copy images and labels during forming dataset. add folder for corrupted labels, small refactor

preprocessing.py

@@ -50,13 +50,10 @@ def image_processing(img_ann: ImageLabel) -> [ImageLabel]:
     return results
 
 
-def write_result(img_ann: ImageLabel, show_image=False):
+def write_result(img_ann: ImageLabel):
     os.makedirs(os.path.dirname(img_ann.image_path), exist_ok=True)
     os.makedirs(os.path.dirname(img_ann.labels_path), exist_ok=True)
 
-    if show_image:
-        img_ann.visualize(annotation_classes)
-
     cv2.imencode('.jpg', img_ann.image)[1].tofile(img_ann.image_path)
     print(f'{img_ann.image_path} written')
 
@@ -92,28 +89,16 @@ def process_image(img_ann):
         image_path=os.path.join(processed_images_dir, Path(img_ann.image_path).name),
         labels_path=os.path.join(processed_labels_dir, Path(img_ann.labels_path).name)
     ))
-    # os.remove(img_ann.image_path)
-    # os.remove(img_ann.labels_path)
 
 
 def main():
-    checkpoint = datetime.now() - timedelta(days=720)
-    try:
-        with open(checkpoint_file, 'r') as f:
-            checkpoint = datetime.strptime(f.read(), checkpoint_date_format)
-    except:
-        pass
-    last_date = checkpoint
     while True:
+        processed_images = set(f.name for f in os.scandir(processed_images_dir))
         images = []
         with os.scandir(data_images_dir) as imd:
             for image_file in imd:
-                if not image_file.is_file():
-                    continue
-                mod_time = datetime.fromtimestamp(image_file.stat().st_mtime)
-                if mod_time > checkpoint:
+                if image_file.is_file() and image_file.name not in processed_images:
                     images.append(image_file)
-                    last_date = max(last_date, mod_time)
 
         for image_file in images:
             try:
@@ -128,14 +113,8 @@ def main():
                 ))
             except Exception as e:
                 print(f'Error appeared {e}')
-        if last_date != checkpoint:
-            checkpoint = last_date
-            try:
-                with open(checkpoint_file, 'w') as f:
-                    f.write(datetime.strftime(checkpoint, checkpoint_date_format))
-            except:
-                pass
-        time.sleep(5)
+        print('All processed, waiting for 2 minutes...')
+        time.sleep(120)
 
 
 if __name__ == '__main__':