delete breeding

add proper preprocessing. not so tested yet

.gitignore

@@ -1 +1,3 @@
 .idea/
+*labels/
+*images/

breeding_date_set.py

@@ -1,119 +0,0 @@
-import math
-import datetime
-import cv2
-import albumentations as A
-import numpy as np
-import os
-def file_magnification(folder_path):
-    file_txt = []
-    file_jpg = []
-    for foldername, subfolders, filenames in os.walk(folder_path):
-        for filename in filenames:
-            f = filename.split('.')
-
-            if f[-1] == 'txt':
-                file_txt.append(filename)
-            elif f[-1] == 'jpg':
-                file_jpg.append(filename)
-
-    for k in range(len(file_jpg)):
-        image = cv2.imread(f'{folder_path}\\{file_jpg[k]}')
-        annotations = []
-        with open(f'{folder_path}\\{file_txt[k]}', 'r') as file:
-            lines = file.readlines()
-            for line in lines:
-                annotations.append(line)
-
-
-        main_fillet_yolo_conversion = []
-        fillet_yolo_bboxes = []
-        fillet_yolo_class = []
-        print(annotations)
-        for ii in range(len(annotations)):
-            a = annotations[ii].split(' ')
-            for i in range(len(a)):
-                try:
-                    main_fillet_yolo_conversion.append(int(a[i]))
-                except ValueError:
-                    main_fillet_yolo_conversion.append(float(a[i]))
-                print(main_fillet_yolo_conversion)
-            fillet_yolo_class.append(main_fillet_yolo_conversion[0])
-            del main_fillet_yolo_conversion[0]
-            fillet_yolo_bboxes.append(main_fillet_yolo_conversion)
-            main_fillet_yolo_conversion = []
-
-        for o in range(10):
-            bboxes = fillet_yolo_bboxes
-            category_ids = fillet_yolo_class
-
-            transform = A.Compose([
-                A.HorizontalFlip(p=0.5),
-                A.RandomBrightnessContrast(p=0.2),
-                A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=15, p=0.5),
-            ], bbox_params=A.BboxParams(format='yolo', label_fields=['category_ids']))
-
-            transformed = transform(image=image, bboxes=bboxes, category_ids=category_ids)
-            transformed_image = transformed['image']
-            transformed_bboxes = transformed['bboxes']
-            transformed_category_ids = transformed['category_ids']
-
-            cv2.imwrite(f'{folder_path}\\{o}_{file_jpg[k]}', transformed_image)
-            with open(f'{folder_path}\\{o}_{file_txt[k]}', 'w') as f:
-                for bbox, category_id in zip(transformed_bboxes, transformed_category_ids):
-                    x_center, y_center, width, height = bbox
-                    cla = category_id
-                    f.write(f"{cla} {x_center} {y_center} {width} {height}\n")
-file_txt_1 = []
-file_jpg_1 = []
-file_start = 'Zombobase-'+str(datetime.date.today())
-folder_path = ('train')
-for foldername, subfolders, filenames in os.walk(folder_path):
-    for subfolder in subfolders:
-        folder_path = (f'train\\{subfolder}')
-        for foldername, subfolders, filenames in os.walk(folder_path):
-            for filename in filenames:
-
-                f = filename.split('.')
-
-                if f[-1] == 'txt':
-                    file_txt_1.append(filename)
-                elif f[-1] == 'jpg':
-                    file_jpg_1.append(filename)
-
-annotations = []
-os.makedirs(file_start)
-file = ['test', 'train']
-percent_fille = [0.20,0.10]
-for fi, p_f in zip(file, percent_fille):
-    os.makedirs(f'{file_start}\\{fi}')
-
-    for i in range(math.ceil(len(file_txt_1)* p_f)):
-        image = cv2.imread(f'D:\\train\\images\\{file_jpg_1[i]}')
-        with open(f'D:\\train\\labels\\{file_txt_1[i]}', 'r') as file:
-            lines = file.readlines()
-            for line in lines:
-                annotations.append(line)
-        cv2.imwrite(f'{file_start}\\{fi}\\{file_jpg_1[i]}', image)
-        with open(f'{file_start}\\{fi}\\{file_txt_1[i]}', 'w') as f:
-            for iii in range(len(annotations)):
-                f.write(annotations[iii])
-
-        annotations = []
-        del file_txt_1[i]
-        del file_jpg_1[i]
-
-os.makedirs(f'{file_start}\\validation')
-for a, j in zip(file_txt_1, file_jpg_1):
-    image = cv2.imread(f'D:\\train\\images\\{j}')
-    with open(f'D:\\train\\labels\\{a}', 'r') as file:
-        lines = file.readlines()
-        for line in lines:
-            annotations.append(line)
-    cv2.imwrite(f'{file_start}\\Validation\\{j}', image)
-    with open(f'{file_start}\\Validation\\{a}', 'w') as f:
-        for iii in range(len(annotations)):
-            f.write(annotations[iii])
-    annotations = []
-file = ['test', 'train','validation']
-for i in file:
-    file_magnification(f'{file_start}\\{i}')

