rock-100/facekit

[CVPR 2018] Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

Real-Time Rotation-Invariant Face Detection and Tracking

Face Warping

Face Smoothing

Face Color Transfer

License

This code is distributed under the BSD 2-Clause license.

facekit's Issues

how to run the demo on gpu?

hi, jack-cv, I see that in compile.sh there is a CPU_ONLY tag, how to run it on GPU?

Training Problem

Hi, @jack-cv. It is really a nice work to detect the large pose face. Can you explain how to get the rotate angular label of face to supervise the trainning. As I know, WIDER FACE don't have the facial landmark. Do you use one of the facial landmark detect algorithms to get the facial landmark and then calculate the facial angular or just label all the faces manually?

Besides, what do you mean that "we rotate the initial training images uniformly in the range of..." in section 2.3 and 2.4 of the paper? As a beginner, I am confused of the statement.

怎么在Ubuntu编译呢？

下载了源码以后怎么在Ubuntu编译仿真呢？谢谢

What is the orientation accuracy in training set of phase-1?

Hi,
Jack, I try to re-implement your PCN model, but I found that training phase1, the up-down face orientation prediction accuracy is very low(about 90% in training set). I think that is not well enough for the training of the second phase. Do I miss sth? Please comment, thank you.

Best,
Edward

How to use it if not opencv2?

How to use it if not opencv2?

About the Iou?

Is the Iou about the ground true and predicted box?

已经把caffe-master的目录添加进去了，可还是有错误。。

PCN.h:12:27: fatal error: caffe/caffe.hpp: No such file or directory

Promote the accuracy

Have you tried using Resnet or other deeper net to promote the PCN accuracy？

python代码

请问有python调用的代码吗？

How to train my datasets？

I want to train my own datasets? How can i do it?

Do you plan to release the training code?

Dear Jack-CV
This a really good job. Do you plan to release the training code? @jack-cv

你好，网络输入大小和论文图片中6中的大小不用样

你好检测效果很好，有个地方没看明白，就是代码中网络图片的输入大小和论文图片中6中的所示的图片大小是不一样的，代码中网络的输入数据大小是变化的。

Your fps is fast when the minsize is 48, but when decrease the minsize to 12, the speed is slow.

Comparing with s3fd, setting pcn with minsize face = 16, the speed is much slower, so your algorithm only performs real-time with a bigger face size?

Segmentation fault (core dumped)

您好，请问Segmentation fault (core dumped)这个报错怎么解决呢是opencv版本问题还是其他什么问题，求指教

does it can run on windows?

rt

source code version open？？

libPCN.so: cannot open shared object file: No such file or directory

运行sh run.sh picture/video/fddb报错
./picture/video/picture: error while loading shared libraries: libPCN.so: cannot open shared object file: No such file or directory
我的opencv为3.4 是不是不兼容??

Promote accuracy

Have you tried using other architecture in PCN？

compile error on ubuntu16.04

OS: Ubuntu 16.04
Protobuf version: 2.6.1
OpenCV version: 2.4.13
gcc & g++ version: 5.4.0

When I compoling picture.cpp, I got a error as below
compile picture /tmp/ccewgFHU.o: In function main':
picture.cpp:(.text.startup+0x77): undefined reference to PCN::PCN(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)' libPCN.so: undefined reference to google::base::CheckOpMessageBuilder::NewString()'
libPCN.so: undefined reference to caffe::Net<float>::Net(std::string const&, caffe::Phase, int, std::vector<std::string, std::allocator<std::string> > const*)' libPCN.so: undefined reference to caffe::Net::CopyTrainedLayersFrom(std::string)'
collect2: error: ld returned 1 exit status
done
`

I searched some information by google, soameone said this was because the version of gcc&g++ was too high. Then I changed gcc&g++ version to 4.8. However, another error occured.
compile picture /tmp/ccdYSnpl.o: In function main':
picture.cpp:(.text.startup+0x140): undefined reference to cv::imread(std::string const&, int)' picture.cpp:(.text.startup+0x6b1): undefined reference to cv::imshow(std::string const&, cv::_InputArray const&)'
libPCN.so: undefined reference to google::base::CheckOpMessageBuilder::NewString()' libPCN.so: undefined reference to caffe::Net::Net(std::string const&, caffe::Phase, int, std::vector<std::string, std::allocatorstd::string > const*)'
libPCN.so: undefined reference to caffe::Net<float>::CopyTrainedLayersFrom(std::string)' collect2: error: ld returned 1 exit status done

Really have no sense to deal with this. Could you please help me?

Why the part of the face/non face classification has two neuron?

It seems enough that one neuron determine whether it is face.

编译时需要boost版本1.54.0，而我的是1.68.0，请问这有影响吗

how to train with different datasets?

Is there any code for training with different datasets?

About the pcn3 regress loss？

Hi, @jack-cv , your work are very interesting, but I want to know the regress loss of rotation in pcn3. Is it the smooth l1 or Least square estimation? Thank you.

Could you please release a .so library using OpenCV 3.X

thanks a lot!!!!

Possibility to get 3 different models?

Hello! i am trying to port the implementation to other frameworks, and i was wondering if its possible to split the PCN.caffemodel into three parts, like the .prototxt to have PCN-1.caffemodel, PCN-2.caffemodel, PCN-3.caffemodel ?

thanks!

