = directoryPath;
for(;;)
{
char last_char = path.empty() ? 0 : path[path.length() - 1];
if(IsPathSeparator(last_char))
{
path = path.substr(0, path.length() - 1);
continue;
}
break;
}
if(path.empty() || path == "./" || path == ".\\" || path == ".")
return true;
if(IsDirectory(path))
return true;
size_t pos = path.rfind('/');
if(pos == string::npos)
pos = path.rfind('\\');
if(pos != string::npos)
{
string parent_directory = path.substr(0, pos);
if(!parent_directory.empty())
{
if(!CreateDirectories(parent_directory))
return false;
}
}
return CreateDirectory(path);
}
bool CopyFile(const string srcPath, const string dstPath)
{
std::ifstream srcFile(srcPath, ios::binary);
std::ofstream dstFile(dstPath, ios::binary);
if(!srcFile.is_open())
{
printf("can not open %s\n", srcPath.c_str());
return false;
}
if(!dstFile.is_open())
{
printf("can not open %s\n", dstPath.c_str());
return false;
}
if(srcPath == dstPath)
{
printf("src can not be same with dst\n");
return false;
}
char buffer[2048];
unsigned int numberOfBytes = 0;
while(srcFile)
{
srcFile.read(buffer, 2048);
dstFile.write(buffer, srcFile.gcount());
numberOfBytes += srcFile.gcount();
}
srcFile.close();
dstFile.close();
return true;
}
bool CopyDirectories(string srcPath, const string dstPath)
{
if(srcPath == dstPath)
{
printf("src can not be same with dst\n");
return false;
}
// ȥ������·���ָ���
srcPath = srcPath.substr(0, srcPath.size() - 1);
vector<string> fileNameList;
GetFileNameList2(srcPath, "", fileNameList, true, true);
string parentPathOfSrc = GetParentPath(srcPath);
int length = parentPathOfSrc.size();
// create all directories
for(int i = 0; i < fileNameList.size(); ++i)
{
// create directory
string srcFilePath = fileNameList[i];
string subStr = srcFilePath.substr(length, srcFilePath.size() - length);
string dstFilePath = dstPath + subStr;
string parentPathOfDst = GetParentPath(dstFilePath);
CreateDirectories(parentPathOfDst);
}
// copy file
for(int i = 0; i < fileNameList.size(); ++i)
{
string srcFilePath = fileNameList[i];
if(IsDirectory(srcFilePath))
{
continue;
}
string subStr = srcFilePath.substr(length, srcFilePath.size() - length);
string dstFilePath = dstPath + subStr;
// copy file
CopyFile(srcFilePath, dstFilePath);
// process
double process = (1.0 * (i + 1) / fileNameList.size()) * 100;
printf("%s done! %f% \n", GetFileName(fileNameList[i]).c_str(), process);
}
printf("all done!(the number of files:%d)\n", fileNameList.size());
return true;
}
} // namespace migraphxSamples
// 文件以及目录处理
#ifndef __FILE_SYSTEM_H__
#define __FILE_SYSTEM_H__
#include <string>
#include <vector>
namespace migraphxSamples
{
// 路径是否存在
bool Exists(const std::string& path);
// 路径是否为目录
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);
// 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);
/** 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:
1. 多个模式使用","分割,比如"*.jpg,*.png"
2. 支持通配符'*','?' ,比如第一个字符是7的所有文件名:"7*.*", 以512结尾的所有jpg文件名:"*512.jpg"
3. 使用"*.jpg",而不是".jpg"
4. 空string表示返回所有结果
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);
// 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);
// 删除文件或者目录,支持递归删除
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);
// 拷贝文件
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);
} // namespace migraphxSamples
#endif
// 简易日志
#ifndef __SIMPLE_LOG_H__
#define __SIMPLE_LOG_H__
#include <time.h>
#include <string>
#include <map>
#include <thread>
#include <mutex>
#if(defined WIN32 || defined _WIN32)
#include <Windows.h>
#else
#include <sys/time.h>
#endif
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)
LogManager::GetInstance()->Initialize("./Log/","log1");
LogManager::GetInstance()->Initialize("./Log/","log2");
// 写日志
string log = "Hello World";
LOG_INFO(LogManager::GetInstance()->GetLogFile("log1"), "%s\n", log.c_str()); // 写入log1.log
LOG_INFO(LogManager::GetInstance()->GetLogFile("log2"), "%s\n", log.c_str()); // 写入log2.log
// 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());
