New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to train the model for arbitrary images #13

Open

KevinWang676 opened this issue Jun 18, 2023 · 0 comments

KevinWang676 commented Jun 18, 2023 •

edited

Loading

Hi, in the training code

mpiexec -n 8 python image_train.py --data_dir balloons.png --lr 5e-4 --diffusion_steps 1000 --image_size 256 \
--noise_schedule linear --num_channels 64 --num_head_channels 16 --channel_mult "1,2,4" \
--attention_resolutions "2" --num_res_blocks 1 --resblock_updown False --use_fp16 True \
--use_scale_shift_norm True --use_checkpoint True --batch_size 16

the parameter image_size is 256. If I train a model for arbitrary images, how should I adjust the code? Thank you in advance!

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment