ai-training/preprocessing.py

import os.path
import time
from datetime import datetime, timedelta
from pathlib import Path
import albumentations as A
import cv2
import numpy as np

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


def image_processing(img_ann: ImageLabel) -> [ImageLabel]:
    transforms = [
        A.Compose([A.HorizontalFlip(always_apply=True)],
                  bbox_params=A.BboxParams(format='yolo')),
        A.Compose([A.RandomBrightnessContrast(always_apply=True)],
                  bbox_params=A.BboxParams(format='yolo')),
        A.Compose([A.SafeRotate(limit=90, always_apply=True)],
                  bbox_params=A.BboxParams(format='yolo')),
        A.Compose([A.SafeRotate(limit=90, always_apply=True),
                   A.RandomBrightnessContrast(always_apply=True)],
                  bbox_params=A.BboxParams(format='yolo')),
        A.Compose([A.ShiftScaleRotate(scale_limit=0.2, always_apply=True),
                   A.VerticalFlip(always_apply=True), ],
                  bbox_params=A.BboxParams(format='yolo')),
        A.Compose([A.ShiftScaleRotate(scale_limit=0.2, always_apply=True)],
                  bbox_params=A.BboxParams(format='yolo')),
        A.Compose([A.SafeRotate(limit=90, always_apply=True),
                   A.RandomBrightnessContrast(always_apply=True)],
                  bbox_params=A.BboxParams(format='yolo'))
    ]

    results = []
    for i, transform in enumerate(transforms):
        try:
            res = transform(image=img_ann.image, bboxes=img_ann.labels)
            path = Path(img_ann.image_path)
            name = f'{path.stem}_{i + 1}'
            img = ImageLabel(
                image=res['image'],
                labels=res['bboxes'],
                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 transformation: {e}')
    return results


def write_result(img_ann: ImageLabel, show_image=False):
    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')

    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()
    print(f'{img_ann.labels_path} written')


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.replace(',', '.')) for n in str_coordinates]
            # noinspection PyTypeChecker
            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_result(res_ann)
    write_result(ImageLabel(
        image=img_ann.image,
        labels=img_ann.labels,
        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:
        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:
                    images.append(image_file)
                    last_date = max(last_date, mod_time)

        for image_file in images:
            try:
                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,
                    image=image,
                    labels_path=labels_path,
                    labels=read_labels(labels_path)
                ))
            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)


if __name__ == '__main__':
    main()