* 注意:
1. 需要C++11
2. 多线程的时候需要加锁(打开#define LOG_MUTEX),否则会导致日志显示混乱
*/
// #define LOG_MUTEX // 加锁
class LogManager
{
private:
LogManager() {}
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)
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())
{
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)
{
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)
{
std::map<string, FILE*>::const_iterator iter = logMap.find(logName);
if(iter == logMap.end())
{
return;
}
fclose((*iter).second);
logMap.erase(iter);
}
inline std::mutex& GetLogMutex() { return logMutex; }
// Singleton
static LogManager* GetInstance()
{
static LogManager logManager;
return &logManager;
}
private:
std::map<string, FILE*> logMap;
std::mutex logMutex;
};
#ifdef LOG_MUTEX
#define LOCK LogManager::GetInstance()->GetLogMutex().lock()
#define UNLOCK LogManager::GetInstance()->GetLogMutex().unlock()
#else
#define LOCK
#define UNLOCK
#endif
// log time
typedef struct _LogTime
{
string year;
string month;
string day;
string hour;
string minute;
string second;
string millisecond; // ms
string microsecond; // us
string weekDay;
} LogTime;
inline LogTime GetTime()
{
LogTime currentTime;
#if(defined WIN32 || defined _WIN32)
SYSTEMTIME systemTime;
GetLocalTime(&systemTime);
char temp[8] = {0};
sprintf(temp, "%04d", systemTime.wYear);
currentTime.year = string(temp);
sprintf(temp, "%02d", systemTime.wMonth);
currentTime.month = string(temp);
sprintf(temp, "%02d", systemTime.wDay);
currentTime.day = string(temp);
sprintf(temp, "%02d", systemTime.wHour);
currentTime.hour = string(temp);
sprintf(temp, "%02d", systemTime.wMinute);
currentTime.minute = string(temp);
sprintf(temp, "%02d", systemTime.wSecond);
currentTime.second = string(temp);
sprintf(temp, "%03d", systemTime.wMilliseconds);
currentTime.millisecond = string(temp);
sprintf(temp, "%d", systemTime.wDayOfWeek);
currentTime.weekDay = string(temp);
#else
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));
currentTime.millisecond = string(temp);
sprintf(temp, "%03d", (int)(tv.tv_usec % 1000));
currentTime.microsecond = string(temp);
sprintf(temp, "%d", p->tm_wday);
currentTime.weekDay = string(temp);
#endif
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)
#endif // __SIMPLE_LOG_H__
This diff is collapsed.
/*******************************************************************************
* *
* Author : Angus Johnson *
* Version : 6.4.2 *
* Date : 27 February 2017 *
* Website : http://www.angusj.com *
* Copyright : Angus Johnson 2010-2017 *
* *
* License: *
* Use, modification & distribution is subject to Boost Software License Ver 1. *
* http://www.boost.org/LICENSE_1_0.txt *
* *
* Attributions: *
* The code in this library is an extension of Bala Vatti's clipping algorithm: *
* "A generic solution to polygon clipping" *
* Communications of the ACM, Vol 35, Issue 7 (July 1992) pp 56-63. *
* http://portal.acm.org/citation.cfm?id=129906 *
* *
* Computer graphics and geometric modeling: implementation and algorithms *
* By Max K. Agoston *
* Springer; 1 edition (January 4, 2005) *
* http://books.google.com/books?q=vatti+clipping+agoston *
* *
* See also: *
* "Polygon Offsetting by Computing Winding Numbers" *
* Paper no. DETC2005-85513 pp. 565-575 *
* ASME 2005 International Design Engineering Technical Conferences *
* and Computers and Information in Engineering Conference (IDETC/CIE2005) *
* September 24-28, 2005 , Long Beach, California, USA *
* http://www.me.berkeley.edu/~mcmains/pubs/DAC05OffsetPolygon.pdf *
* *
*******************************************************************************/
#pragma once
#ifndef clipper_hpp
#define clipper_hpp
#define CLIPPER_VERSION "6.4.2"
// use_int32: When enabled 32bit ints are used instead of 64bit ints. This
// improve performance but coordinate values are limited to the range +/- 46340
//#define use_int32
// use_xyz: adds a Z member to IntPoint. Adds a minor cost to perfomance.
