Add YOLO11 TensorRT quantization benchmark scripts

- Engine build scripts (FP16/INT8)
- Benchmark validation scripts
- Result parsing and analysis tools
- COCO dataset configuration

full_coco_benchmark.bat

@@ -0,0 +1,27 @@
+@echo off
+echo ============================================
+echo Full COCO Benchmark: FP16-480p vs INT8-640p
+echo Dataset: COCO val2017 (5000 images)
+echo No class filtering - full 80 classes
+echo ============================================
+
+call conda activate yolo
+
+echo [1/3] Build FP16 480p engine (if not exists)...
+if not exist yolo11n_fp16_480.engine (
+    yolo export model=yolo11n.pt format=engine imgsz=480 device=0 half=True
+) else (
+    echo FP16 480p engine already exists
+)
+
+echo.
+echo [2/3] Test FP16 480p (full COCO, no classes filter)...
+yolo val model=yolo11n_fp16_480.engine data=coco.yaml imgsz=480 batch=1 device=0 > fp16_480_full_results.txt 2>&1
+
+echo.
+echo [3/3] Test INT8 640p (full COCO, no classes filter)...
+yolo val model=yolo11n_int8_b1_8.engine data=coco.yaml imgsz=640 batch=1 device=0 > int8_640_full_results.txt 2>&1
+
+echo.
+echo Done. Run: python parse_full_coco.py
+pause