Giter VIP home page Giter VIP logo

mtcnn-accelerate-onet's Introduction

MTCNN-caffe

MTCNN Face Detection & Alignment This is a C++ version used Caffe

half model shrink the orignal onet by half quantities of parameters with faster forward computing and similar results on fddb you can try different thresholds and minsize value to perform best on your own datasets

Results

image image image image image image image image

mtcnn-accelerate-onet's People

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

mtcnn-accelerate-onet's Issues

Just three models

hello, i m new to mtcnn.
I noted that the origin version has four models(), the last one is named L-net. I guess L-net is used to generate five points on the face(face alignment). But in your repo you just have three models and show some pictures have landmarks. So, my question is, without L-net also can generate five points?

how to use you project?????

/usr/bin/ld: CMakeFiles/MTCNN.dir/mtcnn.cpp.o: undefined reference to symbol '_ZN6google4base21CheckOpMessageBuilder7ForVar2Ev'
//usr/local/lib/libglog.so.0: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
CMakeFiles/MTCNN.dir/build.make:142: recipe for target 'MTCNN' failed
make[2]: *** [MTCNN] Error 1
CMakeFiles/Makefile2:67: recipe for target 'CMakeFiles/MTCNN.dir/all' failed
make[1]: *** [CMakeFiles/MTCNN.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2

This project requires Nvidia GPU to work?

I get the following error during compilation:

/home/user/caffe/build/install/include/caffe/util/device_alternate.hpp:34:10: fatal error: 'cublas_v2.h' file not found
#include <cublas_v2.h>
         ^~~~~~~~~~~~~
1 error generated.

Thanks.

test speed

Hi, these day i test the mode with camera.
my compute GTX760
640480 ~80ms GPU minSize 40 threshold:: 0.7f, 0.6f, 0.6f
GTX1080Ti
640
480 ~66ms GPU minSize 40 threshold:: 0.7f, 0.6f, 0.6f
66ms is a little low.
how can i improve the algorithm to accelerate the detect expect for resize Image

training data

To achieve your retrained model's accuracy, how many training data you used for each net?

how to build your project?

