Spaces:
Sleeping
Sleeping
File size: 2,030 Bytes
b87aa54 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
import os
import json
import xml.etree.ElementTree as ET
# Paths (Modify These)
ANNOTATIONS_DIR = "datasets/annotations" # Change to your XML annotations folder
OUTPUT_JSON = "datasets/annotations.json" # Where to save the COCO JSON
# COCO JSON Format
coco_data = {
"images": [],
"annotations": [],
"categories": [{"id": 1, "name": "object"}] # Only one class
}
annotation_id = 0
# Process Each XML File
for xml_file in os.listdir(ANNOTATIONS_DIR):
if not xml_file.endswith(".xml"):
continue
try:
tree = ET.parse(os.path.join(ANNOTATIONS_DIR, xml_file))
root = tree.getroot()
except ET.ParseError:
print(f"Skipping file due to parsing error: {xml_file}")
continue
# Extract Image Info
filename = root.find("filename").text
width = int(root.find("size/width").text)
height = int(root.find("size/height").text)
image_id = len(coco_data["images"])
coco_data["images"].append({
"id": image_id,
"file_name": filename,
"width": width,
"height": height
})
# Extract Objects
for obj in root.findall("object"):
bbox = obj.find("bndbox")
xmin = int(bbox.find("xmin").text)
ymin = int(bbox.find("ymin").text)
xmax = int(bbox.find("xmax").text)
ymax = int(bbox.find("ymax").text)
# Convert VOC bbox format (xmin, ymin, xmax, ymax) to COCO format (x, y, width, height)
bbox_coco = [xmin, ymin, xmax, ymax]
# Add Annotation
coco_data["annotations"].append({
"id": annotation_id,
"image_id": image_id,
"category_id": 1, # Only one class
"bbox": bbox_coco,
"area": (bbox_coco[2] - bbox_coco[0]) * (bbox_coco[3] - bbox_coco[1]),
"iscrowd": 0
})
annotation_id += 1
# Save to JSON File
with open(OUTPUT_JSON, "w") as f:
json.dump(coco_data, f, indent=4)
print(f"COCO annotations saved to {OUTPUT_JSON}")
|