"""Ultimate WBF: All models × All scales ======================================== Maximum firepower: 5 models × 3 scales = 15 prediction sources → WBF fusion. Also tests per-camera weighted WBF and confidence-gated variants. """ import sys, os, json import numpy as np from PIL import Image from tqdm import tqdm PROJECT_DIR = '/home/user/goat' os.chdir(PROJECT_DIR) sys.path.insert(0, PROJECT_DIR) from ultralytics import YOLO def compute_iou(b1, b2): x1, y1 = max(b1[0], b2[0]), max(b1[1], b2[1]) x2, y2 = min(b1[2], b2[2]), min(b1[3], b2[3]) inter = max(0, x2-x1) * max(0, y2-y1) a1 = (b1[2]-b1[0])*(b1[3]-b1[1]) a2 = (b2[2]-b2[0])*(b2[3]-b2[1]) return inter/(a1+a2-inter+1e-8) def wbf(boxes_list, scores_list, iou_thr=0.55): if not boxes_list or all(len(b) == 0 for b in boxes_list): return np.array([]), np.array([]) all_boxes, all_scores = [], [] for boxes, scores in zip(boxes_list, scores_list): for i in range(len(boxes)): all_boxes.append(boxes[i]) all_scores.append(scores[i]) if not all_boxes: return np.array([]), np.array([]) all_boxes = np.array(all_boxes); all_scores = np.array(all_scores) order = np.argsort(-all_scores) all_boxes, all_scores = all_boxes[order], all_scores[order] clusters, used = [], np.zeros(len(all_boxes), dtype=bool) for i in range(len(all_boxes)): if used[i]: continue cluster = [(all_boxes[i], all_scores[i])] used[i] = True for j in range(i+1, len(all_boxes)): if used[j]: continue tw = sum(s for _, s in cluster) center = sum(b*s/tw for b, s in cluster) if compute_iou(center.tolist(), all_boxes[j].tolist()) > iou_thr: cluster.append((all_boxes[j], all_scores[j])) used[j] = True clusters.append(cluster) result_boxes, result_scores = [], [] for cl in clusters: tw = sum(s for _, s in cl) avg_b = sum(b*s/tw for b, s in cl) result_boxes.append(avg_b) result_scores.append(tw) return np.array(result_boxes), np.array(result_scores) def evaluate(name, get_boxes_fn, val_files, val_img_dir, val_label_dir): iou_thrs = [round(0.5+i*0.05, 2) for i in range(10)] tp = {t:0 for t in iou_thrs} total_gt = 0 for img_file in tqdm(val_files, desc=name): img = Image.open(os.path.join(val_img_dir, img_file)) gt_boxes = [] lf = img_file.replace('.jpg','.txt') with open(os.path.join(val_label_dir, lf)) as f: for line in f: p = line.strip().split() if len(p) >= 5: cx,cy,w,h = [float(x) for x in p[1:5]] gt_boxes.append([(cx-w/2)*img.size[0], (cy-h/2)*img.size[1], (cx+w/2)*img.size[0], (cy+h/2)*img.size[1]]) total_gt += len(gt_boxes) if not gt_boxes: continue preds = get_boxes_fn(img) for t in iou_thrs: matched = set() for pb in preds: best_iou, best_gi = 0, -1 for gi, gb in enumerate(gt_boxes): if gi in matched: continue iou = compute_iou(pb.tolist(), gb) if iou > best_iou: best_iou = iou; best_gi = gi if best_iou >= t and best_gi >= 0: tp[t] += 1; matched.add(best_gi) recalls = [tp[t]/total_gt for t in iou_thrs] mAP = np.mean(recalls) return mAP, recalls[5] def main(): val_img_dir = 'Data/Detection_dataset/images/val' val_label_dir = 'Data/Detection_dataset/labels/val' val_files = sorted([f for f in os.listdir(val_img_dir) if f.endswith('.jpg')]) # Discover available models exp_dir = 'runs/detect/Detection_experiments' all_models = [] for ename in sorted(os.listdir(exp_dir)): best_path = os.path.join(exp_dir, ename, 'weights', 'best.pt') if os.path.exists(best_path): all_models.append((ename, best_path)) print(f'Found {len(all_models)} trained models:') for ename, path