your readme file is not comment about how to build,can you share your build process?because when i compile your mtcnn.cpp file ,there are some errors:
/tmp/cc7DRBwV.o:在函数‘MTCNN::GenerateBBox(caffe::Blob, caffe::Blob, float, float)’中:
mtcnn.cpp:(.text+0xd93):对‘caffe::Blob::cpu_data() const’未定义的引用
mtcnn.cpp:(.text+0xdbb):对‘caffe::Blob::cpu_data() const’未定义的引用
/tmp/cc7DRBwV.o:在函数‘MTCNN::MTCNN(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&)’中:
mtcnn.cpp:(.text+0x112d):对‘caffe::Net::Net(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, caffe::Phase, int, std::vector<std::__cxx11::basic_string<char, std::char_traits, std::allocator >, std::allocator<std::__cxx11::basic_string<char, std::char_traits, std::allocator > > > const*)’未定义的引用
mtcnn.cpp:(.text+0x1190):对‘caffe::Net::CopyTrainedLayersFrom(std::__cxx11::basic_string<char, std::char_traits, std::allocator >)’未定义的引用
mtcnn.cpp:(.text+0x11ec):对‘caffe::Net::Net(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, caffe::Phase, int, std::vector<std::__cxx11::basic_string<char, std::char_traits, std::allocator >, std::allocator<std::__cxx11::basic_string<char, std::char_traits, std::allocator > > > const*)’未定义的引用
mtcnn.cpp:(.text+0x1257):对‘caffe::Net::CopyTrainedLayersFrom(std::__cxx11::basic_string<char, std::char_traits, std::allocator >)’未定义的引用
mtcnn.cpp:(.text+0x12ad):对‘caffe::Net::Net(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&, caffe::Phase, int, std::vector<std::__cxx11::basic_string<char, std::char_traits, std::allocator >, std::allocator<std::__cxx11::basic_string<char, std::char_traits, std::allocator > > > const*)’未定义的引用
mtcnn.cpp:(.text+0x130f):对‘caffe::Net::CopyTrainedLayersFrom(std::__cxx11::basic_string<char, std::char_traits, std::allocator >)’未定义的引用
mtcnn.cpp:(.text+0x1394):对‘google::LogMessageFatal::LogMessageFatal(char const*, int)’未定义的引用
mtcnn.cpp:(.text+0x13a8):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text+0x1403):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text+0x14dc):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘MTCNN::ProposalNet(cv::Mat const&, int, float, float)’中:
mtcnn.cpp:(.text+0x182a):对‘cv::resize(cv::_InputArray const&, cv::OutputArray const&, cv::Size, double, double, int)’未定义的引用
mtcnn.cpp:(.text+0x1872):对‘caffe::Blob::Reshape(int, int, int, int)’未定义的引用
mtcnn.cpp:(.text+0x1889):对‘caffe::Net::Reshape()’未定义的引用
mtcnn.cpp:(.text+0x1898):对‘caffe::Blob::mutable_cpu_data()’未定义的引用
mtcnn.cpp:(.text+0x1a5e):对‘caffe::Net::Forward(float*)’未定义的引用
mtcnn.cpp:(.text+0x1ab3):对‘caffe::Net::blob_by_name(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
mtcnn.cpp:(.text+0x1b4b):对‘caffe::Net::blob_by_name(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
/tmp/cc7DRBwV.o:在函数‘MTCNN::NextStage(cv::Mat const&, std::vector<FaceInfo, std::allocator >&, int, int, int, float)’中:
mtcnn.cpp:(.text+0x1fa5):对‘caffe::Blob::Reshape(int, int, int, int)’未定义的引用
mtcnn.cpp:(.text+0x1fc0):对‘caffe::Net::Reshape()’未定义的引用
mtcnn.cpp:(.text+0x201f):对‘caffe::Blob::Reshape(int, int, int, int)’未定义的引用
mtcnn.cpp:(.text+0x203a):对‘caffe::Net::Reshape()’未定义的引用
mtcnn.cpp:(.text+0x204a):对‘caffe::Blob::mutable_cpu_data()’未定义的引用
mtcnn.cpp:(.text+0x21e8):对‘cv::resize(cv::_InputArray const&, cv::OutputArray const&, cv::Size, double, double, int)’未定义的引用
mtcnn.cpp:(.text+0x22ee):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text+0x22fd):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text+0x230c):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text+0x24e2):对‘caffe::Net::Forward(float*)’未定义的引用
mtcnn.cpp:(.text+0x253b):对‘caffe::Net::blob_by_name(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
mtcnn.cpp:(.text+0x25d7):对‘caffe::Net::blob_by_name(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
mtcnn.cpp:(.text+0x263f):对‘caffe::Net::Forward(float*)’未定义的引用
mtcnn.cpp:(.text+0x2698):对‘caffe::Net::blob_by_name(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
mtcnn.cpp:(.text+0x2734):对‘caffe::Net::blob_by_name(std::_cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
mtcnn.cpp:(.text+0x27d0):对‘caffe::Net::blob_by_name(std::cxx11::basic_string<char, std::char_traits, std::allocator > const&) const’未定义的引用
mtcnn.cpp:(.text+0x2823):对‘caffe::Blob::cpu_data() const’未定义的引用
mtcnn.cpp:(.text+0x2839):对‘caffe::Blob::cpu_data() const’未定义的引用
mtcnn.cpp:(.text+0x2864):对‘caffe::Blob::cpu_data() const’未定义的引用
mtcnn.cpp:(.text+0x2b75):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘main’中:
mtcnn.cpp:(.text+0x391e):对‘cv::imread(cv::String const&, int)’未定义的引用
mtcnn.cpp:(.text+0x3941):对‘cv::getTickCount()’未定义的引用
mtcnn.cpp:(.text+0x399b):对‘cv::getTickCount()’未定义的引用
mtcnn.cpp:(.text+0x39b9):对‘cv::getTickFrequency()’未定义的引用
mtcnn.cpp:(.text+0x3c12):对‘cv::rectangle(cv::Mat&, cv::Rect
, cv::Scalar
const&, int, int, int)’未定义的引用
mtcnn.cpp:(.text+0x3d6c):对‘cv::circle(cv::InputOutputArray const&, cv::Point, int, cv::Scalar
const&, int, int, int)’未定义的引用
mtcnn.cpp:(.text+0x3e4a):对‘cv::imwrite(cv::String const&, cv::_InputArray const&, std::vector<int, std::allocator > const&)’未定义的引用
mtcnn.cpp:(.text+0x3edb):对‘cv::imshow(cv::String const&, cv::_InputArray const&)’未定义的引用
mtcnn.cpp:(.text+0x3f03):对‘cv::waitKey(int)’未定义的引用
/tmp/cc7DRBwV.o:在函数‘__static_initialization_and_destruction_0(int, int)’中:
mtcnn.cpp:(.text+0x428b):对‘boost::system::generic_category()’未定义的引用
mtcnn.cpp:(.text+0x4297):对‘boost::system::generic_category()’未定义的引用
mtcnn.cpp:(.text+0x42a3):对‘boost::system::system_category()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘caffe::Caffe::set_mode(caffe::Caffe::Brew)’中:
mtcnn.cpp:(.text._ZN5caffe5Caffe8set_modeENS0_4BrewE[_ZN5caffe5Caffe8set_modeENS0_4BrewE]+0xc):对‘caffe::Caffe::Get()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::String::String(char const*)’中:
mtcnn.cpp:(.text._ZN2cv6StringC2EPKc[_ZN2cv6StringC5EPKc]+0x4d):对‘cv::String::allocate(unsigned long)’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::String::~String()’中:
mtcnn.cpp:(.text._ZN2cv6StringD2Ev[_ZN2cv6StringD5Ev]+0x14):对‘cv::String::deallocate()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::String::operator=(cv::String const&)’中:
mtcnn.cpp:(.text.ZN2cv6StringaSERKS0[ZN2cv6StringaSERKS0]+0x28):对‘cv::String::deallocate()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::Mat::~Mat()’中:
mtcnn.cpp:(.text._ZN2cv3MatD2Ev[_ZN2cv3MatD5Ev]+0x39):对‘cv::fastFree(void*)’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::Mat::clone() const’中:
