Skip to content

yqx7150/HoloDiffusion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

docker's environment:(cuda10.2,ubuntu16.04) 
docker pull zieghart/base:C10U16_perfect 
then:
conda activate ncsn

train:
python main.py --config=aapm_sin_ncsnpp_gb.py --workdir=exp_zl --mode=train --eval_folder=result

test size and gap:
python A_1k_arg_PCsampling_demo.py --size=500 --gpu=0 --gap=60 --useNet=True

test sensor number: 
python A_1k_arg_PCsampling_demo.py --size=500 --gpu=0 --gap=60 --ssn=2 --useNet=True 
python A_1k_arg_PCsampling_demo.py --size=500 --gpu=0 --gap=60 --ssn=3 --useNet=True

test sparse: 
python -u A_1k_arg_PCsampling_demo.py --size=500 --gpu=1 --gap=60 --sparse=6 --useNet=True # means SR = 5/6 
python -u A_1k_arg_PCsampling_demo.py --size=500 --gpu=1 --gap=60 --sparse=5 --useNet=True # means SR = 4/5

background_test(for long time test): 
nohup python -u A_1k_arg_PCsampling_demo.py --size=500 --gpu=0 --gap=60 > ./records/your_path/S500_G60.out 2>&1 &

if have any questions:
[email protected]

About

HoloDiffusion's code.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published