feat(actpred): 多帧注意力架构改造（Transformer 替换 concat 融合，支持多帧图像+历史动作序列）

actpred/predict.py

@@ -28,6 +28,7 @@ class ActionPredictorInference:
 
         self.action_dim = self._data_cfg.action_dim
         self.history_len = self._data_cfg.history_len
+        self.frame_len = self._data_cfg.frame_len
 
         self._transform = transforms.Compose([
             transforms.Resize((self._data_cfg.image_size, self._data_cfg.image_size)),
@@ -61,13 +62,23 @@ class ActionPredictorInference:
             self._action_std = stats[1].astype(np.float32)
 
     @torch.no_grad()
-    def predict(self, image: np.ndarray, action_history: np.ndarray) -> np.ndarray:
+    def predict(self, images, action_history: np.ndarray) -> np.ndarray:
+        """images: 长度为 frame_len 的 RGB 图像序列（旧→新，末帧为当前帧）"""
+        if not isinstance(images, (list, tuple)):
+            images = [images]
+        if len(images) != self._data_cfg.frame_len:
+            raise ValueError(
+                f"images 应为 {self._data_cfg.frame_len} 帧，实际为 {len(images)} 帧。"
+                f"冷启动时可重复传入同一帧。")
         expected_shape = (self._data_cfg.history_len, self._data_cfg.action_dim)
         if action_history.shape != expected_shape:
             raise ValueError(
                 f"action_history 形状应为 {expected_shape}，实际为 {action_history.shape}")
-        img = Image.fromarray(image) if isinstance(image, np.ndarray) else image
-        img_tensor = self._transform(img).unsqueeze(0).to(self._device)
+        frames = []
+        for image in images:
+            img = Image.fromarray(image) if isinstance(image, np.ndarray) else image
+            frames.append(self._transform(img))
+        img_tensor = torch.stack(frames).unsqueeze(0).to(self._device)  # (1, F, 3, S, S)
         history = torch.tensor(action_history, dtype=torch.float32)
         if self._action_mean is not None:
             history = (history - self._action_mean) / self._action_std
@@ -93,7 +104,9 @@ def parse_action_history(s: str, action_dim: int) -> np.ndarray:
 def main():
     parser = argparse.ArgumentParser(description="actpred inference")
     parser.add_argument("--model", required=True, help="checkpoint path")
-    parser.add_argument("--image", required=True, help="image file path")
+    parser.add_argument("--images", required=True, nargs="+",
+                        help="按时间顺序（旧→新）传入 frame_len 个图像路径；"
+                             "冷启动时可重复传同一帧路径")
     parser.add_argument("--action-history", required=True,
                         help="冒号分隔各步，每步 action_dim 个值，共 history_len 步。"
                              "e.g. '0,0,0,0:1,0,0,0' (action_dim=4, history_len=2)")
@@ -106,9 +119,13 @@ def main():
     predictor = ActionPredictorInference(args.model, args.device)
     action_dim = args.action_dim or predictor.action_dim
 
-    image = Image.open(args.image).convert("RGB")
+    if len(args.images) != predictor.frame_len:
+        raise SystemExit(
+            f"--images 需传入 {predictor.frame_len} 个路径（旧→新），"
+            f"实际为 {len(args.images)} 个。冷启动时可重复传同一帧路径。")
+    images = [np.array(Image.open(p).convert("RGB")) for p in args.images]
     history = parse_action_history(args.action_history, action_dim)
-    predicted = predictor.predict(np.array(image), history)
+    predicted = predictor.predict(images, history)
 
     if args.output_format == "json":
         print(json.dumps({"predicted_action": predicted.tolist()}, indent=2))