LearnableInverter,
RadialMaskFunc,
rotate_real,
unprep_fft_channel,
)
# ----- load configuration -----
import config # isort:skip
# ----- global configuration -----
mpl.use("agg")
device = torch.device("cuda:0")
torch.cuda.set_device(0)
# ----- measurement configuration -----
mask_func = RadialMaskFunc(config.n, 40)
mask = unprep_fft_channel(mask_func((1, 1) + config.n + (1, )))
OpA = Fourier(mask)
inverter = LearnableInverter(config.n, mask, learnable=False)
# ----- network configuration -----
subnet_params = {
"in_channels": 2,
"out_channels": 2,
"drop_factor": 0.0,
"down_blocks": (5, 7, 9, 12, 15),
"up_blocks": (15, 12, 9, 7, 5),
"pool_factors": (2, 2, 2, 2, 2),
"bottleneck_layers": 20,
"growth_rate": 16,
"out_chans_first_conv": 16,
unprep_fft_channel,
)
from reconstruction_methods import admm_l1_rec_diag, grid_search
# ----- load configuration -----
import config # isort:skip
# ------ setup ----------
device = torch.device("cuda:0")
file_name = "grid_search_l1_fourier_"
save_path = os.path.join(config.RESULTS_PATH, "grid_search_l1")
# ----- operators --------
n = (320, 320)
mask_func = RadialMaskFunc(n, 50)
mask = unprep_fft_channel(mask_func((1, 1) + n + (1, )))
OpA = Fourier(mask)
OpTV = TVAnalysisPeriodic(n, device=device)
# ----- load test data --------
test_data_params = {
"mask_func":
mask_func,
"seed":
1,
"filter": [filter_acquisition_no_fs],
"num_sym_slices":
0,
"multi_slice_gt":
False,
CropOrPadAndResimulate((320, 320)),
Flatten(0, -3),
Normalize(reduction="mean", use_target=True),
], ),
"train_loader_params": {
"shuffle": True,
"num_workers": 8
},
"val_loader_params": {
"shuffle": False,
"num_workers": 8
},
}
# ----- data configuration -----
mask_func = RadialMaskFunc((320, 320), 50)
train_data_params = {
"mask_func": mask_func,
"seed": 1,
"filter": [filter_acquisition_no_fs],
"num_sym_slices": 0,
"multi_slice_gt": False,
"keep_mask_as_func": True,
}
train_data = AlmostFixedMaskDataset
val_data_params = {
"mask_func": mask_func,
"seed": 1,
"filter": [filter_acquisition_no_fs],