ryanjay0 / miles-deep Goto Github PK

View Code? Open in Web Editor NEW

2.6K 2.6K 284.0 21.76 MB

Deep Learning Porn Video Classifier/Editor with Caffe

License: GNU General Public License v3.0

Makefile 4.43% C++ 95.57%

miles-deep's People

Contributors

Stargazers

Watchers

Forkers

yanlinaung wavelets loretoparisi amitshah korczis shaoweipng ivan801 nivir number0 alimakki philipz wanjinchang bussiere beckettman kuyun-zhangyang hank-wood lyimage fungosforks lzdjlu homoni hhy5277 zhanganl curtiszimmerman infinith4 fujianhai juno249 benjamesbabala thomasdic2000 mfzhang kk9599 antonini bradparks nivertech lyk125 matrixplayer lol666666 zhengfangwu jianweilin zxqdlenovo anazou akhatri1 cmc1023 ttsvetanov ilucaslee mrpurplz andrewgjohnson-forks coocoky kurumiserori theodoreyin supereagleflying ericxsun wtest wenlihaoyu jarhot1992 zhuhui197 baicwang tanxinwuyu amc1989 ml-lab handsome2734 supermario1990 tourbillon1994 allen-wan aihgf alexbigboy yangwao zhanglei hj3938 lizyyy guoyu07 ezhangle zachlungu kilmas lfthwjx felixbrf wang1ang sdtm1016 renhua devenlu deflated-criossant templeblock muzicstation eaglewei chenziyu2016 wltongxing fireae usingtcnower yingjin-us jinyu0310 jayinai joseroubert08 ikalin harisris aabbcc23 mayotomale zsvanderlaan zino974 walkoncross jzxyouok chenjianjuncjj

miles-deep's Issues

occur error when compile the project. Dose anyone make the project ?

Hi,
Dose anyone make the project ?
I clone the code and follow the instructions to build the envs.
errors as below when I run 'make'
any solution will be appreciated.

