RuntimeError: CUDA out of memory. Tried to allocate 9.00 MiB (GPU 0; 10.92 GiB total capacity; 208.18 MiB already allocated; 2.19 MiB free; 838.00 KiB cached)
https://discuss.pytorch.org/t/gpu-is-not-utilized-while-occur-runtimeerror-cuda-runtime-error-out-of-memory-at/34780
python: symbol lookup error: /your_path_to_lib/lib/python3.6/site-packages/torch/lib/libtorch_python.so: undefined symbol: PySlice_Unpack
https://github.com/pytorch/pytorch/issues/14931
pip install
transfomers
scikit-learn
matplotlib
pytorch-nlp
keras
FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
https://juejin.im/post/5d7f28946fb9a06b0703ef58
pip install numpy=1.16.4