Thanks to visit codestin.com
Credit goes to github.com

Skip to content

ICSResearch/USBNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

USB-Net-ICS

Put the pth files in the folder "model".

  • Test
python test.py --model=usbnet --cs_ratio=25

The results will be generated in the folder "./results/usbnet/{dataset}/{cs_ratio}/", where results.csv will save the results in the format "{Image},{PSNR},{SSIM},{Time}".

  • Train
  1. Multi-GPU
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train.py --model=usbnet --data_path="" --eval_data_path="" --cs_ratio=10 --blr=1e-4 --min_lr=1e-6 --epochs=400 --batch_size=16 --warmup_epochs=10 --input_size=96
  1. Single GPU
python train.py --model=usbnet --data_path="" --eval_data_path="" --cs_ratio=10 --blr=1e-4 --min_lr=1e-6 --epochs=400 --batch_size=16 --warmup_epochs=10 --input_size=96

USB-Net-CSMRI

Put the pth files in the folder "model-Cartesian" or "model-Radial".

  • Test
python test.py --model=usbnet --cs_ratio=5 --input_size=256 --mask_type=Radial

The results will be generated in the folder "./results/usbnet/{dataset}/{cs_ratio}/", where results.csv will save the results in the format "{Image},{PSNR},{SSIM},{Time}".

  • Train
  1. Multi-GPU
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train.py --model=usbnet --data_path="" --eval_data_path="" --cs_ratio=5 --blr=5e-5 --min_lr=1e-6 --epochs=100 --batch_size=1 --warmup_epochs=10 --input_size=256 --mask_type=Radial
  1. Single GPU
python train.py --model=usbnet --data_path="" --eval_data_path="" --cs_ratio=5 --blr=5e-5 --min_lr=1e-6 --epochs=100 --batch_size=1 --warmup_epochs=10 --input_size=256 --mask_type=Radial

USB-Net-SCI

Simulation

Put the pth files in the folder "Sim".

python test.py --data_root="path of data"

Real

Put the pth files in the folder "Real".

python test_real.py --data_path="path of data" --mask_path="path of mask"

Model

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages