some problems about readNetFromDarknet

[nuistlyk]

here is the traceback when we try to run detects_sms__img.py

Traceback (most recent call last):
  File "spam_hunter.py", line 75, in <module>
    spamhunter =SpamHunter(start_time.strftime('%Y-%m-%dT%HZ'), end_time.strftime('%Y-%m-%dT%HZ'))
  File "spam_hunter.py", line 20, in __init__
    self.smsDetector: SMSDetector = SMSDetector()
  File "/home/ykli/spamhunter/SpamHunter-main/detect_sms_img.py", line 16, in __init__
    self.net, self.output_layers = self.load_model()
  File "/home/ykli/spamhunter/SpamHunter-main/detect_sms_img.py", line 20, in load_model
    net = cv2.dnn.readNetFromDarknet(self.config, self.weights)
cv2.error: OpenCV(4.6.0) /io/opencv/modules/dnn/src/darknet/darknet_io.cpp:933: error: (-213:The function/feature is not implemented) Transpose the weights (except for convolutional) is not implemented in function 'ReadDarknetFromWeightsStream'

and i have solved this problem after reading stack overflow

[opmusic]

For large files (i.e., twitter_train_yolo_final.weights in the pretrained models), we recommend to download it with git lfs.