调整：移除推理性能汇总日志输出

main.py

@@ -9,7 +9,6 @@ import sys
 import threading
 import signal
 import time
-from collections import deque
 from datetime import datetime
 from typing import Dict, Any, Optional, List, Tuple
 
@@ -85,9 +84,6 @@ class EdgeInferenceService:
         self._scheduler_interval_sec = 0.01
         self._max_frame_age_sec = 0.5
         self._max_pending_roi_items = self._max_batch_size * 32
-        self._latency_window = deque(maxlen=256)
-        self._last_latency_log_time = 0.0
-        self._latency_log_interval_sec = 5.0
 
         # 摄像头级别告警去重：同一摄像头+告警类型在冷却期内只上报一次
         self._camera_alert_cooldown: Dict[str, datetime] = {}
@@ -677,35 +673,6 @@ class EdgeInferenceService:
             if not had_frame:
                 self._stop_event.wait(self._scheduler_interval_sec)
 
-    def _log_inference_latency_summary(self, inference_time_ms: float, batch_size: int):
-        """聚合输出推理时延，避免逐批 INFO 日志刷屏。"""
-        self._latency_window.append({
-            "latency_ms": inference_time_ms,
-            "batch_size": batch_size,
-        })
-
-        now = time.monotonic()
-        if now - self._last_latency_log_time < self._latency_log_interval_sec:
-            return
-
-        self._last_latency_log_time = now
-        samples = list(self._latency_window)
-        if not samples:
-            return
-
-        latencies = sorted(sample["latency_ms"] for sample in samples)
-        batches = [sample["batch_size"] for sample in samples]
-        p95_index = max(0, min(len(latencies) - 1, int(len(latencies) * 0.95) - 1))
-
-        self._logger.info(
-            "推理性能汇总: "
-            f"样本={len(samples)}, "
-            f"batch_avg={sum(batches) / len(batches):.2f}, "
-            f"latency_avg={sum(latencies) / len(latencies):.2f}ms, "
-            f"latency_p95={latencies[p95_index]:.2f}ms, "
-            f"latency_max={latencies[-1]:.2f}ms"
-        )
-    
     def _batch_process_rois(self):
         """批量处理 ROI - 真正的 batch 推理（按 max_batch_size 分块）"""
         with self._batch_lock:
@@ -740,10 +707,6 @@ class EdgeInferenceService:
                     batch_size=len(chunk),
                     throughput_fps=1000.0 / inference_time_ms if inference_time_ms > 0 else 0
                 )
-                self._log_inference_latency_summary(
-                    inference_time_ms,
-                    batch_size=len(chunk),
-                )
 
                 # 诊断：输出原始推理结果形状（非告警诊断日志，使用 DEBUG 级别）
                 import numpy as np