MTCNN_Caffe

MTCNN_Caffe copied to clipboard

error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor

6

``` (py3.6_caffe) zhangxin@zhangxin-AW:~/github/MTCNN_Caffe$ sudo make Package opencv3 was not found in the pkg-config search path. Perhaps you should add the directory containing `opencv3.pc' to the PKG_CONFIG_PATH environment variable No package...

ZhangXinNan

Why does it take me 1 second to load caffe model on my 1050 card ，But more than a minute to load it on my V100 card

niushaoda

请问为何在我的GTX1080Ti上测试450*450像素的图像都需要500ms?，而且我已将试过了将下面 四行注释掉： //const Dtype* tempTop = top[0]->gpu_data(); //for(int i=0;i

flexibility2

CPU Benchmarking

6

Hi DaFu, Thanks a lot for sharing your code. Did you get a chance to benchmark your code on CPU? Thanks, Sri

srireddy821

training code

1

Hi, How did you train this MTmodel? Did you change any settings compared to the training process in the raw paper? Can you provide training code if u don't mind?

hustzhzhu

error on mtcnn face detection

2

Detect 1080X1920F1229 22:31:31.232031 10620 data_transformer.cpp:167] Check fail ed: channels == datum_channels (1095 vs. 3) *** Check failure stack trace: ***

anguoyang

Hi! Whether I can compile MTMain.cpp in other version CAFFE, and what new code you have added to the your caffe project? Thank you!

steven-chow