scripts/download_test_images.py

#!/usr/bin/env python3
"""
Download test images for SAM3 inference testing
Uses free, high-quality images from Unsplash and Pixabay
"""

import requests
from pathlib import Path
import time

# Configuration
OUTPUT_DIR = Path("assets/test_images")
OUTPUT_DIR.mkdir(parents=True, exist_ok=True)

# Free test images from Unsplash (free to use, no attribution required)
# These are direct links to specific images showing potholes, road cracks, and roads
UNSPLASH_IMAGES = [
    {
        "url": "https://images.unsplash.com/photo-1597155483629-a55bcccce5c7?w=1200",
        "filename": "pothole_01.jpg",
        "description": "Large pothole in asphalt road"
    },
    {
        "url": "https://images.unsplash.com/photo-1621544402532-00f7d6ee6e9d?w=1200",
        "filename": "road_crack_01.jpg",
        "description": "Cracked pavement"
    },
    {
        "url": "https://images.unsplash.com/photo-1558618666-fcd25c85cd64?w=1200",
        "filename": "road_01.jpg",
        "description": "Clean asphalt road"
    },
    {
        "url": "https://images.unsplash.com/photo-1449034446853-66c86144b0ad?w=1200",
        "filename": "road_02.jpg",
        "description": "Highway road surface"
    },
]

# Pixabay images (CC0 license - free for commercial use)
PIXABAY_IMAGES = [
    {
        "url": "https://pixabay.com/get/gf8f2bdb5e6d7fd9b6e7e35e8481e93c1ff5f0e2d1b7a6c4b8b7e7d5e1b7d8c4c_1280.jpg",
        "filename": "pothole_02.jpg",
        "description": "Road pothole damage"
    },
]

def download_image(url, output_path, description):
    """Download an image from URL"""
    try:
        print(f"Downloading: {description}")
        print(f"  URL: {url}")
        print(f"  Output: {output_path}")

        headers = {
            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36'
        }

        response = requests.get(url, headers=headers, timeout=30)
        response.raise_for_status()

        with open(output_path, 'wb') as f:
            f.write(response.content)

        print(f"  ✅ Downloaded ({len(response.content)} bytes)")
        return True

    except Exception as e:
        print(f"  ❌ Failed: {e}")
        return False

def main():
    """Download all test images"""
    print("="*80)
    print("Downloading Test Images for SAM3")
    print("="*80)
    print(f"Output directory: {OUTPUT_DIR}")
    print()

    all_images = UNSPLASH_IMAGES + PIXABAY_IMAGES
    successful = 0
    failed = 0

    for image_info in all_images:
        output_path = OUTPUT_DIR / image_info["filename"]

        # Skip if already exists
        if output_path.exists():
            print(f"Skipping {image_info['filename']} (already exists)")
            successful += 1
            continue

        if download_image(image_info["url"], output_path, image_info["description"]):
            successful += 1
        else:
            failed += 1

        # Be respectful to servers
        time.sleep(1)
        print()

    print("="*80)
    print(f"Download Summary")
    print("="*80)
    print(f"Total: {len(all_images)}")
    print(f"Successful: {successful}")
    print(f"Failed: {failed}")

if __name__ == "__main__":
    main()