Add YOLO11 TensorRT quantization benchmark scripts

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

run_full_workflow.bat

@@ -0,0 +1,94 @@
+@echo off
+chcp 65001 >nul
+echo ============================================
+echo YOLO INT8 Quantization Complete Workflow
+echo ============================================
+echo.
+
+REM 激活虚拟环境
+echo [1/4] Activating yolo virtual environment...
+call conda activate yolo
+echo.
+
+REM 步骤1: 检查并导出ONNX模型
+echo [2/4] Checking ONNX model...
+if not exist yolo11n.onnx (
+    echo ONNX model not found. Exporting from yolo11n.pt...
+    if not exist yolo11n.pt (
+        echo ERROR: yolo11n.pt not found!
+        echo Please place yolo11n.pt in the current directory.
+        pause
+        exit /b 1
+    )
+    python -c "from ultralytics import YOLO; model = YOLO('yolo11n.pt'); model.export(format='onnx', dynamic=True, simplify=True, opset=12)"
+    if not exist yolo11n.onnx (
+        echo ERROR: ONNX export failed!
+        pause
+        exit /b 1
+    )
+    echo ONNX model exported successfully.
+) else (
+    echo ONNX model already exists: yolo11n.onnx
+)
+echo.
+
+REM 步骤2: 生成校准缓存
+echo [3/4] Generating calibration cache...
+if not exist yolo11n_int8.cache (
+    echo Running calibration_gen.py...
+    python calibration_gen.py
+    if not exist yolo11n_int8.cache (
+        echo ERROR: Calibration cache generation failed!
+        pause
+        exit /b 1
+    )
+    echo Calibration cache generated: yolo11n_int8.cache
+) else (
+    echo Calibration cache already exists: yolo11n_int8.cache
+)
+echo.
+
+REM 步骤3: 构建TensorRT Engine
+echo [4/4] Building TensorRT Engine...
+echo.
+echo Running trtexec with INT8 calibration...
+echo.
+
+trtexec ^
+   --onnx=yolo11n.onnx ^
+   --saveEngine=yolo11n_int8_b1_8.engine ^
+   --explicitBatch ^
+   --int8 ^
+   --fp16 ^
+   --workspace=4096 ^
+   --builderOptimizationLevel=5 ^
+   --profilingVerbosity=detailed ^
+   --calib=yolo11n_int8.cache ^
+   --minShapes=input:1x3x640x640 ^
+   --optShapes=input:4x3x640x640 ^
+   --maxShapes=input:8x3x640x640 ^
+   --useCudaGraph ^
+   --useSpinWait ^
+   --noTF32
+
+if %errorlevel% equ 0 (
+    echo.
+    echo ============================================
+    echo TensorRT Engine built successfully!
+    echo Output: yolo11n_int8_b1_8.engine
+    echo ============================================
+    echo.
+    echo Next steps:
+    echo 1. Run: python quantize_yolo.py
+    echo    to validate models and calculate mAP drop
+    echo.
+) else (
+    echo.
+    echo ============================================
+    echo Engine build failed!
+    ============================================
+    pause
+    exit /b 1
+)
+
+pause