Giters

CMU-Perceptual-Computing-Lab / openpose_train

Training repository for OpenPose

Home Page:https://github.com/CMU-Perceptual-Computing-Lab/openpose

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

What kind GPU is required to run the training?

ting3000 opened this issue · comments

commented

I followed the training/README.md file to build the code on the Ubuntu box which has 1 GPU Quadro RTX 5000 with 16GB memory. But the running "bash train_pose.sh 0" reported "error == cudaSuccess (2 vs. 0) out of memory".
What kind GPU is required to run the training?
Is there a way to work around it?

Thanks!

commented

I lower the batch size to be 4 from 10, the issue is resolved.

commented

I was facing the same problem, thanks!

commented

Running a RTX 3070 with 8GB memory for some local testing. Using the default settings the training would just be stuck at the first iteration. I modified line 70 in d_setLayers.py to:

 sBatchSizes = [4]

after that training would finally run at about 15s/20 iter.