mingyuan-zhang / MotionDiffuse

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
https://mingyuan-zhang.github.io/projects/MotionDiffuse.html
Other
850 stars 74 forks source link

About DDP traing? #8

Open LinghaoChan opened 2 years ago

LinghaoChan commented 2 years ago

If I want to train my model via multi-GPUs and I don't have srun and slurm in my system, how can I run the code?

mingyuan-zhang commented 1 year ago

Sorry for the late reply. I have updated scripts for DataParallel training, which does not need slurm. You can follow the commands in text2motion/README.md