//#define use_xyz
// use_lines: Enables line clipping. Adds a very minor cost to performance.
#define use_lines
// use_deprecated: Enables temporary support for the obsolete functions
//#define use_deprecated
#include <cstdlib>
#include <cstring>
#include <functional>
#include <list>
#include <ostream>
#include <queue>
#include <set>
#include <stdexcept>
#include <vector>
namespace ClipperLib {
enum ClipType { ctIntersection, ctUnion, ctDifference, ctXor };
enum PolyType { ptSubject, ptClip };
// By far the most widely used winding rules for polygon filling are
// EvenOdd & NonZero (GDI, GDI+, XLib, OpenGL, Cairo, AGG, Quartz, SVG, Gr32)
// Others rules include Positive, Negative and ABS_GTR_EQ_TWO (only in OpenGL)
// see http://glprogramming.com/red/chapter11.html
enum PolyFillType { pftEvenOdd, pftNonZero, pftPositive, pftNegative };
#ifdef use_int32
typedef int cInt;
static cInt const loRange = 0x7FFF;
static cInt const hiRange = 0x7FFF;
#else
typedef signed long long cInt;
static cInt const loRange = 0x3FFFFFFF;
static cInt const hiRange = 0x3FFFFFFFFFFFFFFFLL;
typedef signed long long long64; // used by Int128 class
typedef unsigned long long ulong64;
#endif
struct IntPoint {
cInt X;
cInt Y;
#ifdef use_xyz
cInt Z;
IntPoint(cInt x = 0, cInt y = 0, cInt z = 0) : X(x), Y(y), Z(z){};
#else
IntPoint(cInt x = 0, cInt y = 0) : X(x), Y(y){};
#endif
friend inline bool operator==(const IntPoint &a, const IntPoint &b) {
return a.X == b.X && a.Y == b.Y;
}
friend inline bool operator!=(const IntPoint &a, const IntPoint &b) {
return a.X != b.X || a.Y != b.Y;
}
};
//------------------------------------------------------------------------------
typedef std::vector<IntPoint> Path;
typedef std::vector<Path> Paths;
inline Path &operator<<(Path &poly, const IntPoint &p) {
poly.push_back(p);
return poly;
}
inline Paths &operator<<(Paths &polys, const Path &p) {
polys.push_back(p);
return polys;
}
std::ostream &operator<<(std::ostream &s, const IntPoint &p);
std::ostream &operator<<(std::ostream &s, const Path &p);
std::ostream &operator<<(std::ostream &s, const Paths &p);
struct DoublePoint {
double X;
double Y;
DoublePoint(double x = 0, double y = 0) : X(x), Y(y) {}
DoublePoint(IntPoint ip) : X((double)ip.X), Y((double)ip.Y) {}
};
//------------------------------------------------------------------------------
#ifdef use_xyz
typedef void (*ZFillCallback)(IntPoint &e1bot, IntPoint &e1top, IntPoint &e2bot,
IntPoint &e2top, IntPoint &pt);
#endif
enum InitOptions {
ioReverseSolution = 1,
ioStrictlySimple = 2,
ioPreserveCollinear = 4
};
enum JoinType { jtSquare, jtRound, jtMiter };
enum EndType {
etClosedPolygon,
etClosedLine,
etOpenButt,
etOpenSquare,
etOpenRound
};
class PolyNode;
typedef std::vector<PolyNode *> PolyNodes;
