This code loads images and their labels from folders. It reads bounding boxes in normalized form and converts them to pixel values. Then it prints the objects found in each image.
import os
from PIL import Image
def load_dataset(image_dir, label_dir):
dataset = []
for filename in os.listdir(image_dir):
if filename.endswith('.jpg') or filename.endswith('.png'):
image_path = os.path.join(image_dir, filename)
label_path = os.path.join(label_dir, filename.rsplit('.',1)[0] + '.txt')
if os.path.exists(label_path):
with open(label_path, 'r') as f:
labels = [line.strip().split() for line in f.readlines()]
image = Image.open(image_path)
width, height = image.size
objects = []
for label in labels:
class_id, x_c, y_c, w, h = label
x_c, y_c, w, h = map(float, (x_c, y_c, w, h))
# Convert normalized to pixel coordinates
x_center = x_c * width
y_center = y_c * height
box_width = w * width
box_height = h * height
objects.append({
'class_id': int(class_id),
'bbox': [x_center, y_center, box_width, box_height]
})
dataset.append({'image': filename, 'objects': objects})
return dataset
# Example usage
image_dir = 'images'
label_dir = 'labels'
dataset = load_dataset(image_dir, label_dir)
for data in dataset:
print(f"Image: {data['image']}")
for obj in data['objects']:
print(f" Class {obj['class_id']} at {obj['bbox']}")
