https://github.com/CMU-Perceptual-Computing-Lab/openpose
https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/installation.md
$ nvidia-smi
Fri Sep 1 06:57:58 2017
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 375.66 Driver Version: 375.66 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 750 Off | 0000:01:00.0 On | N/A |
| 30% 35C P8 1W / 38W | 720MiB / 1992MiB | 12% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1226 G /usr/lib/xorg/Xorg 554MiB |
| 0 2060 G compiz 22MiB |
| 0 4248 G ...el-token=4B65CE4504E8A2FF5010D4DBF73FD9D7 135MiB |
| 0 9767 G rviz 6MiB |
+-----------------------------------------------------------------------------+
Could kill rviz and chrome to free up more gpu, how to reduce xorg usage?
currently have libcudart7.5, so will have to do manual compilation.
Going to download cudnn for cuda 7.5
tar xvf cudnn-7.5-linux-x64-v5.1.tgz
cuda/include/cudnn.h
cuda/lib64/libcudnn.so
cuda/lib64/libcudnn.so.5
cuda/lib64/libcudnn.so.5.1.10
cuda/lib64/libcudnn_static.a