Question about your paper reproduction about ilvr_adm

[jychoi118]

Did you check the model flag when you run the script? For example:
--learn_sigma True --num_channels 128 --num_head_channels 64 --num_res_blocks 1 --resblock_updown True --use_scale_shift_norm True

[sooyalim]

Thanks for the reply!!!! I could generate some samples with your help.

I will enjoy changing the number of N and range t to produce various results.

Thanks again for helping me out!

[FayeGGG]

Did you check the model flag when you run the script? For example: --learn_sigma True --num_channels 128 --num_head_channels 64 --num_res_blocks 1 --resblock_updown True --use_scale_shift_norm True

Hi, I also met this RuntimeError: Error(s) in loading state_dict for UNetModel: when I want to run the code on my own dataset.

There is my code to run the script:
python scripts/ilvr_sample.py --attention_resolutions 16 --class_cond False --diffusion_steps 1000 --dropout 0.0 --image_size 512 --learn_sigma True --noise_schedule linear --num_channels 128 --num_head_channels 64 --num_res_blocks 3 --resblock_updown True --use_fp16 False --use_scale_shift_norm True --timestep_respacing 100 --model_path models/512x512_diffusion.pt --base_samples ref_imgs/magnetogram/500G --down_N 32 --range_t 20 --save_dir output/magnetogram_N32

Could you please tell me how to solve this problem? @jychoi118
Thanks a lot!!!

[LZX-ZNRA]

My problem is also #2 (comment).

Could you please provide a way to solve it. Thanks. @jychoi118