zhreshold
400ms on gpu/1060 which is much slow than yolo
i have tested on your demo on gpu mode, it took about 400ms for 1 image, which is much slow than yolo(<100ms).
- The default config is not using cuda and cudnn. you should check your config.
- As in my case,the first time of running will take more time than usual. you can test more.
hi,thank you, I have checked the pre-defined values before the main, and debug to see the device type and device id, they are OK. and i also added clock related lines before and after the detect function to calculate the duration only on the detection. is there any other configurations?
you can just use normal mxnet-ssd if you want to run on gtx1060, Why to use this version? This version seems that it supports cuda but doesn't support cudnn .
How did you get GPU to work using this repo? I think the makefile don't support GPU yet.
I modify on visual studio to run it, GPU is working,however, cudnn is not working
The default config about cuda is #define MSHADOW_USE_CUDA 0, As @threshold ,the default seems don't support cuda. You can use c_predict_api.h to use gtx1060 in c++ .
@anguoyang how did you modify it on visual studio to work with GPU? I'd gladly accept any pointers to be able to do the same
@zhreshold i can not get gpu to work ,could you give me some tips to get gpu to work? thanks