Definition of RIP?

Hi,@jack-cv! Can you explain how you define the concept of RIP(rotation-in-plane) for different conditions such as side face and front face (e.g. how do you know whether a face's angular is exactly 51 degree)? Any formular?

请问PCN.dat model文件的存储类型和格式是怎样的?

请问PCN.dat model文件的存储类型和格式是怎样的? @jack-cv

whats picture/video/fddb? how should I compile?

Can you help me whats picture/video/fddb? how should I compile?
Is it the path for fddb.cpp?

When use different min_face_size, got different result on same picture? A confusing question.

Hi, Jack
I have a question，when change detector.SetMinFaceSize(48) to detector.SetMinFaceSize(20), the result changes. When test with 30, there is no face detected. test with the same input，the output is different with rotate of the angle, I am confused and want to know your opinion, the test input is as follows：

when the minFaceSize is 21 or 48, the output is as follows：

when the minFaceSize is 20, the output is as follow：

when the minFaceSize is 30, the output is as follow：

It turns out that the output angle has been flipped up and down or just lost the face, could you please give me a hint what causes that? Should I change the ImagePyramidScaleFactor?
Best,
Edward

GPU版本

你好。有没有考虑过开源GPU版本呢？

Use the network in paper, cannot train orientation task well?

question1: I use the network in the paper, to train the PCN-2, but the accuracy is only about 80% in the training datset, cannot get 96% , any ideas?

question2: I parse your caffemodel, and see the input is three data, i.e. data1, data2, data3, could you tell me what the three data mean and how to generate them?

Best,
Edward

misleading in paper

As shown in paper, the bounding box regresion contains 3 factors. a b and w that represents the conordinate of top-left point and its width. but the S use t and t*

ta tb tw is given by the paper,but what 's the t* ? is there any explaination?

人脸特征点没有返回标定？？人脸对齐？？

/usr/lib/gcc/x86_64-linux-gnu/5/../../../x86_64-linux-gnu/crt1.o：在函数‘_start’中： (.text+0x20)：对‘main’未定义的引用 collect2: error: ld returned 1 exit status

GPU version？？

您好，请问你训练的时候，是先把人脸截出来吗？还有就是PCN训练的框是正立的还是斜着的？

看rotate这里面写到，似乎框是正立的？
那这个正立的框是怎么得到的呢？是取斜着框的x和y的最大最小得到的吗？
另一个问题：你在训练时如何控制各个角度人脸的比例呢？每个角度都生成相同比例的人脸吗？

Really can run at 29FPS in cpu?

Hi jack-CV
I run the code picture.cpp at my computer Intel(R) Core(TM) i7-3770K CPU @ 3.50GHz.

Is that ok? @jack-cv

what is your system environment?Can you give me some more ditails?

which cuda version, cudnn version and lots of dependency version are you using? Can you give us some instructions to test your demo? Thank you very much.

Compilation documentation

In command,
sh compile.sh picture/video/fddb
whats "picture/video/fddb" does it points to fddb.cpp?

Also, in fddb.cpp I can see hardcoded paths.

I am using Ubuntu 16.04 with caffe and opencv 3.0

get face candidate by sliding window and image pyramid？

You said you use sliding window and image pyramid to get face candidates?
why do you use fully convolution like MT-CNN?
thanks

What's the differences with MTCNN?

With the similar architecture of MTCNN, you did not even mention it in your paper? Where is the highlight of this work? Just re-train the 3 nets in MTCNN and sightly modify the test code, we can get the same results and higher fps than your paper.

角度问题

您好，请问支持旋转角度输出吗？ 比如人脸左右的旋转，上下的旋转角度

caffe+cpu+ubuntu14.04 can not use

How to get faces with different angles before training?

Hi,@jack-cv. As is shown in the picture, when rotating a face, the bounding box will be rotated accordingly. Thus would lead some undefined pixes around a face（e.g. black pixes in the above image). How do you handle this problem? In other words, how do you ajust bounding box label according to the rotate angle?

loading the network in pycaffe

Hi.
I'm trying to load the network in pycaffe. For this I need the "caffe.proto". Can you release the file? or can you release the source code for the libPCN.so?

Thanks

how to convert wider rectangle label to a square? what formulation you used for your papar results.

Coordinate Calculation problems

@jack-cv what do face.x, face.y, face.width mean in PCN.h? I cannot understand your coordinates calculation, could you please give me a hint?
Best,
Edward

How to feed the data by batch?

@jack-cv Would you please kindly tell me how to run PCN with mini-batch not single image?

System environment for demo

I tried to work on docker image from official caffe(bvlc/caffe:gpu) but it didnt work because of glog(maybe) and caffe version. I finally made it works on an image of nvidia/cuda:ubuntu14.04 with caffe 1.0.0 built by myself.

Could you upload binary file(libPCN.so) that can works on current official caffe docker image?

is there a docker image or another version?

I tried this development environment more than 10 times and it did not work.
 If you do not mind, I wonder if you can tell me the way to get a docker image or another version (tensor flow, keras, etc).

Thank you again for your hard work, it is greatly appreciated.