class PolyNode {
public:
PolyNode();
virtual ~PolyNode(){};
Path Contour;
PolyNodes Childs;
PolyNode *Parent;
PolyNode *GetNext() const;
bool IsHole() const;
bool IsOpen() const;
int ChildCount() const;
private:
// PolyNode& operator =(PolyNode& other);
unsigned Index; // node index in Parent.Childs
bool m_IsOpen;
JoinType m_jointype;
EndType m_endtype;
PolyNode *GetNextSiblingUp() const;
void AddChild(PolyNode &child);
friend class Clipper; // to access Index
friend class ClipperOffset;
};
class PolyTree : public PolyNode {
public:
~PolyTree() { Clear(); };
PolyNode *GetFirst() const;
void Clear();
int Total() const;
private:
// PolyTree& operator =(PolyTree& other);
PolyNodes AllNodes;
friend class Clipper; // to access AllNodes
};
bool Orientation(const Path &poly);
double Area(const Path &poly);
int PointInPolygon(const IntPoint &pt, const Path &path);
void SimplifyPolygon(const Path &in_poly, Paths &out_polys,
PolyFillType fillType = pftEvenOdd);
void SimplifyPolygons(const Paths &in_polys, Paths &out_polys,
PolyFillType fillType = pftEvenOdd);
void SimplifyPolygons(Paths &polys, PolyFillType fillType = pftEvenOdd);
void CleanPolygon(const Path &in_poly, Path &out_poly, double distance = 1.415);
void CleanPolygon(Path &poly, double distance = 1.415);
void CleanPolygons(const Paths &in_polys, Paths &out_polys,
double distance = 1.415);
void CleanPolygons(Paths &polys, double distance = 1.415);
void MinkowskiSum(const Path &pattern, const Path &path, Paths &solution,
bool pathIsClosed);
void MinkowskiSum(const Path &pattern, const Paths &paths, Paths &solution,
bool pathIsClosed);
void MinkowskiDiff(const Path &poly1, const Path &poly2, Paths &solution);
void PolyTreeToPaths(const PolyTree &polytree, Paths &paths);
void ClosedPathsFromPolyTree(const PolyTree &polytree, Paths &paths);
void OpenPathsFromPolyTree(PolyTree &polytree, Paths &paths);
void ReversePath(Path &p);
void ReversePaths(Paths &p);
struct IntRect {
cInt left;
cInt top;
cInt right;
cInt bottom;
};
// enums that are used internally ...
enum EdgeSide { esLeft = 1, esRight = 2 };
// forward declarations (for stuff used internally) ...
struct TEdge;
struct IntersectNode;
struct LocalMinimum;
struct OutPt;
struct OutRec;
struct Join;
typedef std::vector<OutRec *> PolyOutList;
typedef std::vector<TEdge *> EdgeList;
typedef std::vector<Join *> JoinList;
typedef std::vector<IntersectNode *> IntersectList;
//------------------------------------------------------------------------------
// ClipperBase is the ancestor to the Clipper class. It should not be
// instantiated directly. This class simply abstracts the conversion of sets of
// polygon coordinates into edge objects that are stored in a LocalMinima list.
