chore: update project docs and scripts for new dataset

- 更新README.md数据集描述（12类，6735训练图+765验证图）
- 更新模型性能指标（新12类模型结果）
- 删除已过时的download_dataset.py和retry_download.py脚本
- 更新usage_example.py使用正确的路径和模型名

scripts/download_dataset.py

@@ -1,152 +0,0 @@
-#!/usr/bin/env python3
-"""
-数据集下载脚本
-从SCIDB下载红外电力设备数据集
-"""
-
-import argparse
-import sys
-import time
-from pathlib import Path
-from urllib.parse import urlparse, parse_qs
-
-import requests
-from tqdm import tqdm
-
-
-def parse_urls_file(file_path: Path) -> list:
-    """解析URL文件，返回URL和类别信息"""
-    with open(file_path, 'r', encoding='utf-8') as f:
-        lines = f.readlines()
-
-    items = []
-    for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-
-        # 解析URL获取类别和文件名
-        parsed = urlparse(line)
-        query = parse_qs(parsed.query)
-
-        path = query.get('path', [''])[0]
-        filename = query.get('fileName', ['unknown.jpg'])[0]
-
-        # 从路径提取类别
-        parts = path.split('/')
-        if len(parts) >= 3:
-            category = parts[-2]  # 如 "Wave Traps"
-        else:
-            category = "Unknown"
-
-        items.append({
-            'url': line,
-            'filename': filename,
-            'category': category
-        })
-
-    return items
-
-
-def create_directories(base_dir: Path, categories: set) -> dict:
-    """创建类别目录"""
-    dirs = {}
-    for cat in categories:
-        cat_dir = base_dir / cat
-        cat_dir.mkdir(parents=True, exist_ok=True)
-        dirs[cat] = cat_dir
-    return dirs
-
-
-def download_file(url: str, output_path: Path, session: requests.Session) -> bool:
-    """下载单个文件"""
-    try:
-        response = session.get(url, timeout=30, stream=True)
-        response.raise_for_status()
-
-        with open(output_path, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-
-        return True
-    except Exception as e:
-        print(f"Error downloading {output_path.name}: {e}")
-        return False
-
-
-def download_dataset(urls_file: Path, output_dir: Path, max_workers: int = 4) -> None:
-    """下载整个数据集"""
-    print("=" * 50)
-    print("开始下载红外电力设备数据集")
-    print("=" * 50)
-
-    # 解析URL
-    print("解析URL文件...")
-    items = parse_urls_file(urls_file)
-    print(f"共找到 {len(items)} 个文件")
-
-    # 创建目录
-    categories = set(item['category'] for item in items)
-    print(f"发现 {len(categories)} 个类别: {categories}")
-    dirs = create_directories(output_dir, categories)
-
-    # 创建session
-    session = requests.Session()
-    session.headers.update({
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
-    })
-
-    # 统计
-    success_count = 0
-    fail_count = 0
-
-    # 下载文件
-    print("\n开始下载...")
-    for item in tqdm(items, desc="下载进度"):
-        category_dir = dirs[item['category']]
-        output_path = category_dir / item['filename']
-
-        # 跳过已存在的文件
-        if output_path.exists():
-            success_count += 1
-            continue
-
-        if download_file(item['url'], output_path, session):
-            success_count += 1
-        else:
-            fail_count += 1
-
-        # 避免请求过快
-        time.sleep(0.1)
-
-    print("\n" + "=" * 50)
-    print(f"下载完成!")
-    print(f"成功: {success_count}")
-    print(f"失败: {fail_count}")
-    print(f"数据目录: {output_dir}")
-    print("=" * 50)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="下载红外电力设备数据集")
-    parser.add_argument("--urls-file", type=str,
-                       default="data/dataurls.txt",
-                       help="URL列表文件")
-    parser.add_argument("--output-dir", type=str,
-                       default="data/raw/images",
-                       help="输出目录")
-
-    args = parser.parse_args()
-
-    urls_file = Path(args.urls_file)
-    output_dir = Path(args.output_dir)
-
-    if not urls_file.exists():
-        print(f"错误: URL文件不存在: {urls_file}")
-        sys.exit(1)
-
-    download_dataset(urls_file, output_dir)
-
-
-if __name__ == "__main__":
-    main()

