liusifei / face_parsing_2016 Goto Github PK

View Code? Open in Web Editor NEW

77.0 77.0 18.0 21.87 MB

Faster model for Multi-Objective Convolutional Learning for Face Labeling

Home Page: https://www.sifeiliu.net/face-parsing

CMake 1.17% Makefile 0.28% C++ 80.74% Cuda 9.95% Shell 0.34% Python 6.73% MATLAB 0.78% M 0.01%

face_parsing_2016's People

Contributors

Stargazers

Watchers

Forkers

caomw liuguoyou vsooda haiyang21 valkure-yip zhf459 xianghan228 fbi0817 pinglmlcv amanmeetgarg vzhangmeng726 klqulei peterzs lzh990711 liyinglr yueyedeai liulisixin irfanazhar

face_parsing_2016's Issues

Caffe Layer Parameter has no field named resize param

I'm getting the following error when i'm trying to use the prototxt file. google.protobuf.text_format.ParseError: 911:3 : Message type "caffe.LayerParameter" has no field named "resize_param". I want to be able to convert the given model and prototxt to keras.

run_demo.m matlab与gcc版本不匹配

环境：Ubuntu:16.04 CUDA: 9.1 gcc/g++: 5.4 Matlab: 2017b
运行run_demo.m时报错：
Missing symbol
'ZNSt7__cxx1112basic_stringIwSt11char_traitsIwESaIwEE12_M_constructEmw'
required by
'/usr/lib/x86_64-linux-gnu/libboost_python-py27.so.1.58.0->/home/lyf/git-repo/Face_Parsing_2016/matlab/+caffe/private/caffe.mexa64'
Missing symbol
'ZNSt7__cxx1112basic_stringIwSt11char_traitsIwESaIwEE9_M_createERmm'
required by
'/usr/lib/x86_64-linux-gnu/libboost_python-py27.so.1.58.0->/home/lyf/git-repo/Face_Parsing_2016/matlab/+caffe/private/caffe.mexa64'.
Error in caffe.get_net (line 27)
hNet = caffe_('get_net', model_file, phase_name);
Error in caffe.Net (line 31)
self = caffe.get_net(varargin{:});
Error in run_demo (line 21)
net_ = caffe.Net(testproto, trainedmodel,'train');
怀疑是gcc和matlab版本不匹配，但是将gcc切换为4.8/4.9均会报其他编译错误，而matlab不支持gcc5.4.
OK,一句命令解决了：export LD_PRELOAD=$LD_PRELOAD:/usr/lib/x86_64-linux-gnu/libstdc++.so.6:/usr/lib/x86_64-linux-gnu/libprotobuf.so.9

what's the purpose of edge_balance ?

Hi,

What is the purpose of edge_balance ?

no training model

Hi sifei,
Are there any ways to get training model?
I can't find face_parsing_v1_iter_20800.caffemodel and face_parsing_v1_test.prototxt

inference time

Hi,
Thanks for sharing this code.
Since I don't have MATLAB to play with it, I'd like to know the processing time (inference time) that would take for a test image ?

Thanks in advance,

how to train the model

@Liusifei hi, sifei, could you give some instructions and necessary files to train the models? such as the "AlignedImages_helen " ?

Can you transform this project in python?

Hi,did you know how to get the mean_shap.mat？I find the same problem.

I saw the "meanshape.mat" that you uploaded. It seems that there was a same "meanshape.mat" before, and it is match to the "run_demo.m". But the problem is that I can get a good result using your meanshape.mat and image "56.jpg". However when I want to parse my own image, I can only get the my own meanshape.mat like: 227.877089985418 399.676893964180 392.914917072870 407.590902848304 289.034926826012 510.745893120704 235.884287987975 564.034451229388 387.794255212460 566.046032186108(I use this method: http://mmlab.ie.cuhk.edu.hk/archive/CNN_FacePoint.htm). The coordinate origin is the upper left corner of the image and all number are positive(and very large). But your "meanshape.mat" has negative numbers and the values are small. And I can't get a good result with my own "meanshape.mat". So I want to know how can I transfer my data to yours?

Thank you very much.
@Liusifei

Originally posted by @dadaduoduo in #5 (comment)

Inference without shape priors ? Does it change anything ?

Hi sifei,

In which place the non-parametric priors are included as a complementary channels (as it was introduced in the paper) ?

Because as I saw in run_demo.m, the inference is done only using the aligned image channels.