class ClipperBase {
public:
ClipperBase();
virtual ~ClipperBase();
virtual bool AddPath(const Path &pg, PolyType PolyTyp, bool Closed);
bool AddPaths(const Paths &ppg, PolyType PolyTyp, bool Closed);
virtual void Clear();
IntRect GetBounds();
bool PreserveCollinear() { return m_PreserveCollinear; };
void PreserveCollinear(bool value) { m_PreserveCollinear = value; };
protected:
void DisposeLocalMinimaList();
TEdge *AddBoundsToLML(TEdge *e, bool IsClosed);
virtual void Reset();
TEdge *ProcessBound(TEdge *E, bool IsClockwise);
void InsertScanbeam(const cInt Y);
bool PopScanbeam(cInt &Y);
bool LocalMinimaPending();
bool PopLocalMinima(cInt Y, const LocalMinimum *&locMin);
OutRec *CreateOutRec();
void DisposeAllOutRecs();
void DisposeOutRec(PolyOutList::size_type index);
void SwapPositionsInAEL(TEdge *edge1, TEdge *edge2);
void DeleteFromAEL(TEdge *e);
void UpdateEdgeIntoAEL(TEdge *&e);
typedef std::vector<LocalMinimum> MinimaList;
MinimaList::iterator m_CurrentLM;
MinimaList m_MinimaList;
bool m_UseFullRange;
EdgeList m_edges;
bool m_PreserveCollinear;
bool m_HasOpenPaths;
PolyOutList m_PolyOuts;
TEdge *m_ActiveEdges;
typedef std::priority_queue<cInt> ScanbeamList;
ScanbeamList m_Scanbeam;
};
//------------------------------------------------------------------------------
class Clipper : public virtual ClipperBase {
public:
Clipper(int initOptions = 0);
bool Execute(ClipType clipType, Paths &solution,
PolyFillType fillType = pftEvenOdd);
bool Execute(ClipType clipType, Paths &solution, PolyFillType subjFillType,
PolyFillType clipFillType);
bool Execute(ClipType clipType, PolyTree &polytree,
PolyFillType fillType = pftEvenOdd);
bool Execute(ClipType clipType, PolyTree &polytree, PolyFillType subjFillType,
PolyFillType clipFillType);
bool ReverseSolution() { return m_ReverseOutput; };
void ReverseSolution(bool value) { m_ReverseOutput = value; };
bool StrictlySimple() { return m_StrictSimple; };
void StrictlySimple(bool value) { m_StrictSimple = value; };
// set the callback function for z value filling on intersections (otherwise Z
// is 0)
#ifdef use_xyz
void ZFillFunction(ZFillCallback zFillFunc);
#endif
protected:
virtual bool ExecuteInternal();
private:
JoinList m_Joins;
JoinList m_GhostJoins;
IntersectList m_IntersectList;
ClipType m_ClipType;
typedef std::list<cInt> MaximaList;
MaximaList m_Maxima;
TEdge *m_SortedEdges;
bool m_ExecuteLocked;
PolyFillType m_ClipFillType;
PolyFillType m_SubjFillType;
bool m_ReverseOutput;
bool m_UsingPolyTree;
bool m_StrictSimple;
#ifdef use_xyz
ZFillCallback m_ZFill; // custom callback
#endif
void SetWindingCount(TEdge &edge);
bool IsEvenOddFillType(const TEdge &edge) const;
bool IsEvenOddAltFillType(const TEdge &edge) const;
void InsertLocalMinimaIntoAEL(const cInt botY);
void InsertEdgeIntoAEL(TEdge *edge, TEdge *startEdge);
void AddEdgeToSEL(TEdge *edge);
bool PopEdgeFromSEL(TEdge *&edge);
void CopyAELToSEL();
void DeleteFromSEL(TEdge *e);
void SwapPositionsInSEL(TEdge *edge1, TEdge *edge2);
bool IsContributing(const TEdge &edge) const;
bool IsTopHorz(const cInt XPos);
void DoMaxima(TEdge *e);
void ProcessHorizontals();
void ProcessHorizontal(TEdge *horzEdge);
void AddLocalMaxPoly(TEdge *e1, TEdge *e2, const IntPoint &pt);
OutPt *AddLocalMinPoly(TEdge *e1, TEdge *e2, const IntPoint &pt);