root@hxh:/home/hxh/common_use/tools/miles-deep-master# make
g++ -std=c++11 -Wno-sign-compare -Wall -pthread -fPIC -DNDEBUG -O2 -DUSE_OPENCV -o miles-deep *.cpp -Wl,--whole-archive /home/hxh/common_use/caffe/.build_release/lib/libcaffe.a -Wl,--no-whole-archive  -lm -lglog -lopencv_core -lopencv_highgui -lopencv_imgproc -lstdc++ -lhdf5 -lhdf5_hl -lopenblas -I/usr/local/include -I.  -I/home/hxh/common_use/caffe/include \
    -I/usr/local/cuda/include -L/usr/local/cuda/lib64 -lcublas -lcudart -lcurand -lcudnn -DUSE_CUDNN  -L/usr/lib -L/usr/local/lib -L/usr/lib/x86_64-linux-gnu -L/home/hxh/anaconda2/pkgs/hdf5-1.10.1-h9caa474_1/lib /usr/lib/x86_64-linux-gnu/libgflags.a /usr/lib/x86_64-linux-gnu/libboost_thread.a /usr/lib/x86_64-linux-gnu/libboost_system.a /usr/lib/x86_64-linux-gnu/libprotobuf.a 
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(layer_factory.o)：在函数‘__static_initialization_and_destruction_0(int, int) [clone .constprop.245]’中：
layer_factory.cpp:(.text.startup+0x6e)：对‘_Py_NoneStruct’未定义的引用
layer_factory.cpp:(.text.startup+0x44a)：对‘boost::python::converter::registry::lookup(boost::python::type_info)’未定义的引用
layer_factory.cpp:(.text.startup+0x47d)：对‘boost::python::converter::registry::lookup_shared_ptr(boost::python::type_info)’未定义的引用
layer_factory.cpp:(.text.startup+0x485)：对‘boost::python::converter::registry::lookup(boost::python::type_info)’未定义的引用
layer_factory.cpp:(.text.startup+0x4a3)：对‘boost::python::converter::registry::lookup_shared_ptr(boost::python::type_info)’未定义的引用
layer_factory.cpp:(.text.startup+0x4ab)：对‘boost::python::converter::registry::lookup(boost::python::type_info)’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(layer_factory.o)：在函数‘boost::python::detail::returnable<boost::python::api::object>::type boost::python::call<boost::python::api::object, caffe::LayerParameter>(_object*, caffe::LayerParameter const&, boost::type<boost::python::api::object>*)’中：
layer_factory.cpp:(.text._ZN5boost6python4callINS0_3api6objectEN5caffe14LayerParameterEEENS0_6detail10returnableIT_E4typeEP7_objectRKT0_PNS_4typeIS8_EE[_ZN5boost6python4callINS0_3api6objectEN5caffe14LayerParameterEEENS0_6detail10returnableIT_E4typeEP7_objectRKT0_PNS_4typeIS8_EE]+0x2f)：对‘boost::python::converter::detail::arg_to_python_base::arg_to_python_base(void const volatile*, boost::python::converter::registration const&)’未定义的引用
layer_factory.cpp:(.text._ZN5boost6python4callINS0_3api6objectEN5caffe14LayerParameterEEENS0_6detail10returnableIT_E4typeEP7_objectRKT0_PNS_4typeIS8_EE[_ZN5boost6python4callINS0_3api6objectEN5caffe14LayerParameterEEENS0_6detail10returnableIT_E4typeEP7_objectRKT0_PNS_4typeIS8_EE]+0x45)：对‘PyEval_CallFunction’未定义的引用
layer_factory.cpp:(.text._ZN5boost6python4callINS0_3api6objectEN5caffe14LayerParameterEEENS0_6detail10returnableIT_E4typeEP7_objectRKT0_PNS_4typeIS8_EE[_ZN5boost6python4callINS0_3api6objectEN5caffe14LayerParameterEEENS0_6detail10returnableIT_E4typeEP7_objectRKT0_PNS_4typeIS8_EE]+0xa4)：对‘boost::python::throw_error_already_set()’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(layer_factory.o)：在函数‘boost::shared_ptr<caffe::Layer<double> > caffe::GetPythonLayer<double>(caffe::LayerParameter const&)’中：
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x25)：对‘Py_Initialize’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x49)：对‘boost::python::detail::str_base::str_base(char const*)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x54)：对‘boost::python::import(boost::python::str)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x9b)：对‘boost::python::api::getattr(boost::python::api::object const&, char const*)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0xea)：对‘boost::python::converter::rvalue_from_python_stage1(_object*, boost::python::converter::registration const&)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x117)：对‘boost::python::converter::rvalue_from_python_stage2(_object*, boost::python::converter::rvalue_from_python_stage1_data&, boost::python::converter::registration const&)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x2c8)：对‘vtable for boost::python::error_already_set’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x2db)：对‘PyErr_Print’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIdEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x300)：对‘boost::python::error_already_set::~error_already_set()’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(layer_factory.o)：在函数‘boost::shared_ptr<caffe::Layer<float> > caffe::GetPythonLayer<float>(caffe::LayerParameter const&)’中：
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x25)：对‘Py_Initialize’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x49)：对‘boost::python::detail::str_base::str_base(char const*)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x54)：对‘boost::python::import(boost::python::str)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x9b)：对‘boost::python::api::getattr(boost::python::api::object const&, char const*)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0xea)：对‘boost::python::converter::rvalue_from_python_stage1(_object*, boost::python::converter::registration const&)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x117)：对‘boost::python::converter::rvalue_from_python_stage2(_object*, boost::python::converter::rvalue_from_python_stage1_data&, boost::python::converter::registration const&)’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x2c8)：对‘vtable for boost::python::error_already_set’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x2db)：对‘PyErr_Print’未定义的引用
layer_factory.cpp:(.text._ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE[_ZN5caffe14GetPythonLayerIfEEN5boost10shared_ptrINS_5LayerIT_EEEERKNS_14LayerParameterE]+0x300)：对‘boost::python::error_already_set::~error_already_set()’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(layer_factory.o):(.data.DW.ref._ZTIN5boost6python17error_already_setE[DW.ref._ZTIN5boost6python17error_already_setE]+0x0)：对‘typeinfo for boost::python::error_already_set’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(upgrade_proto.o)：在函数‘caffe::UpgradeSnapshotPrefixProperty(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, caffe::SolverParameter*)’中：
upgrade_proto.cpp:(.text+0x19d4)：对‘boost::filesystem::path::replace_extension(boost::filesystem::path const&)’未定义的引用
upgrade_proto.cpp:(.text+0x1af3)：对‘boost::filesystem::detail::status(boost::filesystem::path const&, boost::system::error_code*)’未定义的引用
