Camshowrecordings/model/sam_samantha/5 -

model: name: sam_samantha version: 5 backbone: vit_h image_size: 1024 num_classes: 1 # Usually segmentation → binary mask preprocess: normalize: true mean: [0.485, 0.456, 0.406] std: [0.229, 0.224, 0.225] device: cuda Below is a minimal, self‑contained script that loads the model and runs a single inference on a video frame.

# ------------------------------------------------------------------ # 3️⃣ Load checkpoint # ------------------------------------------------------------------ ckpt_path = Path(__file__).parent / "model" / "sam_samantha" / "5" / "model.ckpt" model = build_model(cfg) state_dict = torch.load(ckpt_path, map_location="cpu") model.load_state_dict(state_dict) model.eval() camshowrecordings/model/sam_samantha/5

parser = argparse.ArgumentParser(description="Run SAM‑Samantha v5 on a frame") parser.add_argument("image_path", type=str, help="Path to an image (or a video frame)") args = parser.parse_args() 0.406] std: [0.229

if frame_idx % stride == 0: mask = infer(frame) # binary mask (0/255) overlay = cv2.addWeighted(frame, 0.7, cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR), 0.3, 0) out.write(overlay) else: out.write(frame) # write raw frame for non‑processed indices camshowrecordings/model/sam_samantha/5