Release the hyperparamers of pre-trained models

openai / guided-diffusion

MIT License

5.87k stars 781 forks source link

Release the hyperparamers of pre-trained models #103

Open yc-cui opened 1 year ago

yc-cui commented 1 year ago

When training using the option --resume_checkpoint logs/256x256_diffusion.pt, it always failed training due to Unexpected key(s) in state_dict and size mismatch. Could you please tell us the hyperparamers of these pretrained models so that our fine-tuning models can match them?

wst2333 commented 8 months ago

hi! Now have you get the hyperparamers?

sushilkhadkaanon commented 4 months ago

HI @yc-cui @wst2333 did you guys resolve it? I'm also facing the same issue.