upgrade_proto.cpp:(.text+0x1b46)：对‘boost::filesystem::path::stem() const’未定义的引用
upgrade_proto.cpp:(.text+0x1b99)：对‘boost::filesystem::path::operator/=(boost::filesystem::path const&)’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDB::Open(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, caffe::db::Mode)’中：
db_leveldb.cpp:(.text+0x104)：对‘leveldb::Options::Options()’未定义的引用
db_leveldb.cpp:(.text+0x146)：对‘leveldb::DB::Open(leveldb::Options const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, leveldb::DB**)’未定义的引用
db_leveldb.cpp:(.text+0x1ef)：对‘leveldb::Status::ToString[abi:cxx11]() const’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDB::NewCursor()’中：
db_leveldb.cpp:(.text._ZN5caffe2db7LevelDB9NewCursorEv[_ZN5caffe2db7LevelDB9NewCursorEv]+0xb9)：对‘leveldb::Status::ToString[abi:cxx11]() const’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDBTransaction::~LevelDBTransaction()’中：
db_leveldb.cpp:(.text._ZN5caffe2db18LevelDBTransactionD2Ev[_ZN5caffe2db18LevelDBTransactionD5Ev]+0x18)：对‘leveldb::WriteBatch::~WriteBatch()’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDBTransaction::~LevelDBTransaction()’中：
db_leveldb.cpp:(.text._ZN5caffe2db18LevelDBTransactionD0Ev[_ZN5caffe2db18LevelDBTransactionD5Ev]+0x18)：对‘leveldb::WriteBatch::~WriteBatch()’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDBTransaction::Put(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)’中：
db_leveldb.cpp:(.text._ZN5caffe2db18LevelDBTransaction3PutERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES9_[_ZN5caffe2db18LevelDBTransaction3PutERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES9_]+0x42)：对‘leveldb::WriteBatch::Put(leveldb::Slice const&, leveldb::Slice const&)’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDB::NewTransaction()’中：
db_leveldb.cpp:(.text._ZN5caffe2db7LevelDB14NewTransactionEv[_ZN5caffe2db7LevelDB14NewTransactionEv]+0x48)：对‘leveldb::WriteBatch::WriteBatch()’未定义的引用
db_leveldb.cpp:(.text._ZN5caffe2db7LevelDB14NewTransactionEv[_ZN5caffe2db7LevelDB14NewTransactionEv]+0xea)：对‘leveldb::WriteBatch::~WriteBatch()’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_leveldb.o)：在函数‘caffe::db::LevelDBTransaction::Commit()’中：
db_leveldb.cpp:(.text._ZN5caffe2db18LevelDBTransaction6CommitEv[_ZN5caffe2db18LevelDBTransaction6CommitEv]+0x74)：对‘leveldb::Status::ToString[abi:cxx11]() const’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDBTransaction::DoubleMapSize()’中：
db_lmdb.cpp:(.text+0x155)：对‘mdb_env_info’未定义的引用
db_lmdb.cpp:(.text+0x177)：对‘mdb_env_set_mapsize’未定义的引用
db_lmdb.cpp:(.text+0x1da)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0x25a)：对‘mdb_strerror’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDB::Open(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, caffe::db::Mode)’中：
db_lmdb.cpp:(.text+0x328)：对‘mdb_env_create’未定义的引用
db_lmdb.cpp:(.text+0x364)：对‘mdb_env_open’未定义的引用
db_lmdb.cpp:(.text+0x466)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0x4ec)：对‘mdb_strerror’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDBTransaction::Commit()’中：
db_lmdb.cpp:(.text+0x675)：对‘mdb_txn_begin’未定义的引用
db_lmdb.cpp:(.text+0x69c)：对‘mdb_dbi_open’未定义的引用
db_lmdb.cpp:(.text+0x752)：对‘mdb_put’未定义的引用
db_lmdb.cpp:(.text+0x7a5)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0x806)：对‘mdb_txn_commit’未定义的引用
db_lmdb.cpp:(.text+0x834)：对‘mdb_dbi_close’未定义的引用
db_lmdb.cpp:(.text+0x8a6)：对‘mdb_txn_abort’未定义的引用
db_lmdb.cpp:(.text+0x8b3)：对‘mdb_dbi_close’未定义的引用
db_lmdb.cpp:(.text+0x926)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0x9a4)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0xa39)：对‘mdb_strerror’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDB::NewCursor()’中：
db_lmdb.cpp:(.text+0xb2e)：对‘mdb_txn_begin’未定义的引用
db_lmdb.cpp:(.text+0xb54)：对‘mdb_dbi_open’未定义的引用
db_lmdb.cpp:(.text+0xb7c)：对‘mdb_cursor_open’未定义的引用
db_lmdb.cpp:(.text+0xbd1)：对‘mdb_cursor_get’未定义的引用
db_lmdb.cpp:(.text+0xc5e)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0xcdc)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0xd5a)：对‘mdb_strerror’未定义的引用
db_lmdb.cpp:(.text+0xdd7)：对‘mdb_strerror’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDBCursor::~LMDBCursor()’中：
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursorD2Ev[_ZN5caffe2db10LMDBCursorD5Ev]+0x17)：对‘mdb_cursor_close’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursorD2Ev[_ZN5caffe2db10LMDBCursorD5Ev]+0x20)：对‘mdb_txn_abort’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDB::Close()’中：
db_lmdb.cpp:(.text._ZN5caffe2db4LMDB5CloseEv[_ZN5caffe2db4LMDB5CloseEv]+0x11)：对‘mdb_dbi_close’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db4LMDB5CloseEv[_ZN5caffe2db4LMDB5CloseEv]+0x1a)：对‘mdb_env_close’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDBCursor::~LMDBCursor()’中：
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursorD0Ev[_ZN5caffe2db10LMDBCursorD5Ev]+0x17)：对‘mdb_cursor_close’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursorD0Ev[_ZN5caffe2db10LMDBCursorD5Ev]+0x20)：对‘mdb_txn_abort’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDB::~LMDB()’中：
db_lmdb.cpp:(.text._ZN5caffe2db4LMDBD2Ev[_ZN5caffe2db4LMDBD5Ev]+0x22)：对‘mdb_dbi_close’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db4LMDBD2Ev[_ZN5caffe2db4LMDBD5Ev]+0x2b)：对‘mdb_env_close’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDB::~LMDB()’中：
db_lmdb.cpp:(.text._ZN5caffe2db4LMDBD0Ev[_ZN5caffe2db4LMDBD5Ev]+0x1f)：对‘mdb_dbi_close’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db4LMDBD0Ev[_ZN5caffe2db4LMDBD5Ev]+0x28)：对‘mdb_env_close’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDBCursor::Next()’中：
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursor4NextEv[_ZN5caffe2db10LMDBCursor4NextEv]+0x2d)：对‘mdb_cursor_get’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursor4NextEv[_ZN5caffe2db10LMDBCursor4NextEv]+0xa8)：对‘mdb_strerror’未定义的引用
/home/hxh/common_use/caffe/.build_release/lib/libcaffe.a(db_lmdb.o)：在函数‘caffe::db::LMDBCursor::SeekToFirst()’中：
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursor11SeekToFirstEv[_ZN5caffe2db10LMDBCursor11SeekToFirstEv]+0x2a)：对‘mdb_cursor_get’未定义的引用
db_lmdb.cpp:(.text._ZN5caffe2db10LMDBCursor11SeekToFirstEv[_ZN5caffe2db10LMDBCursor11SeekToFirstEv]+0xa8)：对‘mdb_strerror’未定义的引用
collect2: error: ld returned 1 exit status
Makefile:35: recipe for target 'miles-deep' failed
make: *** [miles-deep] Error 1