OutRec *GetOutRec(int idx);
void AppendPolygon(TEdge *e1, TEdge *e2);
void IntersectEdges(TEdge *e1, TEdge *e2, IntPoint &pt);
OutPt *AddOutPt(TEdge *e, const IntPoint &pt);
OutPt *GetLastOutPt(TEdge *e);
bool ProcessIntersections(const cInt topY);
void BuildIntersectList(const cInt topY);
void ProcessIntersectList();
void ProcessEdgesAtTopOfScanbeam(const cInt topY);
void BuildResult(Paths &polys);
void BuildResult2(PolyTree &polytree);
void SetHoleState(TEdge *e, OutRec *outrec);
void DisposeIntersectNodes();
bool FixupIntersectionOrder();
void FixupOutPolygon(OutRec &outrec);
void FixupOutPolyline(OutRec &outrec);
bool IsHole(TEdge *e);
bool FindOwnerFromSplitRecs(OutRec &outRec, OutRec *&currOrfl);
void FixHoleLinkage(OutRec &outrec);
void AddJoin(OutPt *op1, OutPt *op2, const IntPoint offPt);
void ClearJoins();
void ClearGhostJoins();
void AddGhostJoin(OutPt *op, const IntPoint offPt);
bool JoinPoints(Join *j, OutRec *outRec1, OutRec *outRec2);
void JoinCommonEdges();
void DoSimplePolygons();
void FixupFirstLefts1(OutRec *OldOutRec, OutRec *NewOutRec);
void FixupFirstLefts2(OutRec *InnerOutRec, OutRec *OuterOutRec);
void FixupFirstLefts3(OutRec *OldOutRec, OutRec *NewOutRec);
#ifdef use_xyz
void SetZ(IntPoint &pt, TEdge &e1, TEdge &e2);
#endif
};
//------------------------------------------------------------------------------
class ClipperOffset {
public:
ClipperOffset(double miterLimit = 2.0, double roundPrecision = 0.25);
~ClipperOffset();
void AddPath(const Path &path, JoinType joinType, EndType endType);
void AddPaths(const Paths &paths, JoinType joinType, EndType endType);
void Execute(Paths &solution, double delta);
void Execute(PolyTree &solution, double delta);
void Clear();
double MiterLimit;
double ArcTolerance;
private:
Paths m_destPolys;
Path m_srcPoly;
Path m_destPoly;
std::vector<DoublePoint> m_normals;
double m_delta, m_sinA, m_sin, m_cos;
double m_miterLim, m_StepsPerRad;
IntPoint m_lowest;
PolyNode m_polyNodes;
void FixOrientations();
void DoOffset(double delta);
void OffsetPoint(int j, int &k, JoinType jointype);
void DoSquare(int j, int k);
void DoMiter(int j, int k, double r);
void DoRound(int j, int k);
};
//------------------------------------------------------------------------------
class clipperException : public std::exception {
public:
clipperException(const char *description) : m_descr(description) {}
virtual ~clipperException() throw() {}
virtual const char *what() const throw() { return m_descr.c_str(); }
private:
std::string m_descr;
};
//------------------------------------------------------------------------------
} // ClipperLib namespace
#endif // clipper_hpp
#include "ocr_engine.hpp"
using namespace ppocr;
int main(int argc, char** argv)
{
std::string det_model_onnx = "../Resource/Models/ppocrv5_server_det_infer.onnx";
std::string rec_model_onnx = "../Resource/Models/ppocrv5_server_rec_infer.onnx";
std::string img_path = "../Resource/Images/20250703205038.png";
std::string character_dict_path = "../Resource/ppocr_keys_v5.txt";
float segm_thres=0.3;
float box_thresh=0.3;
ppOcrEngine ocr_engine(det_model_onnx,
rec_model_onnx,
character_dict_path,
segm_thres,
box_thresh,
true,
"fp32");
cv::Mat img=cv::imread(img_path);
ocr_engine.forward(img);
return 0;
}
\ No newline at end of file
This diff is collapsed.
