运行YOLOv3代码遇cv2.error: Unknown C++ exception报错求助

运行基于OpenCV的YOLOv3目标检测代码时，执行layerOutputs = net.forward(output_layers_names)语句触发错误：cv2.error: Unknown C++ exception from OpenCV code，更换多个OpenCV版本后问题依旧。

代码如下：

import cv2
import numpy as np

net = cv2.dnn.readNet('yolov3.weights', 'yolov3.cfg')

classes = []
with open("coco.txt", "r") as f:
    classes = f.read().splitlines()

cap = cv2.VideoCapture(0)

font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0, 255, size=(100, 3))

while True:
    _, img = cap.read()
    height, width, _ = img.shape

    blob = cv2.dnn.blobFromImage(img, 1/255, (416, 416), (0,0,0), swapRB=True, crop=False)
    net.setInput(blob)
    output_layers_names = net.getUnconnectedOutLayersNames()
    layerOutputs = net.forward(output_layers_names)

    boxes = []
    confidences = []
    class_ids = []

    for output in layerOutputs:
        for detection in output:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > 0.3:
                center_x = int(detection[0]*width)
                center_y = int(detection[1]*height)
                w = int(detection[2]*width)
                h = int(detection[3]*height)

                x = int(center_x - w/2)
                y = int(center_y - h/2)

                boxes.append([x, y, w, h])
                confidences.append((float(confidence)))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.2, 0.4)

    if len(indexes)>0:
        for i in indexes.flatten():
            x, y, w, h = boxes[i]
            label = str(classes[class_ids[i]])
            confidence = str(round(confidences[i],2))
            color = colors[i]
            cv2.rectangle(img, (x,y), (x+w, y+h), color, 2)
            cv2.putText(img, label + " " + confidence, (x, y+20), font, 2, (255,255,255), 2)

    cv2.imshow('Image', img)
    key = cv2.waitKey(1)
    if key==27:
        break

cap.release()
cv2.destroyAllWindows()

问题截图：

• 检查模型文件完整性：确认yolov3.weights、yolov3.cfg、coco.txt路径正确且未损坏。weights文件约240MB，若下载中断会导致文件残缺，可重新下载官方版本并验证MD5值。
• 验证摄像头输入：cv2.VideoCapture(0)调用默认摄像头，若设备不存在或被占用，img可能为空，引发后续blob处理异常。可添加判断逻辑：

  _, img = cap.read()
  if img is None:
      print("无法读取摄像头画面")
      continue
  

• 指定DNN后端与目标设备：OpenCV的dnn模块支持多后端，强制指定可解决兼容性问题：

  net = cv2.dnn.readNet('yolov3.weights', 'yolov3.cfg')
  # 有GPU时优先用CUDA加速
  net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
  net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)
  # 无GPU则用CPU后端
  # net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
  # net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
  

• 核对输入尺寸配置：YOLOv3输入尺寸需为32的倍数（如416、608），确保blobFromImage的(416,416)与cfg文件中width、height参数完全一致。
• 排查OpenCV编译问题：若用源码编译OpenCV，需确认编译时开启了DNN模块及对应后端支持；用pip安装时，优先选择官方预编译包，避免第三方编译版本的兼容性bug。

内容的提问来源于stack exchange，提问作者Bagas30h