openai / guided-diffusion

MIT License
6.03k stars 803 forks source link

Fix resumed model training for Multi-GPUs #64

Open harubaru opened 2 years ago

harubaru commented 2 years ago

Although the poster had closed the issue related to this https://github.com/openai/guided-diffusion/issues/23, I encountered the same issues when resuming training from a model checkpoint and solved it with OP's fix which is in this PR.