Add model save/load and --resume for training continuation

- AsymmetricEncoder.save_checkpoint(): saves model_state + metadata
- AsymmetricEncoder.load_checkpoint(): rebuilds model with frozen backbones,
  then loads trainable weights from checkpoint
- --resume flag restores optimizer, loss (learnable tau), and scheduler state
- Training continues from the saved epoch

Usage:
  python -m src.training.train_gtauav --resume out/gtauav/with_text/ckpt_epoch004.pt

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/models/asymmetric_encoder.py

@@ -527,6 +527,56 @@ class AsymmetricEncoder(nn.Module):
         """Return list of parameters that require grad."""
         return [p for p in self.parameters() if p.requires_grad]
 
+    def save_checkpoint(self, path: str | Path, **extra) -> None:
+        """Save model checkpoint with metadata."""
+        path = Path(path)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        ckpt = {
+            "model_state": self.state_dict(),
+            "proj_dim": self.proj_dim,
+            "baseline_mode": self.baseline_mode,
+            **extra,
+        }
+        tmp = path.with_suffix(path.suffix + ".tmp")
+        torch.save(ckpt, tmp)
+        tmp.replace(path)
+        LOGGER.info("💾 Model saved to %s", path)
+
+    @classmethod
+    def load_checkpoint(
+        cls,
+        path: str | Path,
+        dino_web_path: str = "nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth",
+        dino_sat_path: str = "nn_models/DINO_SAT/model.safetensors",
+        lrsclip_path: str = "nn_models/LRSCLIP/DGTRS-CLIP-ViT-L-14.pt",
+        device: str = "cuda",
+    ) -> tuple[AsymmetricEncoder, dict]:
+        """Load model from checkpoint.
+
+        First builds the model (loading frozen backbones), then loads
+        the saved trainable weights on top.
+
+        Returns:
+            (model, checkpoint_dict) — model ready for eval/resume,
+            checkpoint_dict has optimizer_state, epoch, etc.
+        """
+        path = Path(path)
+        LOGGER.info("📂 Loading checkpoint from %s", path)
+        ckpt = torch.load(str(path), map_location="cpu", weights_only=False)
+
+        model = cls(
+            dino_web_path=dino_web_path,
+            dino_sat_path=dino_sat_path,
+            lrsclip_path=lrsclip_path,
+            proj_dim=ckpt.get("proj_dim", 512),
+            baseline_mode=ckpt.get("baseline_mode", False),
+            device=device,
+        )
+        model.load_state_dict(ckpt["model_state"], strict=False)
+        model = model.to(device)
+        LOGGER.info("✅ Checkpoint loaded (epoch=%s)", ckpt.get("epoch", "?"))
+        return model, ckpt
+
     def train(self, mode: bool = True) -> AsymmetricEncoder:
         """Override to keep frozen encoders in eval mode."""
         super().train(mode)