完整错误如下:
/data/home/file_name/.conda/envs/cmr/lib/python3.7/site-packages/torch/utils/data/_utils/collate.py:63:
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 /opt/conda/conda-bld/pytorch_1603729006826/work/torch/csrc/utils/tensor_numpy.cpp:141.)
return default_collate([torch.as_tensor(b).copy() for b in batch])
翻译一下:
给定的NumPy数组不可写,PyTorch不支持不可写张量。
这意味着您可以使用张量写入底层(假定不可写)NumPy数组。
在将数组转换为张量之前,可能需要复制数组以保护其数据或使其可写。
解决办法:
根据
/data/home/file_name/.conda/envs/cmr/lib/python3.7/site-packages/torch/utils/data/_utils/collate.py:63
找到第63行进行修改:
# 将
return default_collate([torch.as_tensor(b) for b in batch])
# 修改为
return default_collate([torch.as_tensor(b.copy()) for b in batch])
问题解决!