refactor: extract repeated sample image path to module constant

Replace 6 inline string repetitions of the sample image path with
a single SAMPLE_IMAGE module-level constant for easier maintenance.

scripts/usage_example.py

@@ -14,13 +14,15 @@ from src.diagnose import FaultDiagnoser
 import cv2
 import json
 
+SAMPLE_IMAGE = "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg"
+
 
 def example1_basic_detection():
     """示例1：基础目标检测"""
     print("\n【示例1】基础目标检测")
 
     detector = InfraredDetector("weights/best.pt", conf=0.25)
-    detections = detector.detect("data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg")
+    detections = detector.detect(SAMPLE_IMAGE)
 
     print(f"检测到 {len(detections)} 个目标:")
     for i, det in enumerate(detections):
@@ -36,7 +38,7 @@ def example2_detect_and_draw():
 
     detector = InfraredDetector("weights/best.pt")
     detector.detect_and_draw(
-        "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg",
+        SAMPLE_IMAGE,
         output_path=str(output_dir / "detection_result.jpg")
     )
     print(f"结果已保存至: {output_dir / 'detection_result.jpg'}")
@@ -46,15 +48,14 @@ def example3_temperature_extraction():
     """示例3：温度特征提取"""
     print("\n【示例3】温度特征提取")
 
-    sample_image = "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg"
     extractor = TempFeatureExtractor("weights/best.pt")
     detector = InfraredDetector("weights/best.pt")
 
     # 读取图像
-    gray_img = cv2.imread(sample_image, cv2.IMREAD_GRAYSCALE)
+    gray_img = cv2.imread(SAMPLE_IMAGE, cv2.IMREAD_GRAYSCALE)
 
     # 检测目标
-    detections = detector.detect(sample_image)
+    detections = detector.detect(SAMPLE_IMAGE)
 
     # 提取第一个检测框的温度特征
     if detections:
@@ -72,9 +73,8 @@ def example4_fault_diagnosis():
     """示例4：故障诊断"""
     print("\n【示例4】故障诊断")
 
-    sample_image = "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg"
     diagnoser = FaultDiagnoser("weights/best.pt")
-    result = diagnoser.diagnose(sample_image)
+    result = diagnoser.diagnose(SAMPLE_IMAGE)
 
     print(f"诊断状态: {result['summary']['status']}")
     print(f"故障类型: {result['summary']['fault_types']}")
@@ -102,7 +102,6 @@ def example6_custom_threshold():
     """示例6：自定义温度阈值"""
     print("\n【示例6】自定义温度阈值")
 
-    sample_image = "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg"
     # 自定义温度阈值
     threshold = {
         "max_temp": 200,   # 最高温度阈值
@@ -110,7 +109,7 @@ def example6_custom_threshold():
     }
 
     diagnoser = FaultDiagnoser("weights/best.pt", temp_threshold=threshold)
-    result = diagnoser.diagnose(sample_image)
+    result = diagnoser.diagnose(SAMPLE_IMAGE)
 
     print(f"使用自定义阈值: max_temp={threshold['max_temp']}, std_temp={threshold['std_temp']}")
     print(f"诊断结果: {result['summary']['status']}")