Spaces:
Sleeping
Sleeping
Download src/data/splits.py from amitaddi/btxrd-workstation: direct link, hf CLI and curl.
- Browser
- Download file 4.56 kB
-
https://huggingface.co/spaces/amitaddi/btxrd-workstation/resolve/main/src/data/splits.py
- Command line
-
hf download hf://spaces/amitaddi/btxrd-workstation/src/data/splits.py
-
curl -L -o splits.py https://huggingface.co/spaces/amitaddi/btxrd-workstation/resolve/main/src/data/splits.py
4.56 kB
| """ | |
| Few-shot split utilities and support set selection. | |
| Provides: | |
| - Reproducible train/val/test split creation | |
| - Stratified few-shot subset selection (1-shot, 5-shot, 10-shot per class) | |
| """ | |
| import os | |
| import glob | |
| import random | |
| import numpy as np | |
| from pathlib import Path | |
| from typing import Dict, List, Tuple, Optional | |
| from collections import defaultdict | |
| from src.data.yolo_to_masks import parse_yolo_label | |
| def get_class_to_samples(labels_dir: str, images_dir: str) -> Dict[int, List[str]]: | |
| """ | |
| Map each class to the list of image stems containing that class. | |
| Returns: | |
| Dict mapping class_id → list of stems | |
| """ | |
| class_to_stems = defaultdict(list) | |
| label_files = sorted(glob.glob(os.path.join(labels_dir, '*.txt'))) | |
| for label_path in label_files: | |
| stem = Path(label_path).stem | |
| # Verify image exists | |
| img_exists = False | |
| for ext in ['.jpeg', '.jpg', '.png']: | |
| if os.path.exists(os.path.join(images_dir, stem + ext)): | |
| img_exists = True | |
| break | |
| if not img_exists: | |
| continue | |
| annotations = parse_yolo_label(label_path) | |
| classes_in_image = set(a[0] for a in annotations) | |
| for cls_id in classes_in_image: | |
| class_to_stems[cls_id].append(stem) | |
| return dict(class_to_stems) | |
| def select_few_shot_support(labels_dir: str, | |
| images_dir: str, | |
| n_shots: int, | |
| seed: int = 42, | |
| strategy: str = 'random') -> Tuple[List[str], List[str]]: | |
| """ | |
| Select a few-shot support set, stratified by class. | |
| Args: | |
| labels_dir: Path to labels | |
| images_dir: Path to images | |
| n_shots: Number of examples per class | |
| seed: Random seed | |
| strategy: 'random' or 'diverse' | |
| Returns: | |
| support_stems: List of stems selected as support | |
| query_stems: Remaining stems for evaluation | |
| """ | |
| rng = random.Random(seed) | |
| class_to_stems = get_class_to_samples(labels_dir, images_dir) | |
| support_stems = set() | |
| for cls_id, stems in sorted(class_to_stems.items()): | |
| available = [s for s in stems if s not in support_stems] | |
| if strategy == 'random': | |
| selected = rng.sample(available, min(n_shots, len(available))) | |
| elif strategy == 'diverse': | |
| # Select diverse examples (spread across the stem ID range) | |
| indices = np.linspace(0, len(available) - 1, min(n_shots, len(available))) | |
| selected = [available[int(i)] for i in indices] | |
| else: | |
| raise ValueError(f"Unknown strategy: {strategy}") | |
| support_stems.update(selected) | |
| # All stems | |
| all_stems = set() | |
| for stems in class_to_stems.values(): | |
| all_stems.update(stems) | |
| query_stems = sorted(all_stems - support_stems) | |
| support_stems = sorted(support_stems) | |
| return support_stems, query_stems | |
| def print_split_statistics(labels_dir: str, images_dir: str, stems: List[str], name: str): | |
| """Print class distribution for a set of stems.""" | |
| CLASS_NAMES = [ | |
| 'giant cell tumor', 'multiple osteochondromas', 'osteochondroma', | |
| 'osteofibroma', 'osteosarcoma', 'other bt', 'other mt', | |
| 'simple bone cyst', 'synovial osteochondroma' | |
| ] | |
| class_counts = defaultdict(int) | |
| for stem in stems: | |
| label_path = os.path.join(labels_dir, stem + '.txt') | |
| if os.path.exists(label_path): | |
| annotations = parse_yolo_label(label_path) | |
| for cls_id, _, _, _, _ in annotations: | |
| class_counts[cls_id] += 1 | |
| print(f"\n{name} ({len(stems)} images):") | |
| for cls_id in range(9): | |
| count = class_counts.get(cls_id, 0) | |
| print(f" {CLASS_NAMES[cls_id]:30s}: {count}") | |
| if __name__ == '__main__': | |
| root = '.' | |
| labels_dir = os.path.join(root, 'BTXRD dataset', 'labels', 'train') | |
| images_dir = os.path.join(root, 'BTXRD dataset', 'images', 'train') | |
| for n_shots in [1, 5, 10]: | |
| support, query = select_few_shot_support( | |
| labels_dir, images_dir, n_shots=n_shots | |
| ) | |
| print(f"\n{'='*60}") | |
| print(f"{n_shots}-shot selection") | |
| print(f"{'='*60}") | |
| print(f"Support set: {len(support)} images") | |
| print(f"Query set: {len(query)} images") | |
| print_split_statistics(labels_dir, images_dir, support, f"{n_shots}-shot support") | |