测试失败

ubuntu@ubuntu:~/miles-deep$ ./miles-deep -t blowjob_handjob test.mp4
Targets: [blowjob_handjob]
Waiting for: /tmp/screenshots/img_00001.jpg
Label not found in list: blowjob_handjob

It happens whichever way I use it, but for the sake of simplicity.
./miles-deep -v 0.75 vid.mp4
I've also noticed minimum scores are being ignored.
./miles-deep -s 0.75 vid.mp4
I've even gone so far as to modify line 369 and 370 in miles-deep.cpp to 0.75 and recompile.
Not sure whats going on here.

Blowjobs and Handjobs Should Not Be Tagged By The Same Label

At this moment miles-deep seperates porn by:

Blowjob AND Handjob
Cunnilingus
sex_back
sex_front
titfuck
other

I think there is a big difference between blowjobs and handjobs and therefore they should be tagged separately.

low accuracy?

hi @ryanjay0 , thanks for so awesome project. After I compiled(using the same version caffe ,models as this project) and tested, it seems that the model is low accuracy.
eg. most porn image are mis-classified as 'other' class(ie. non-sexual) but in fact they are 'titfuck' or 'blowjob_handjob' [1]

what are the situations behind your training data? what size, full nude, strict definitions of categories .... etc

Pardon me if the image below is looked uncomfortable (but I think it's a must to illustrate the problem mentioned above)
[1]

Did you use any public dataset to train the model?

As the title, just curious.

Can't reach you on mail

Hello, sorry for insistence, I wrote you to gmail several days ago but can't get if it reached you or not. Please let me know how can I contact you.

Best regards.

It does not detect midget porn

What the title says.

About the training set.