mtcnn.cpp:(.text._ZNK2cv3Mat5cloneEv[_ZNK2cv3Mat5cloneEv]+0x4e):对‘cv::Mat::copyTo(cv::_OutputArray const&) const’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::Mat::release()’中:
mtcnn.cpp:(.text._ZN2cv3Mat7releaseEv[ZN2cv3Mat7releaseEv]+0x4b):对‘cv::Mat::deallocate()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::Mat::operator()(cv::Rect
const&) const’中:
mtcnn.cpp:(.text._ZNK2cv3MatclERKNS_5Rect_IiEE[ZNK2cv3MatclERKNS_5Rect_IiEE]+0x27):对‘cv::Mat::Mat(cv::Mat const&, cv::Rect const&)’未定义的引用
/tmp/cc7DRBwV.o:在函数‘cv::String::String(std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&)’中:
mtcnn.cpp:(.text._ZN2cv6StringC2ERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE[_ZN2cv6StringC5ERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE]+0x69):对‘cv::String::allocate(unsigned long)’未定义的引用
/tmp/cc7DRBwV.o:在函数‘caffe::Blob::offset(int, int, int, int) const’中:
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x99):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0xa5):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0xb1):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x11f):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x12b):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x137):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x1a2):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x1ae):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x1ba):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x228):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x234):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x240):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x2ab):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x2b7):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x2c3):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x331):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x33d):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x349):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x3b4):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x3c0):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x3cc):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x43a):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x446):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x452):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x4c9):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x4d5):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x4e1):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x4ed):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
/tmp/cc7DRBwV.o:mtcnn.cpp:(.text._ZNK5caffe4BlobIfE6offsetEiiii[_ZNK5caffe4BlobIfE6offsetEiiii]+0x4f9): 跟着更多未定义的参考到 google::LogMessageFatal::~LogMessageFatal()
/tmp/cc7DRBwV.o:在函数‘std::__cxx11::basic_string<char, std::char_traits, std::allocator >* google::MakeCheckOpString<int, int>(int const&, int const&, char const*)’中:
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x33):对‘google::base::CheckOpMessageBuilder::CheckOpMessageBuilder(char const*)’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x5d):对‘google::base::CheckOpMessageBuilder::ForVar2()’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x7b):对‘google::base::CheckOpMessageBuilder::NewStringabi:cxx11’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x8a):对‘google::base::CheckOpMessageBuilder::~CheckOpMessageBuilder()’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIiiEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0xad):对‘google::base::CheckOpMessageBuilder::~CheckOpMessageBuilder()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘caffe::Blob::LegacyShape(int) const’中:
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x83):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x8f):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0xa8):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x107):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x113):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x11f):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x17e):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x18a):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x196):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x1ff):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x20b):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE11LegacyShapeEi[_ZNK5caffe4BlobIfE11LegacyShapeEi]+0x217):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘std::__cxx11::basic_string<char, std::char_traits, std::allocator >* google::MakeCheckOpString<bool, bool>(bool const&, bool const&, char const*)’中:
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x33):对‘google::base::CheckOpMessageBuilder::CheckOpMessageBuilder(char const*)’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x5d):对‘google::base::CheckOpMessageBuilder::ForVar2()’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x7b):对‘google::base::CheckOpMessageBuilder::NewStringabi:cxx11’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0x8a):对‘google::base::CheckOpMessageBuilder::~CheckOpMessageBuilder()’未定义的引用
mtcnn.cpp:(.text._ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc[_ZN6google17MakeCheckOpStringIbbEEPNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKT_RKT0_PKc]+0xad):对‘google::base::CheckOpMessageBuilder::~CheckOpMessageBuilder()’未定义的引用
/tmp/cc7DRBwV.o:在函数‘caffe::Blob::CanonicalAxisIndex(int) const’中:
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0xaa):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0xb6):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0x115):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0x1a2):对‘google::LogMessageFatal::LogMessageFatal(char const*, int, google::CheckOpString const&)’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0x1ae):对‘google::LogMessage::stream()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0x20d):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0x248):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
mtcnn.cpp:(.text._ZNK5caffe4BlobIfE18CanonicalAxisIndexEi[_ZNK5caffe4BlobIfE18CanonicalAxisIndexEi]+0x26e):对‘google::LogMessageFatal::~LogMessageFatal()’未定义的引用
collect2: error: ld returned 1 exit status

i don't know how to solve it.thank you! @blankWorld
my OS:ubuntu16.04

Face Alignment

Can I know if the code does face alignment after face recognition.
If so, can I know the location where the code for face alignment starts

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.