scripts/retry_download.py

@@ -1,152 +0,0 @@
-#!/usr/bin/env python3
-"""
-重试下载失败的图片（429限速后等待重试）
-"""
-
-import argparse
-import sys
-import time
-from pathlib import Path
-from urllib.parse import urlparse, parse_qs
-
-import requests
-from tqdm import tqdm
-
-
-def parse_urls_file(file_path: Path) -> list:
-    """解析URL文件，返回URL和类别信息"""
-    with open(file_path, 'r', encoding='utf-8') as f:
-        lines = f.readlines()
-
-    items = []
-    for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-
-        parsed = urlparse(line)
-        query = parse_qs(parsed.query)
-        path = query.get('path', [''])[0]
-        filename = query.get('fileName', ['unknown.jpg'])[0]
-
-        parts = path.split('/')
-        if len(parts) >= 3:
-            category = parts[-2]
-        else:
-            category = "Unknown"
-
-        items.append({
-            'url': line,
-            'filename': filename,
-            'category': category
-        })
-
-    return items
-
-
-def create_directories(base_dir: Path, categories: set) -> dict:
-    dirs = {}
-    for cat in categories:
-        cat_dir = base_dir / cat
-        cat_dir.mkdir(parents=True, exist_ok=True)
-        dirs[cat] = cat_dir
-    return dirs
-
-
-def download_file(url: str, output_path: Path, session: requests.Session) -> bool:
-    try:
-        response = session.get(url, timeout=30, stream=True)
-        response.raise_for_status()
-
-        with open(output_path, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-        return True
-    except Exception as e:
-        return False
-
-
-def get_missing_files(urls_file: Path, output_dir: Path) -> list:
-    """获取缺失文件的URL列表"""
-    items = parse_urls_file(urls_file)
-    missing = []
-
-    for item in items:
-        category_dir = output_dir / item['category']
-        output_path = category_dir / item['filename']
-
-        if not output_path.exists() or output_path.stat().st_size == 0:
-            missing.append(item)
-
-    return missing
-
-
-def retry_download(urls_file: Path, output_dir: Path, max_retries: int = 3,
-                   wait_seconds: int = 60) -> None:
-    """重试下载失败的文件"""
-    print("=" * 50)
-    print("重试下载失败的文件")
-    print("=" * 50)
-
-    # 找到缺失的文件
-    missing = get_missing_files(urls_file, output_dir)
-    print(f"缺失 {len(missing)} 个文件")
-
-    if not missing:
-        print("没有缺失文件，下载完成！")
-        return
-
-    categories = set(item['category'] for item in missing)
-    dirs = create_directories(output_dir, categories)
-
-    session = requests.Session()
-    session.headers.update({
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
-    })
-
-    success_count = 0
-    fail_count = 0
-
-    print(f"\n等待 {wait_seconds} 秒以避免限速...")
-    time.sleep(wait_seconds)
-
-    print("\n开始重试下载...")
-    for item in tqdm(missing, desc="重试进度"):
-        category_dir = dirs[item['category']]
-        output_path = category_dir / item['filename']
-
-        if download_file(item['url'], output_path, session):
-            success_count += 1
-        else:
-            fail_count += 1
-            time.sleep(1)  # 失败后稍作等待
-
-        time.sleep(0.2)  # 避免过快请求
-
-    print("\n" + "=" * 50)
-    print(f"重试完成!")
-    print(f"成功: {success_count}")
-    print(f"失败: {fail_count}")
-    print("=" * 50)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="重试下载失败的文件")
-    parser.add_argument("--urls-file", type=str, default="data/dataurls.txt")
-    parser.add_argument("--output-dir", type=str, default="data/raw/images")
-    parser.add_argument("--wait", type=int, default=60, help="初始等待秒数")
-
-    args = parser.parse_args()
-
-    urls_file = Path(args.urls_file)
-    output_dir = Path(args.output_dir)
-
-    if not urls_file.exists():
-        print(f"错误: URL文件不存在: {urls_file}")
-        sys.exit(1)
-
-    retry_download(urls_file, output_dir, wait_seconds=args.wait)
-
-
-if __name__ == "__main__":
-    main()

