There was a warning during training. I don't know why

[DamonYangyang]

UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)

[liyunsheng13]

Thanks for letting me know the warning. I think it does not influence the implementation of the other codes. Since I cannot produce the warning on my side, could you let me know which part of the code caused it?

[DamonYangyang]

Thanks for letting me know the warning. I think it does not influence the implementation of the other codes. Since I cannot produce the warning on my side, could you let me know which part of the code caused it?

In the dataloaders.py module on lines 27 and 32, which is the "torch.from_numpy" in the fast_collate function, the tens variable in the other 27 lines seems to be useless. I don’t know if it’s the torch version. My torch is 1.6 . Of course, this warning does not affect the operation of the program

[liyunsheng13]

I think it is probably caused by the mismatch of Pytorch version since I cannot reproduce this warning on my side. Thanks for letting me know.

[wisper181]

I got the warning, too. And the program was killed then. I want to train the model on my own dataset, so I put my data under .\data. But there are some mistakes. Can you help me, plz. My environment： CUDA 10.2 Python 3.6 torch 1.8