CMU-Perceptual-Computing-Lab / caffe_rtpose

Realtime C++ code for multi-person pose estimation
Other
356 stars 207 forks source link

The number of GPUs to increase fps. #16

Closed wschoi89 closed 7 years ago

wschoi89 commented 7 years ago

I want to make pose recognition similar to real time. To do this,

I used this expression below.

--num_gpu 4 <--- Parallelize over this number of GPUs. Default is 1.

and I got this error. F1219 15:59:41.175240 36602 common.cpp:137] Check failed: error == cudaSuccess (10 vs. 0) invalid device ordinal

I just have one graphic card, Do I have to increase the number of graphic cards to recognize the human pose in real time??

ZheC commented 7 years ago

We use one GTX 1080/ Titanx GPU and achieves the speed of 8~9 fps. And yes, num_gpu <= the number of graphic cards in your computer. In your case, it can not be more than one.