fix

api_routes.py

@@ -63,10 +63,10 @@ if DEEPFACE_AVAILABLE:
     try:
         from deepface import DeepFace
         deepface_module = DeepFace
-        
+
         # 为 DeepFace.verify 方法添加兼容性包装
         _original_verify = getattr(DeepFace, 'verify', None)
-        
+
         if _original_verify:
             def _wrapped_verify(*args, **kwargs):
                 """
@@ -88,10 +88,10 @@ if DEEPFACE_AVAILABLE:
                     )
                     _recover_deepface_model()
                     return _original_verify(*args, **kwargs)
-            
+
             DeepFace.verify = _wrapped_verify
             logger.info("Patched DeepFace.verify for SymbolicTensor compatibility")
-        
+
         try:
             from deepface.models import FacialRecognition as df_facial_recognition
 
@@ -3526,6 +3526,34 @@ def _extract_tar_archive(archive_path: str, target_dir: str) -> Dict[str, str]:
     }
 
 
+def extract_chinese_celeb_dataset_sync() -> Dict[str, Any]:
+    """
+    同步执行 chinese_celeb_dataset 解压操作，供启动流程或其他同步场景复用。
+    """
+    archive_path = os.path.join(MODELS_PATH, "chinese_celeb_dataset.tar.gz")
+    target_dir = "/opt/data"
+
+    if not os.path.isfile(archive_path):
+        raise FileNotFoundError(f"数据集文件不存在: {archive_path}")
+
+    try:
+        os.makedirs(target_dir, exist_ok=True)
+    except OSError as exc:
+        logger.error(f"创建目标目录失败: {target_dir}, {exc}")
+        raise RuntimeError(f"创建目标目录失败: {exc}") from exc
+
+    extract_result = _extract_tar_archive(archive_path, target_dir)
+    return {
+        "success": True,
+        "message": "chinese_celeb_dataset 解压完成",
+        "archive_path": archive_path,
+        "target_dir": target_dir,
+        "command": extract_result.get("command"),
+        "stdout": extract_result.get("stdout"),
+        "stderr": extract_result.get("stderr"),
+    }
+
+
 def _run_shell_command(command: str, timeout: int = 300) -> Dict[str, Any]:
     """执行外部命令并返回输出。"""
     logger.info(f"准备执行系统命令: {command}")
@@ -3554,36 +3582,18 @@ async def extract_chinese_celeb_dataset():
     """
     解压 MODELS_PATH 下的 chinese_celeb_dataset.tar.gz 到 /opt/data/chinese_celeb_dataset。
     """
-    archive_path = os.path.join(MODELS_PATH, "chinese_celeb_dataset.tar.gz")
-    target_dir = "/opt/data"
-
-    if not os.path.isfile(archive_path):
-        raise HTTPException(status_code=404, detail=f"数据集文件不存在: {archive_path}")
-
-    try:
-        os.makedirs(target_dir, exist_ok=True)
-    except OSError as exc:
-        logger.error(f"创建目标目录失败: {target_dir}, {exc}")
-        raise HTTPException(status_code=500, detail=f"创建目标目录失败: {exc}")
-
     loop = asyncio.get_event_loop()
     try:
-        extract_result = await loop.run_in_executor(
-            executor, _extract_tar_archive, archive_path, target_dir
+        result = await loop.run_in_executor(
+            executor, extract_chinese_celeb_dataset_sync
         )
+    except FileNotFoundError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
     except Exception as exc:
         logger.error(f"解压 chinese_celeb_dataset 失败: {exc}")
         raise HTTPException(status_code=500, detail=f"解压失败: {exc}")
 
-    return {
-        "success": True,
-        "message": "chinese_celeb_dataset 解压完成",
-        "archive_path": archive_path,
-        "target_dir": target_dir,
-        "command": extract_result.get("command"),
-        "stdout": extract_result.get("stdout"),
-        "stderr": extract_result.get("stderr"),
-    }
+    return result
 
 
 @api_router.post("/files/upload", tags=["文件管理"])

app.py

@@ -43,7 +43,7 @@ except Exception as exc:
 
 try:
     t_start = time.perf_counter()
-    from api_routes import api_router
+    from api_routes import api_router, extract_chinese_celeb_dataset_sync
     import_time = time.perf_counter() - t_start
     logger.info(f"api_routes module imported successfully, time: {import_time:.3f}s")
 except Exception as e:
@@ -51,6 +51,19 @@ except Exception as e:
     logger.error(f"api_routes module import failed, time: {import_time:.3f}s, error: {e}")
     raise
 
+try:
+    t_extract_start = time.perf_counter()
+    extract_result = extract_chinese_celeb_dataset_sync()
+    extract_time = time.perf_counter() - t_extract_start
+    logger.info(
+        "Chinese celeb dataset extracted successfully, time: %.3fs, target: %s",
+        extract_time,
+        extract_result.get("target_dir"),
+    )
+except Exception as exc:
+    logger.error(f"Failed to extract Chinese celeb dataset automatically: {exc}")
+    raise
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):