#pragma once
#include<iostream>
#include <migraphx/program.hpp>
#include <migraphx/onnx.hpp>
#include <migraphx/gpu/target.hpp>
#include <migraphx/quantization.hpp>
#include <hip/hip_runtime_api.h>
#include <opencv2/opencv.hpp>
#include "CommonDefinition.h"
#include "Filesystem.h"
#include "SimpleLog.h"
#include "clipper.h"
namespace ppocr{
struct _TEXT_BOX
{
cv::Rect t_rect;
float score;
};
using T_BOX = struct _TEXT_BOX;
class CTCDecode
{
private:
//inference image
float* data;
std::unordered_map<std::string, migraphx::argument> device_data;
migraphx::program net;
int batch_size;
int net_input_width;
int net_input_height;
int net_input_channel;
bool offload_copy;
std::string precision_mode;
std::unordered_map<std::string, migraphx::argument> dev_argument;
void* input_buffer_device;
void* output_buffer_device;
void* output_buffer_host;
migraphx::shape input_shape;
migraphx::shape output_shape;
std::string input_name;
std::string output_name;
//postprocess: n_channel->model output channel,feature_size--> feature size one channel
int n_channel;
int feature_size;
std::vector<std::string> k_words;
public:
CTCDecode(std::string rec_model_path,
std::string precision_mode="fp32",
int image_width=480,
int image_height=48,
int channel=3,
int batch_size = 1,
bool offload_copy = true,
std::string character_dict_path="./ppocr_keys_v5.txt");
~CTCDecode();
/**
* @brief 字符识别编码,可支持,最长可支持预测90个字符,18385个字符
*/
std::string forward(cv::Mat& img);
private:
/**
* @brief 预处理
* pixel = (src_img*scale-0.5)/0.5;
* scale = 1.0/255
* @param img 字符图片
* @param data 预处理输出
* @param img_w 模型输入宽
* @param img_h 模型输入高
* @return 成功:true,失败:false
*/
bool preproc(cv::Mat img,float* data,int img_w=480,int img_h=48);
/**
* @brief 模型预测后处理,获取每行中概率最大的字符,组成一句长度最大为90个字符的句子,模型预测输出shape=[1,90,18385]
* @param feature model output
* @return 成功:text,失败:""
*/
std::string postprocess(float* feature);
/**
* @brief 解码,将模型预测输出与字符集关联起来
* @param probs 模型预测的最大概率
* @param indexs 模型预测的最大概率的索引值
* @param mean_prob 预测句子的平均概率
* @return 成功:text,失败:""
*/
std::string decode(std::vector<float>& probs,std::vector<int>& indexs,float& mean_prob);
};
class OcrDet
{
private:
std::string precision_mode;
bool offload_copy;
migraphx::program net;
migraphx::shape input_shape;
migraphx::shape output_shape;
std::string input_name;
std::string output_name;
int det_batch_size;
int data_size ;
float segm_thres;
float box_thres;
int net_input_width;
int net_input_height;
int net_input_channel;
float* data;
//Allocate device buffer and host buffer,if offload_copy is false
std::unordered_map<std::string, migraphx::argument> dev_argument;
void* input_buffer_device;
void* output_buffer_device;
void* output_buffer_host;
//postprocess
int n_channel;
int feature_size; //single channel feature map size.
int output_width;
int output_height;
int max_candidates;//maximun number of candidates contours.
