Files
ai-training/preprocessing.py
T
Oleksandr Bezdieniezhnykh 02b45f83d1 add more composition stepss
2024-05-27 03:16:46 +03:00

108 lines
3.7 KiB
Python

import os.path
import time
from array import *
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 ImageLabel:
def __init__(self, image_path, image, labels_path, labels):
self.image_path = image_path
self.image = image
self.labels_path = labels_path
self.labels = labels
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.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=-40, always_apply=True)],
bbox_params=A.BboxParams(format='yolo')),
A.Compose([A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=-20, always_apply=True)],
bbox_params=A.BboxParams(format='yolo')),
A.Compose([A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=20, always_apply=True)],
bbox_params=A.BboxParams(format='yolo')),
A.Compose([A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=40, always_apply=True)],
bbox_params=A.BboxParams(format='yolo'))
]
results = []
for i, transform in enumerate(transforms):
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_result(res_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.labels_path)
def main():
while True:
images = os.listdir(images_dir)
if len(images) == 0:
time.sleep(5)
continue
for image in images:
image_path = os.path.join(images_dir, image)
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()