datasets/zombobase-current/labels/Himars_vs_Tulpan_000091.txt

@@ -1,3 +0,0 @@
-3 0.41877 0.64332 0.06107 0.07926
-7 0.40442 0.78827 0.06779 0.05212
-7 0.19860 0.90662 0.05314 0.05429

labels/Himars_vs_Tulpan_000091.txt

@@ -1,3 +0,0 @@
-3 0.41877 0.64332 0.06107 0.07926
-7 0.40442 0.78827 0.06779 0.05212
-7 0.19860 0.90662 0.05314 0.05429

preprocessing.py

@@ -1,60 +1,83 @@
 import os.path
 import time
-
+from array import *
-import cv2
-import albumentations as alb
-from os import listdir
-from os.path import isfile, join
 from pathlib import Path
+import albumentations as A
+import cv2
+
 
 labels_dir = 'labels'
 images_dir = 'images'
 current_dataset_dir = os.path.join('datasets', 'zombobase-current')
+current_images_dir = os.path.join(current_dataset_dir, 'images')
+current_labels_dir = os.path.join(current_dataset_dir, 'labels')
 
-class ImageAnnotation:
 
-    def read_annotations(self) -> [[]]:
+class ImageLabel:
-        with open(self.annotation_path, 'r') as f:
-            rows = f.readlines()
-            arr = []
-            for row in rows:
-                str_coordinates = row.split(' ')
-                class_num = str_coordinates.pop(0)
-                coordinates = [float(n) for n in str_coordinates]
-                coordinates.append(class_num)
-                arr.append(coordinates)
-            return arr
 
-    def __init__(self, image_path):
+    def __init__(self, image_path, image, labels_path, labels):
         self.image_path = image_path
-        self.image_name = Path(image_path).stem
+        self.image = image
-        self.dataset_image_path = os.path.join(current_dataset_dir, images_dir, self.image_name, os.path.basename(image_path))
+        self.labels_path = labels_path
-        self.image = cv2.imread(image_path)
+        self.labels = labels
 
-        self.annotation_path = os.path.join(labels_dir, self.image_name, '.txt')
-        self.dataset_annotation_path = os.path.join(current_dataset_dir, labels_dir, self.image_name, '.txt')
-        self.annotations = self.read_annotations()
 
-def image_processing(img_ann: ImageAnnotation) -> [ImageAnnotation]:
+def image_processing(img_ann: ImageLabel) -> [ImageLabel]:
-    # return structure example:
+    transforms = [
-    # utilize transform albumentations here
+        A.Compose([A.HorizontalFlip(always_apply=True)], bbox_params=A.BboxParams(format='yolo')),
-    return [ImageAnnotation(f'{img_ann.image_name}1', image1, bboxes1 ),
+        A.Compose([A.RandomBrightnessContrast(always_apply=True)], bbox_params=A.BboxParams(format='yolo')),
-            ImageAnnotation(f'{img_ann.image_name}2', image2, bboxes2),
+        A.Compose([A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=15, always_apply=True)],
-            ...
+                  bbox_params=A.BboxParams(format='yolo'))
-                ]
+    ]
 
-def write_results(img_ann: ImageAnnotation):
+    results = []
-    # write image cv2.imwrite(, image) dataset_image_path
+    for i, transform in enumerate(transforms):
-    # write img_ann.annotations into new file with name dataset_annotation_path
+        res = transform(image=img_ann.image, bboxes=img_ann.labels)
+        path = Path(img_ann.image_path)
+        name = f'{path.stem}_{i+1}'
+        results.append(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')
+        ))
+    return results
+
+
+def write_result(img_ann: ImageLabel):
+    cv2.imwrite(img_ann.image_path, img_ann.image)
+    with open(img_ann.labels_path, 'w') as f:
+        lines = [f'{ann[4]} {round(ann[0], 5)} {round(ann[1], 5)} {round(ann[2], 5)} {round(ann[3], 5)}\n' for ann in img_ann.labels]
+        f.writelines(lines)
+        f.close()
+
+
+def read_labels(labels_path) -> [[]]:
+    with open(labels_path, 'r') as f:
+        rows = f.readlines()
+        arr = []
+        for row in rows:
+            str_coordinates = row.split(' ')
+            class_num = str_coordinates.pop(0)
+            coordinates = [float(n) for n in str_coordinates]
+            coordinates.append(class_num)
+            arr.append(coordinates)
+        return arr
 
 
 def process_image(img_ann):
     results = image_processing(img_ann)
     for res_ann in results:
-        write_results(res_ann)
+        write_result(res_ann)
-    write_results(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)
+    ))
     os.remove(img_ann.image_path)
-    os.remove(img_ann.annotation_path)
+    os.remove(img_ann.labels_path)
 
 
 def main():
@@ -66,7 +89,14 @@ def main():
 
         for image in images:
             image_path = os.path.join(images_dir, image)
-            process_image(ImageAnnotation(image_path))
+            labels_path = os.path.join(labels_dir, f'{Path(image_path).stem}.txt')
+            process_image(ImageLabel(
+                image_path=image_path,
+                image=cv2.imread(image_path),
+                labels_path=labels_path,
+                labels=read_labels(labels_path)
+            ))
+
 
 if __name__ == '__main__':
     main()