MTCNN-Accelerate-Onet
MTCNN-Accelerate-Onet copied to clipboard
blankWorld
MTCNN Face Detection & Alignment
/usr/bin/ld: CMakeFiles/MTCNN.dir/mtcnn.cpp.o: undefined reference to symbol '_ZN6google4base21CheckOpMessageBuilder7ForVar2Ev' //usr/local/lib/libglog.so.0: error adding symbols: DSO missing from command line collect2: error: ld returned 1 exit status CMakeFiles/MTCNN.dir/build.make:142: recipe for target 'MTCNN' failed make[2]:...
Hi, these day i test the mode with camera. my compute GTX760 640*480 ~80ms GPU minSize 40 threshold:: 0.7f, 0.6f, 0.6f GTX1080Ti 640*480 ~66ms GPU minSize 40 threshold:: 0.7f, 0.6f,...
To achieve your retrained model's accuracy, how many training data you used for each net?
I found that your code have no operation about the thranspose the img, did you train your model without transpose the model?
Can I know if the code does face alignment after face recognition. If so, can I know the location where the code for face alignment starts
I found it that you models are slower then the official release. Did you retrained all models ?
your readme file is not comment about how to build,can you share your build process?because when i compile your mtcnn.cpp file ,there are some errors: /tmp/cc7DRBwV.o：在函数‘MTCNN::GenerateBBox(caffe::Blob*, caffe::Blob*, float, float)’中： mtcnn.cpp:(.text+0xd93)：对‘caffe::Blob::cpu_data()...
