ai-training/prompts/DALI_initial_prompt.txt

I have a code for augmenting photos for dataset, I'm using albumentations. The problem is - I have 38k photos and more in a future, and albumentations works on CPU. It's working very slow, around 1800/ hour. I want to use GPU approach for augmentation task, DALI, since it's an original Nvidia implementation.
Note, it should create 7 augmented images  + original one.

Here is a code I'm using now:

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

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

total_files_processed = 0
transform = A.Compose([
    # Flips, rotations and brightness
    A.HorizontalFlip(),
    A.RandomBrightnessContrast(brightness_limit=(-0.05, 0.05), contrast_limit=(-0.05, 0.05)),
    A.Affine(p=0.7, scale=(0.8, 1.2), rotate=25, translate_percent=0.1),

    # Weather
    A.RandomFog(p=0.2, fog_coef_range=(0, 0.3)),
    A.RandomShadow(p=0.2),

    # Image Quality/Noise
    A.MotionBlur(p=0.2, blur_limit=(3, 5)),

    # Color Variations
    A.HueSaturationValue(p=0.3, hue_shift_limit=8, sat_shift_limit=8, val_shift_limit=8)
], bbox_params=A.BboxParams(format='yolo'))

def correct_bboxes(labels):
    margin = 0.0005
    min_size = 0.01
    res = []
    for bboxes in labels:
        x = bboxes[0]
        y = bboxes[1]
        half_width = 0.5*bboxes[2]
        half_height = 0.5*bboxes[3]

        # calc how much bboxes are outside borders ( +small margin ).
        # value should be negative. If it's positive, then put 0, as no correction
        w_diff = min( (1 - margin) - (x + half_width), (x - half_width) - margin, 0 )
        w = bboxes[2] + 2*w_diff
        if w < min_size:
            continue
        h_diff = min( (1 - margin) - (y + half_height), ((y - half_height) - margin), 0)
        h = bboxes[3] + 2 * h_diff
        if h < min_size:
            continue
        res.append([x, y, w, h, bboxes[4]])
    return res
    pass


def image_processing(img_ann: ImageLabel) -> [ImageLabel]:
    results = []
    labels = correct_bboxes(img_ann.labels)
    if len(labels) == 0 and len(img_ann.labels) != 0:
        print('no labels but was!!!')
    results.append(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)
        )
    )
    for i in range(7):
        try:
            res = transform(image=img_ann.image, bboxes=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):
    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()
    global total_files_processed
    print(f'{total_files_processed}. {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 preprocess_annotations():
    global total_files_processed  # Indicate that we're using the global counter
    total_files_processed = 0

    os.makedirs(processed_images_dir, exist_ok=True)
    os.makedirs(processed_labels_dir, exist_ok=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 image_file.is_file() and image_file.name not in processed_images:
                images.append(image_file)
    with concurrent.futures.ThreadPoolExecutor() as executor:
        executor.map(process_image_file, images)

def process_image_file(image_file): # this function will be executed in thread
    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)

        img_ann = ImageLabel(
            image_path=image_path,
            image=image,
            labels_path=labels_path,
            labels=read_labels(labels_path)
        )
        try:
            results = image_processing(img_ann)
            for res_ann in results:
                write_result(res_ann)
        except Exception as e:
            print(e)
        global total_files_processed
        total_files_processed += 1
    except Exception as e:
        print(f'Error appeared in thread for {image_file.name}: {e}')


def main():
    while True:
        preprocess_annotations()
        print('All processed, waiting for 2 minutes...')
        time.sleep(120)


if __name__ == '__main__':
    main()


please rewrite the whole code to DALI, utilizing GPU.
I do have 128Gb of RAM, RTX4090 and 32CPU Cores 
Also note, that for each image I'm making 7 augmented version (each of this versions should be different, cause of random factor of apply one or another augmentation + different random parameters in each augmentation mechanism)
Make this number 7 configurable in the beginning of the file. Also utilize GPU as match as possible, use batching