When training the yolo dataset on pycharm, running train.py reports an error:
D:\Applications\anaconda3\envs\pytorch\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\TensorShape.cpp:3484.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Solution:
Find the functional.py file in the virtual environment used by pyrcharm, and find the functional 504 line according to the error message
Add code indexing = ' ij '
return _VF.meshgrid(tensors, **kwargs,indexing = 'ij') # type: ignore[attr-defined]
Although this seems to be the source code in the torch package, it should not be changed logically, but the problem is indeed solved
Reference article: YOLO UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing a_shieres' blog-CSDN Blog