SystemError: ＜class ‘cv2.dnn.DetectionModel‘＞ returned a result with an exception set

我在用opevCV的MobileNet模型做物体对象识别的时候出现如下报错：

cv2.error: OpenCV(4.7.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\caffe\caffe_io.cpp:1138: error: (-2:Unspecified error) FAILED: fs.is_open(). Can't open "frozen_inference_graph.pb" in function 'cv::dnn::ReadProtoFromBinaryFile'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "D:\ZJ\Pycharm\PyCharm Projects\Python_study\MobileNet检测物体.py", line 25, in <module>
    model = cv2.dnn_DetectionModel(frozen_model, config_file)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
SystemError: <class 'cv2.dnn.DetectionModel'> returned a result with an exception set

Process finished with exit code 1
报错部分代码如下：

frozen_model = 'frozen_inference_graph.pb'
config_file = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
model = cv2.dnn_DetectionModel(frozen_model, config_file)

我的解决方案是将 'frozen_inference_graph.pb'和 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'文件换成了绝对路径，问题得到解决。