Implement as command line tool

lungtumormask/__main__.py

@@ -0,0 +1,20 @@
+import sys
+import argparse
+import os
+from lungtumormask import mask
+
+def path(string):
+    if os.path.exists(string):
+        return string
+    else:
+        sys.exit(f'File not found: {string}')
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('input', metavar='input', type=path, help='Path to the input image, should be .nifti')
+    parser.add_argument('output', metavar='output', type=str, help='Filepath for output tumormask')
+
+    argsin = sys.argv[1:]
+    args = parser.parse_args(argsin)
+
+    mask.mask(args.input, args.output)

lungtumormask/dataprocessing.py

@@ -5,7 +5,6 @@ from monai.transforms.intensity.array import ThresholdIntensity
 from monai.transforms.spatial.array import Resize, Spacing
 from monai.transforms.utility.dictionary import ToTensord
 import torch
-from tqdm import tqdm
 import numpy as np
 from monai.transforms import (Compose, LoadImaged, ToNumpyd, ThresholdIntensityd, AddChanneld, NormalizeIntensityd, SpatialCropd, DivisiblePadd, Spacingd, SqueezeDimd)
 
@@ -39,7 +38,7 @@ def mask_lung(scan_path, batch_size=20):
     timage_res = np.empty((np.append(0, tvolslices[0].shape)), dtype=np.uint8)
 
     with torch.no_grad():
-        for X in tqdm(dataloader_val):
+        for X in dataloader_val:
             X = X.float().to(device)
             prediction = model(X)
             pls = torch.max(prediction, 1)[1].detach().cpu().numpy().astype(np.uint8)

setup.py

@@ -7,5 +7,10 @@ setup(
     author="Svein Ole M Sevle, Vemund Fredriksen",
     url="https://github.com/VemundFredriksen/LungTumorMask",
     license="MIT",
-    python_requires='>=3.6'
+    python_requires='>=3.6',
+    entry_points={
+        'console_scripts': [
+            'lungtumormask = lungtumormask.__main__:main'
+        ]
+    }
 )