Due to my current work is also about this area,can you share your training set(maybe a secret link)with me?
Thank you:)

Question

Hey ryanjay0,

There is a port of caffe for Windows. Would you be able to use that, not as a module but as an external program?

I have it working perfectly. Let me know and I will direct you to it, if it's usable.

I have been trying to compile your tool for Windows, both with Cygwin, MingW and other tools, without luck.

run with the command "./miles-deep-cpu -x 1.WMV" ,occur a error

Targets: [blowjob_handjob, cunnilingus, sex_back, sex_front, titfuck]
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Waiting for: /tmp/screenshots/img_00032.jpg
Error making directory: /tmp/cuts

classifies one frame at a time?

Hi,

does miles-deep classify each frame at a time individually or does it use the temporal information (treats it as a sequence of images)?

How to install

Caffe model running out of libido

Running into an error with the caffe model training step here - it appears the caffe model is becoming dehydrated and starts lagging. The output logs mention low stamina but I'm not sure if that's a race condition or something else. Increasing the input training set seems to only make it worse, and my computer starts making strange noises that I can only equate to an ox reaching pure exhaustion.

Passing --use-arm=left doesn't seem to help, either.

This starts happening after a low as 4, maybe 5 videos and gets really bad after the first 30. Is there a way to remedy this and increase Caffe's overall performance?

the purpose of the project

Hi
you are a professional in your field.
i just wonder what is the purpose of classifying these scenes. what is the benefit that will return to the world and humanity of that kind of classifying ?
do you want to filter these scenes or increase it ?
Thanks

Training data for the class of 'other'

Hi!
For 6-classes training dataset, i know 5 classes except 'other' are porn images, then the data of class 'other' mainly includes what kind images? There are so many kinds of images can be not porngraphic.

Thank you!

5

Uploading miles-deep-0.4.tar.gz…
Uploading model.v0.1 (1).tar.gz…

Translation to Tf.Keras?

Awesome ideas! Just wondering if this could be translated into tensorflow.keras model?
Thanks!

Do not concatenate

It would be nice if there was an option to output each cut independently instead of having to grab them from /tmp/cuts/ before final output.

Export to Excel

This is not an issue but a request for an enhancement.

Would it be possible to export the results of a complete scan of multiple hard drives to a comma delimited file? Like this:

About train_val.prototxt

Hi!
Thanks for opening such an interesting model.

I have done some test about the opened model, and it turned out that the model is good when recognizing sex act images, but it can't recognize nudity picture well.
I want to add some new class like "nudity pictures", so can you share the train_val.prototxt and give some details on how to train the model?

My email is [email protected].
Thank you very nuch!

Why you make the test on training samples?

i am not quite understand how you make your test on your model.
you said "The training database consists of 36,000 (and 2500 test images) images" and "tested on 2500 training images"?
i guess you test your model on the training set and got a result with accuracy 95.7, but i want to know the result on other dataset.
if i understand wrong please tell me.

Automatic Tagging of Videos

I would like to use your project and integrate it with my recommendation system.

It will be really nice if you implement "auto-tagging" functionality.

Do you have any plans for implementing this?

Can this model be used for simple NSFW/SFW prediction?

Thanks a lot for doing this. Your model seems like the best candidate for improving my application.

I considered using Yahoo's Open NSFW model, but since it's limited to images, I figured this was a better option. label.txt indicates this is for classifying within NSFW specifically. If you could support binary classification on both images and videos (short gifs mainly), I'd be indebted!

Also have some ideas on scraping for a dataset if you're interested.

Trying to contact you through email.

Hi,

I tried contacting you through email (in the readme.md file). Did you received my message?

Current status?

Thanks for sharing this work =).

Just curious - what is the current status of the project? Are you interesting in updating it to say, Caffe2, or trying it with TF again?

Any chance you're OK sharing the original data-set used for training? (I sent an email to the email in the README).

miles-deep: command not found

Hi, thank you for your sharing~,and i just follow the install instruction to setup this package,i think i have done any things needed,but i still encounter follow problem:
~/miles-deep$ ls
caffe images Makefile.caffe model util.cpp
cut_movie.cpp LICENSE miles-deep README.md util.hpp
cut_movie.hpp Makefile miles-deep.cpp safe.mkv
~/miles-deep$ miles-deep -x safe.mkv
miles-deep: command not found

can you give me some advise? Thank you in advance~

please

Thank you for your interesting project at first!
But I found that is hard to me how to get related pictures.
how can i get your DataSet ?
my email is [email protected].
Thanks a lot !

Recommend Projects

React

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

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

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.