Thanks for your help,

How to get mean_shape.mat?

Hi sifei,
I get the coordinate of 5 key points of a face image, but it is like (200,350). I notice that your data is like (-22,20). I want to know how can I get the data like yours.
Thank you very much.

build error: libcaffe.so: undefined reference to `google::protobuf

I build an official caffe without errors following this Ubuntu-16.04-or-15.10-Installation-Guide, but failed this repo with errors below, strange~ 😭

CXX/LD -o .build_release/tools/device_query.bin                                                                                                [32/1808]
CXX tools/finetune_net.cpp
CXX/LD -o .build_release/tools/finetune_net.bin
CXX tools/upgrade_net_proto_text.cpp
CXX/LD -o .build_release/tools/upgrade_net_proto_text.bin.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::AssignDescriptors(std::__cxx11::basic_string<char, std::char_traits<
char>, std::allocator<char> > const&, google::protobuf::internal::MigrationSchema const*, google::protobuf::Message const* const*, unsigned int const*, 
google::protobuf::MessageFactory*, google::protobuf::Metadata*, google::protobuf::EnumDescriptor const**, google::protobuf::ServiceDescriptor const**)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::WireFormatLite::WriteFloatArray(float const*, int, google::protobuf:
:io::CodedOutputStream*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::ReadVarint64Fallback()'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::IncrementRecursionDepthAndPushLimit(int)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::WireFormatLite::Int32Size(google::protobuf::RepeatedField<int> const
&)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::WireFormat::ReadPackedEnumPreserveUnknowns(google::protobuf::io::Cod
edInputStream*, unsigned int, bool (*)(int), google::protobuf::UnknownFieldSet*, google::protobuf::RepeatedField<int>*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::ReadVarint32Fallback(unsigned int)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::RegisterAllTypes(google::protobuf::Metadata const*, int)
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedOutputStream::WriteVarint32SlowPath(unsigned int)'          [14/1808]
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::InitProtobufDefaults()'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::SkipFallback(int, int)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::Arena::OnArenaAllocation(std::type_info const*, unsigned long) const'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::ArenaImpl::AddCleanup(void*, void (*)(void*))'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::WireFormatLite::WriteDoubleArray(double const*, int, google::protobu
f::io::CodedOutputStream*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::ReadVarintSizeAsIntFallback()'
.build_release/lib/libcaffe.so: undefined reference to `void caffe::ResizeBlob_gpu<float>(caffe::Blob<float> const*, caffe::Blob<float>*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::RepeatedPtrFieldBase::InternalExtend(int)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::WireFormatLite::UInt32Size(google::protobuf::RepeatedField<unsigned 
int> const&)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::ArenaImpl::AllocateAlignedAndAddCleanup(unsigned long, void (*)(void
*))'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::OnShutdownDestroyMessage(void const*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::DecrementRecursionDepthAndPopLimit(int)'
.build_release/lib/libcaffe.so: undefined reference to `void caffe::ResizeBlob_gpu<double>(caffe::Blob<double> const*, caffe::Blob<double>*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedOutputStream::WriteVarint64SlowPath(unsigned long)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::DecrementRecursionDepthAndPopLimit(int)'
.build_release/lib/libcaffe.so: undefined reference to `void caffe::ResizeBlob_gpu<double>(caffe::Blob<double> const*, caffe::Blob<double>*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedOutputStream::WriteVarint64SlowPath(unsigned long)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::OnShutdownDestroyString(std::__cxx11::basic_string<char, std::char_t
raits<char>, std::allocator<char> > const*)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::fixed_address_empty_string[abi:cxx11]'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::Message::SpaceUsedLong() const'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::internal::ArenaImpl::AllocateAligned(unsigned long)'
.build_release/lib/libcaffe.so: undefined reference to `google::protobuf::io::CodedInputStream::ReadTagFallback(unsigned int)'
collect2: error: ld returned 1 exit status
Makefile:617: recipe for target '.build_release/tools/upgrade_net_proto_text.bin' failed
make: *** [.build_release/tools/upgrade_net_proto_text.bin] Error 1

Any suggestions? Thanks in advance. 😭

How to achieve the code

i use matlab2016 to achieve the code ,but meet some issues

MultiHelen_v1 data

Hi sifei,

I want train the helen model, but I can't find MultiHelen_v1.dat. Can you add this data, or can you show us how to generate this file?

thank you.

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.