mattiaspaul

import torch
import torch.nn as nn
import torch.nn.functional as F
import copy
from tqdm import trange
passed = torch.zeros(50)
for i in trange(50):

    pad = tuple(list(torch.randint(3,(3,))))
    dilation = tuple(list(torch.randint(2,(3,))+1))

mattiaspaul

import torch
import torch.nn as nn
import torch.nn.functional as F
import nibabel as nib
import time
import numpy as np
import scipy.ndimage
from scipy.ndimage.interpolation import zoom as zoom
from scipy.ndimage.interpolation import map_coordinates

mattiaspaul

import torch
import torch.nn as nn
import torch.nn.functional as F
import nibabel as nib
import time
import numpy as np
import scipy.ndimage
from scipy.ndimage.interpolation import zoom as zoom
from scipy.ndimage.interpolation import map_coordinates

mattiaspaul

#note: an advanced baseline with additional infos for registration settings
#for Learn2Reg 2021 and recommended pre-processing of lung scans can be found
#here https://github.com/multimodallearning/convexAdam
import torch
import torch.nn as nn
import torch.nn.functional as F
import nibabel as nib
import time
import numpy as np
import scipy.ndimage

mattiaspaul

import numpy as np
import argparse

def main():

    parser = argparse.ArgumentParser()

    parser.add_argument("--inputtag", dest="inputtag", help="input tag file from (MINC)", default=None, required=True)
    parser.add_argument("--savetxt", dest="savetxt",  help="output landmark file to (txt)", default=None, required=True)

mattiaspaul

import numpy as np
import nibabel as nib
import argparse

def main():

    parser = argparse.ArgumentParser()
    parser.add_argument("--inputnii", dest="inputnii", help="input segmentation from (nii.gz)", default=None, required=True)
    parser.add_argument("--movingnii", dest="movingnii",  help="second segmentation from (nii.gz)", default=None, required=False)
    parser.add_argument("--savetxt", dest="savetxt",  help="output landmark file to (txt)", default=None, required=False)