scripts/usage_example.py

@@ -19,8 +19,8 @@ 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/infrared_yolov8n.pt", conf=0.25)
-    detections = detector.detect("data/infrared/images/val/FLIR0166.jpg")
+    detector = InfraredDetector("weights/best.pt", conf=0.25)
+    detections = detector.detect("data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg")
 
     print(f"检测到 {len(detections)} 个目标:")
     for i, det in enumerate(detections):
@@ -34,9 +34,9 @@ def example2_detect_and_draw():
     output_dir = Path(__file__).parent.parent / "output"
     output_dir.mkdir(exist_ok=True)
 
-    detector = InfraredDetector("weights/infrared_yolov8n.pt")
+    detector = InfraredDetector("weights/best.pt")
     detector.detect_and_draw(
-        "data/infrared/images/val/FLIR0166.jpg",
+        "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg",
         output_path=str(output_dir / "detection_result.jpg")
     )
     print(f"结果已保存至: {output_dir / 'detection_result.jpg'}")
@@ -46,14 +46,15 @@ def example3_temperature_extraction():
     """示例3：温度特征提取"""
     print("\n【示例3】温度特征提取")
 
-    extractor = TempFeatureExtractor("weights/infrared_yolov8n.pt")
-    detector = InfraredDetector("weights/infrared_yolov8n.pt")
+    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("data/infrared/images/val/FLIR0166.jpg", cv2.IMREAD_GRAYSCALE)
+    gray_img = cv2.imread(sample_image, cv2.IMREAD_GRAYSCALE)
 
     # 检测目标
-    detections = detector.detect("data/infrared/images/val/FLIR0166.jpg")
+    detections = detector.detect(sample_image)
 
     # 提取第一个检测框的温度特征
     if detections:
@@ -71,8 +72,9 @@ def example4_fault_diagnosis():
     """示例4：故障诊断"""
     print("\n【示例4】故障诊断")
 
-    diagnoser = FaultDiagnoser("weights/infrared_yolov8n.pt")
-    result = diagnoser.diagnose("data/infrared/images/val/FLIR0166.jpg")
+    sample_image = "data/valid/images/20230907095711003_jpg.rf.0e14e8b4344dce21114683dc3f3e7e2e.jpg"
+    diagnoser = FaultDiagnoser("weights/best.pt")
+    result = diagnoser.diagnose(sample_image)
 
     print(f"诊断状态: {result['summary']['status']}")
     print(f"故障类型: {result['summary']['fault_types']}")
@@ -88,9 +90,9 @@ def example5_batch_diagnosis():
     output_dir = Path(__file__).parent.parent / "output"
     output_dir.mkdir(exist_ok=True)
 
-    diagnoser = FaultDiagnoser("weights/infrared_yolov8n.pt")
+    diagnoser = FaultDiagnoser("weights/best.pt")
     diagnoser.batch_diagnose(
-        "data/infrared/images/val",
+        "data/valid/images",
         str(output_dir / "batch_results.json")
     )
     print(f"批量诊断完成，结果已保存至: {output_dir / 'batch_results.json'}")
@@ -100,14 +102,15 @@ 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
         "std_temp": 40     # 标准差阈值
     }
 
-    diagnoser = FaultDiagnoser("weights/infrared_yolov8n.pt", temp_threshold=threshold)
-    result = diagnoser.diagnose("data/infrared/images/val/FLIR0166.jpg")
+    diagnoser = FaultDiagnoser("weights/best.pt", temp_threshold=threshold)
+    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']}")