public:
OcrDet(std::string det_model_path,
std::string precision_mode="float32",
bool offload_copy = true,
float segm_thres = 0.3,
float box_thresh = 0.7);
~OcrDet();
bool forward(cv::Mat& img,std::vector<std::vector<std::vector<int>>>& text_roi_boxes);
private:
/**
* @brief 预处理
* pixel = (scale*src_img*mean/std);
* scale = 1.0/255
* mean = [0.485, 0.456, 0.406]
* std = [0.229, 0.224, 0.225]
* @param img 字符图片
* @param data 预处理输出
* @return 成功:w,h维度的缩放比例
*/
cv::Size preproc(cv::Mat img,float* data);
/**
* @brief 后处理,通过模型预测的二值图获取文本区域
* @param feature 模型预测tensor(这里字符检测使用了dbnet)
* @param boxes 字符区域坐标
* @return 成功:0,失败:-1
*/
int postprocess(float* feature, std::vector<std::vector<std::vector<int>>> &boxes);
int boxes_from_bitmap(cv::Mat& bit_map,std::vector<T_BOX>& box);
std::vector<std::vector<std::vector<int>>>boxes_from_bitmap(
const cv::Mat pred, const cv::Mat bitmap, const float &box_thresh,
const float &det_db_unclip_ratio, const bool &use_polygon_score);
std::vector<std::vector<float>> Mat2Vector(cv::Mat mat);
/**
* @brief 统计多边形区域的平均得分
* @param contour 字符区域的轮廓点集合
* @param pred 模型预测二值图
* @return score
*/
float polygon_score_acc(std::vector<cv::Point> contour,cv::Mat pred);
/**
* @brief 对模型预测的区域进行向内或向外扩散,扩散比例是unclip_ratio ,目的是找到更加合适的字符区域
* @param box 字符区域坐标
* @param pred 模型预测二值图
* @return 处理后的字符区域
*/
cv::RotatedRect unClip(std::vector<std::vector<float>> box,
const float &unclip_ratio);
/**
* @brief 计算偏移距离
* distance = area * unclip_ratio / dist;
* area = ∑(x_i*y_{i+1} - x_{i+1}*y_i)
* dist = sqrtf(dx * dx + dy * dy)
*
* @param box 字符区域坐标
* @param unclip_ratio 缩放比例
* @param distance 偏移距离
* @return NONE
*/
void get_contour_area(const std::vector<std::vector<float>> &box,
float unclip_ratio, float &distance) ;
/**
* @brief 无效字符区域过滤。首先将boxes映射回原始图像,然后过滤无效区域
* @param boxes 字符区域坐标
* @param ratio_h 垂直方向缩放比例
* @param ratio_w 水平方向缩放比例
* @param srcimg 原始图像
*
* @return 字符区域有效坐标
*/
std::vector<std::vector<std::vector<int>>> filter_det_res(std::vector<std::vector<std::vector<int>>> boxes,
float ratio_h, float ratio_w, cv::Mat srcimg);
/**
* @brief 对字符区域按照从上到下,从左到右的顺序排序
* @param pts 字符区域坐标
*
* @return 字符区域有效坐标
*/
std::vector<std::vector<int>> order_points_clockwise(std::vector<std::vector<int>> pts);
/**
* @brief 获取最小矩形坐标
* @param box 字符区域最小外接矩形的坐标
* @param ssid box的最大边
* @return 字符区域有效坐标
*/
std::vector<std::vector<float>> get_mini_boxes(cv::RotatedRect box,float &ssid) ;
/**
* @brief 计算bitmap上的t_rect区域的平均分数
* @param box_array 模型预测的字符区域
* @param pred 模型预测二值图
* @return score
*/
float box_score_fast(std::vector<std::vector<float>> box_array,cv::Mat pred) ;
void visualize_boxes(const cv::Mat &srcimg,
const std::vector<std::vector<std::vector<int>>> &boxes) ;
bool text_recognition(const cv::Mat &srcimg,
const std::vector<std::vector<std::vector<int>>> &boxes);
};
class ppOcrEngine {
private:
std::shared_ptr<OcrDet> text_detector;
std::shared_ptr<CTCDecode> text_recognizer;
public:
ppOcrEngine(const std::string &det_model_path,
const std::string &rec_model_path,
const std::string &character_dict_path,
const float segm_thres=0.3,
const float box_thresh=0.7,
bool offload_copy =true,
std::string precision_mode = "fp32") ;
~ppOcrEngine();
std::vector<std::string> forward(cv::Mat &srcimg);
};
}
FROM image.sourcefind.cn:5000/dcu/admin/base/migraphx:5.0.0-ubuntu22.04-dtk25.04.1-py3.10
\ No newline at end of file
# 模型唯一标识
modelCode =
# 模型名称
modelName=ppocrv5_migraphx
# 模型描述
modelDescription=ppocrv5
# 应用场景
appScenario=制造,政府,医疗,科研,交通,教育
# 框架类型
frameType=migraphx
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