fix folder names, refactoring

move to yolov8m
use checkpoint.txt instead of yaml

preprocessing.py

@@ -1,19 +1,15 @@
 import os.path
 import time
-from datetime import datetime
+from datetime import datetime, timedelta
 from pathlib import Path
 import albumentations as A
 import cv2
 import numpy as np
-from dateutil.relativedelta import relativedelta
 
-from config import Config
-from constants import current_images_dir, current_labels_dir, annotation_classes, prefix, date_format, \
-    current_dataset_dir
+from constants import (data_images_dir, data_labels_dir, processed_images_dir, processed_labels_dir,
+                       annotation_classes, checkpoint_file, checkpoint_date_format)
 from dto.imageLabel import ImageLabel
 
-config = Config()
-
 
 def image_processing(img_ann: ImageLabel) -> [ImageLabel]:
     transforms = [
@@ -45,12 +41,12 @@ def image_processing(img_ann: ImageLabel) -> [ImageLabel]:
             img = ImageLabel(
                 image=res['image'],
                 labels=res['bboxes'],
-                image_path=os.path.join(current_images_dir, f'{name}{path.suffix}'),
-                labels_path=os.path.join(current_labels_dir, f'{name}.txt')
+                image_path=os.path.join(processed_images_dir, f'{name}{path.suffix}'),
+                labels_path=os.path.join(processed_labels_dir, f'{name}.txt')
             )
             results.append(img)
         except Exception as e:
-            print(f'Error during transformtation: {e}')
+            print(f'Error during transformation: {e}')
     return results
 
 
@@ -80,6 +76,7 @@ def read_labels(labels_path) -> [[]]:
             str_coordinates = row.split(' ')
             class_num = str_coordinates.pop(0)
             coordinates = [float(n.replace(',', '.')) for n in str_coordinates]
+            # noinspection PyTypeChecker
             coordinates.append(class_num)
             arr.append(coordinates)
         return arr
@@ -92,34 +89,24 @@ def process_image(img_ann):
     write_result(ImageLabel(
         image=img_ann.image,
         labels=img_ann.labels,
-        image_path=os.path.join(current_images_dir, Path(img_ann.image_path).name),
-        labels_path=os.path.join(current_labels_dir, Path(img_ann.labels_path).name)
+        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 get_checkpoint():
-    if config.checkpoint is not None:
-        return config.checkpoint
-
-    dates = []
-    for directory in os.listdir('models'):
-        try:
-            dates.append(datetime.strptime(directory[len(prefix):], date_format))
-        except:
-            continue
-    if len(dates) == 0:
-        return datetime.now() - relativedelta(years=1)
-    else:
-        return max(dates)
-
-
 def main():
-    last_date = checkpoint = get_checkpoint()
+    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:
         images = []
-        with os.scandir(config.images_dir) as imd:
+        with os.scandir(data_images_dir) as imd:
             for image_file in imd:
                 if not image_file.is_file():
                     continue
@@ -130,8 +117,8 @@ def main():
 
         for image_file in images:
             try:
-                image_path = os.path.join(config.images_dir, image_file.name)
-                labels_path = os.path.join(config.labels_dir, f'{Path(image_path).stem}.txt')
+                image_path = os.path.join(data_images_dir, image_file.name)
+                labels_path = os.path.join(data_labels_dir, f'{Path(image_path).stem}.txt')
                 image = cv2.imdecode(np.fromfile(image_path, dtype=np.uint8), cv2.IMREAD_UNCHANGED)
                 process_image(ImageLabel(
                     image_path=image_path,
@@ -142,42 +129,14 @@ def main():
             except Exception as e:
                 print(f'Error appeared {e}')
         if last_date != checkpoint:
-            checkpoint = config.checkpoint = last_date
-            config.write()
+            checkpoint = last_date
+            try:
+                with open(checkpoint_file, 'w') as f:
+                    f.write(datetime.strftime(checkpoint, checkpoint_date_format))
+            except:
+                pass
         time.sleep(5)
 
 
-def check_labels():
-    for label in os.listdir(os.path.join(current_dataset_dir, 'labels')):
-        with open(os.path.join(current_dataset_dir, 'labels', label), 'r') as f:
-            lines = f.readlines()
-            for line in lines:
-                list_c = line.split(' ')[1:]
-                for l in list_c:
-                    if float(l) > 1:
-                        print('Error!')
-
-
-def fix_class(folder):
-    for label in os.listdir(folder):
-        if label.startswith('0000'):
-            with open(os.path.join(folder, label), 'r+') as f:
-                lines = f.readlines()
-                truncated = False
-                for i in range(0, len(lines)):
-                    if len(lines[i]) < 25:
-                        print(lines[i])
-                        truncated = True
-                        lines.pop(i)
-                if truncated:
-                    f.truncate(0)
-                    f.seek(0)
-                    f.writelines(lines)
-                f.close()
-
-
 if __name__ == '__main__':
-    fix_class('datasets/zombobase-2024-06-18/test/labels')
-    fix_class('datasets/zombobase-2024-06-18/train/labels')
-    fix_class('datasets/zombobase-2024-06-18/valid/labels')
-    # main()
+    main()