刘畅

The speed of face tracking

1

When I run get_face_tracking.py, I found that the performance isn't that great like the gif in README introduction. It's mainly because the following code line is the most time consuming....

in ctc_decoder_layer.cpp, score_data should be the probability sum， `score_data[n] += -max_prob` but I don't know whether this parameter has some meaning？ and how to use it?

Check failed: error == cudaSuccess (77 vs. 0) an illegal memory access was encountered

9

使用的是ms分支，ubuntu14.04 cuda 8.0+cudnn v5，在TITAN X和GTX 1080显卡上train model的时候，均出现如下错误： > I0712 11:19:24.122469 15529 solver.cpp:336] Iteration 0, Testing net (#0) > F0712 11:19:24.439040 15529 math_functions.cu:79] Check failed: error == cudaSuccess (77 vs. 0)...

``` In file included from src/caffe/layers/cudnn_bn_layer.cpp:8:0: ./include/caffe/layers/cudnn_bn_layer.hpp:21:36: error: expected template-name before ‘

When I ran face_align.py,always arise 'NoFaces'. It seems that dlib.get_frontal_face_detector() didn't detect any face...Do you have this problem?Or what cause this？Thanks

In script ./QAN++/test_quality.py

DukeMTMC-VideoReID数据集百度云链接分享

10

链接：https://pan.baidu.com/s/1RqqHH2lb1e4m5BndNqbmfQ 提取码：uluj

Will you release the synthetic dataset your paper used? And the generate script?

When using gen_images.m on my own dataset, there is an matlab error named :out of memory...Did anyone meet this problem? And what can I do to solve the problem?