pytorch報錯RuntimeError: DataLoader worker (pid(s) xxx) exited unexpectedly

報錯

pytorch報錯RuntimeError: 
DataLoader worker (pid(s) ... exited unexpectedly

解決

因爲torch.utils.data.DataLoader中設置了num_works=4，也就是多線程讀取。

根據其他方法，我設置num_works=1或者num_works=0都不行。

最後重裝了pytorch，就可以了。

pip install torch==1.5.1+cu101 torchvision==0.6.1+cu101 -f https://download.pytorch.org/whl/torch_stable.html

原因分析

過程中顯示下面內容，所以，可能是因爲有些包用pip install的時候沒裝上吧。

The following packages will be downloaded:

    package                    |            build
    ---------------------------|-----------------
    certifi-2020.6.20          |           py36_0         160 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    numpy-base-1.18.5          |   py36hde5b4d6_0         5.1 MB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    mkl_random-1.1.1           |   py36h0573a6f_0         382 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    mkl_fft-1.1.0              |   py36h23d657b_0         159 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    numpy-1.18.5               |   py36ha1c710e_0           4 KB  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
    ------------------------------------------------------------
                                           Total:         5.8 MB

The following NEW packages will be INSTALLED:

    blas:           1.0-mkl                               https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    cudatoolkit:    10.1.243-h6bb024c_0                   https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    intel-openmp:   2020.1-217                            https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    libgfortran-ng: 7.3.0-hdf63c60_0                      https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    mkl:            2020.1-217                            https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    mkl-service:    2.3.0-py36he904b0f_0                  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    mkl_fft:        1.1.0-py36h23d657b_0                  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    mkl_random:     1.1.1-py36h0573a6f_0                  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    ninja:          1.9.0-py36hfd86e86_0                  https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    numpy:          1.18.5-py36ha1c710e_0                 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    numpy-base:     1.18.5-py36hde5b4d6_0                 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main    
    pytorch:        1.4.0-py3.6_cuda10.1.243_cudnn7.6.3_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch
    six:            1.15.0-py_0                           https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main 
    ```