in all_models: print(f' {ename}') # Select ensemble models (prefer v6_1 + v12 + v14 seeds) ensemble_models = [] priority_patterns = ['v6_1', 'v12_seed', 'v14_seed'] for ename, path in all_models: for pat in priority_patterns: if pat in ename: ensemble_models.append((ename, path)) break # Limit to 5 best (by filename, assume newer seeds are good) ensemble_models = ensemble_models[:5] print(f'\nEnsemble: {len(ensemble_models)} models') for ename, _ in ensemble_models: print(f' {ename}') models = [(YOLO(p), ename) for ename, p in ensemble_models] scales = [1280, 1536, 1920] # Single model baseline def baseline_1536(img): m, _ = models[0] r = m.predict(img, imgsz=1536, conf=0.25, iou=0.7, max_det=100, verbose=False) if r and len(r[0].boxes): return r[0].boxes.xyxy.cpu().numpy() return np.array([]) mAP_single, r75_single = evaluate('Single model', baseline_1536, val_files, val_img_dir, val_label_dir) print(f'\n{"="*60}') print(f'RESULTS:') print(f' Single: mAP50-95={mAP_single:.4f} IoU@75={r75_single:.4f}') # Multi-model WBF (1536 only) def multi_model_wbf(img): boxes_list, scores_list = [], [] for m, _ in models: r = m.predict(img, imgsz=1536, conf=0.25, iou=0.7, max_det=100, verbose=False) if r and len(r[0].boxes): boxes_list.append(r[0].boxes.xyxy.cpu().numpy()) scores_list.append(r[0].boxes.conf.cpu().numpy()) else: boxes_list.append(np.array([])) scores_list.append(np.array([])) fused, _ = wbf(boxes_list, scores_list) return fused mAP_mm, r75_mm = evaluate(f'{len(models)}model WBF', multi_model_wbf, val_files, val_img_dir, val_label_dir) print(f' {len(models)}model: mAP50-95={mAP_mm:.4f} IoU@75={r75_mm:.4f} (+{mAP_mm-mAP_single:+.4f})') # Single model multi-scale WBF def single_multiscale_wbf(img): m, _ = models[0] boxes_list, scores_list = [], [] for sz in scales: r = m.predict(img, imgsz=sz, conf=0.25, iou=0.7, max_det=100, verbose=False) if r and len(r[0].boxes): boxes_list.append(r[0].boxes.xyxy.cpu().numpy()) scores_list.append(r[0].boxes.conf.cpu().numpy()) else: boxes_list.append(np.array([])) scores_list.append(np.array([])) fused, _ = wbf(boxes_list, scores_list) return fused mAP_sms, r75_sms = evaluate('1model 3scale', single_multiscale_wbf, val_files, val_img_dir, val_label_dir) print(f' 1m x 3sc: mAP50-95={mAP_sms:.4f} IoU@75={r75_sms:.4f} (+{mAP_sms-mAP_single:+.4f})') # ULTIMATE: All models × All scales def ultimate_wbf(img): boxes_list, scores_list = [], [] for m, _ in models: for sz in scales: r = m.predict(img, imgsz=sz, conf=0.25, iou=0.7, max_det=100, verbose=False) if r and len(r[0].boxes): boxes_list.append(r[0].boxes.xyxy.cpu().numpy()) scores_list.append(r[0].boxes.conf.cpu().numpy()) else: boxes_list.append(np.array([])) scores_list.append(np.array([])) fused, _ = wbf(boxes_list, scores_list) return fused mAP_ult, r75_ult = evaluate(f'{len(models)}m x {len(scales)}sc ULTIMATE', ultimate_wbf, val_files, val_img_dir, val_label_dir) print(f' ULTIMATE: mAP50-95={mAP_ult:.4f} IoU@75={r75_ult:.4f} (+{mAP_ult-mAP_single:+.4f})') # Save results results = { 'single': round(mAP_single, 4), 'multimodel': round(mAP_mm, 4), 'multiscale': round(mAP_sms, 4), 'ultimate': round(mAP_ult, 4), 'n_models': len(models), 'n_scales': len(scales), 'model_names': [n for n, _ in ensemble_models], } with open('logs/ultimate_results.json', 'w') as f: json.dump(results, f, indent=2) print(f'\nResults saved to logs/ultimate_results.json') if __name__ == '__main__': main()