エラーメッセージの最後の部分
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 746.00 MiB. GPU 0 has a total capacity of 3.81 GiB of which 611.38 MiB is free. Process 3903313 has 3.18 GiB memory in use. Of the allocated memory 2.71 GiB is allocated by PyTorch, and 389.69 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
参考文献によるとGPUのメモリが足りずにエラーメッセージが出力されているようだ.このことから自分のPCの増強または別のマシンでの学習が必要である.
打ち込んだコマンド
python3 test.py --model_dir night_clean_raw --set_names iso_50
エラーメッセージの最後の部分
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 746.00 MiB. GPU 0 has a total capacity of 3.81 GiB of which 611.38 MiB is free. Process 3903313 has 3.18 GiB memory in use. Of the allocated memory 2.71 GiB is allocated by PyTorch, and 389.69 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
参考文献