Improved loading of models to allow providing a directory, added a few type-hints and improved the code-style a little bit by running an auto-formatter on the entire file.

sbb_binarize/sbb_binarize.py

@@ -1,41 +1,42 @@
 """
 Tool to load model and binarize a given image.
 """
-
+import argparse
 import sys
-from glob import glob
 from os import environ, devnull
-from os.path import join
+from pathlib import Path
-from warnings import catch_warnings, simplefilter
+from typing import Union
 
-import numpy as np
-from PIL import Image
 import cv2
+import numpy as np
+
 environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 stderr = sys.stderr
 sys.stderr = open(devnull, 'w')
 import tensorflow as tf
 from tensorflow.keras.models import load_model
 from tensorflow.python.keras import backend as tensorflow_backend
-sys.stderr = stderr
 
+sys.stderr = stderr
 
 import logging
 
+
 def resize_image(img_in, input_height, input_width):
     return cv2.resize(img_in, (input_width, input_height), interpolation=cv2.INTER_NEAREST)
 
+
 class SbbBinarizer:
 
-    def __init__(self, model_dir, logger=None):
+    def __init__(self, model_dir: Union[str, Path], logger=None):
-        self.model_dir = model_dir
+        model_dir = Path(model_dir)
         self.log = logger if logger else logging.getLogger('SbbBinarizer')
 
         self.start_new_session()
 
-        self.model_files = glob('%s/*.h5' % self.model_dir)
+        self.model_files = list([str(p.absolute()) for p in model_dir.rglob("*.h5")])
         if not self.model_files:
-            raise ValueError(f"No models found in {self.model_dir}")
+            raise ValueError(f"No models found in {str(model_dir)}")
 
         self.models = []
         for model_file in self.model_files:
@@ -53,8 +54,8 @@ class SbbBinarizer:
         self.session.close()
         del self.session
 
-    def load_model(self, model_name):
+    def load_model(self, model_path: str):
-        model = load_model(model_name, compile=False)
+        model = load_model(model_path, compile=False)
         model_height = model.layers[len(model.layers) - 1].output_shape[1]
         model_width = model.layers[len(model.layers) - 1].output_shape[2]
         n_classes = model.layers[len(model.layers) - 1].output_shape[3]
@@ -97,11 +98,8 @@ class SbbBinarizer:
             index_start_w = 0
             img_padded = np.copy(img)
 
-            
         img = np.copy(img_padded)
 
-            
-
         if use_patches:
 
             margin = int(0.1 * model_width)
@@ -109,7 +107,6 @@ class SbbBinarizer:
             width_mid = model_width - 2 * margin
             height_mid = model_height - 2 * margin
 
-
             img = img / float(255.0)
 
             img_h = img.shape[0]
@@ -225,8 +222,6 @@ class SbbBinarizer:
                         mask_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin] = seg
                         prediction_true[index_y_d + margin:index_y_u - margin, index_x_d + margin:index_x_u - margin, :] = seg_color
 
-            
-            
             prediction_true = prediction_true[index_start_h: index_start_h + img_org_h, index_start_w: index_start_w + img_org_w, :]
             prediction_true = prediction_true.astype(np.uint8)
 
@@ -245,14 +240,13 @@ class SbbBinarizer:
         return prediction_true[:, :, 0]
 
     def run(self, image=None, image_path=None, save=None, use_patches=False):
-        if (image is not None and image_path is not None) or \
+        if (image is not None and image_path is not None) or (image is None and image_path is None):
-               (image is None and image_path is None):
             raise ValueError("Must pass either a opencv2 image or an image_path")
         if image_path is not None:
             image = cv2.imread(image_path)
         img_last = 0
         for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
-            self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
+            self.log.info(f"Predicting with model {model_file} [{n + 1}/{len(self.model_files)}]")
 
             res = self.predict(model, image, use_patches)
 
@@ -272,5 +266,7 @@ class SbbBinarizer:
         img_last[:, :][img_last[:, :] > 0] = 255
         img_last = (img_last[:, :] == 0) * 255
         if save:
+            # Create the output directory (and if necessary it's parents) if it doesn't exist already
+            Path(save).parent.mkdir(parents=True, exist_ok=True)
             cv2.imwrite(save, img_last)
         return img_last