Problem 1: There is no solution for PyCharm code editing prompts
问题2: RuntimeError: result type Float can't be cast to the desired output type long int
Question 3: Entering our \yolov5-4.0\runs\detect\exp folder, you can see that although there are result pictures, the recognition results are not framed.
But the detection speed will be slower
问题4:RuntimeError: The size of tensor a (60) must match the size of tensor b (56) at non-singLeton dimension 3
This error occurs because you add the v6.1 SPPF class to common.py under the models file and add the import warnings package . This solution will cause the above error.
The basic method is:
Re-download the yolov5s.pt weight file
Download address: https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5s.pt
问题5:AttributeError: Can't get attribute 'SPPF' on <module 'models.common' from 'C:\\Users\\Administrator\\Desktop\\yolov5\\yolov5-5.0\\models\\common.py'>
Re-download the yolov5s.pt weight file
Download address: https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5s.pt
Question 6: In project yolo v5, an AttributeError error occurs when the terminal executes the detect.py file.