search

Daniil-Osokin / lightweight-human-pose-estimation-3d-demo.pytorch

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
Apache License 2.0
656 stars 138 forks source link

how to run it on GPU? #12

Closed antoniolq closed 4 years ago

antoniolq commented 4 years ago

Hello, it got some problems. when I run it it shows something:

No CUDA device found, inferring on CPU
Qt: Cannot set locale modifiers:

It is very slow, only 0.7fps. However, I input nvcc -V on the command line and run some samples of cuda, it shows cuda and cudnn are installed successfully. Do you how to run it on GPU? Thank you very much, look forward to your reply!

antoniolq commented 4 years ago

and my command is python3 demo.py --model human-pose-estimation-3d.pth --video 0

antoniolq commented 4 years ago

this also shows I haved installed cuda

Python 3.5.2 (default, Oct  8 2019, 13:06:37) 
[GCC 5.4.0 20160609] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> print(torch.version.cuda)
10.1.243
>>>
Daniil-Osokin commented 4 years ago

May be CUDA_VISIBLE_DEVICES environmental variable was set wrongly? Try to run in terminal export CUDA_VISIBLE_DEVICES=0, then run the demo. BTW, ou can check if PyTorch sees any gpu devices by running in python: torch.cuda.device_count(), these commands also may be helpful.

antoniolq commented 4 years ago

Thank you very much！ Get it！