search

bgshih / crnn

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.
MIT License
2.05k stars 549 forks source link

cuda runtime error (38) : no CUDA-capable device is detected #123

Open devshilei opened 6 years ago

devshilei commented 6 years ago

运行crnn_main.py文件报错： RuntimeError: cuda runtime error (38) : no CUDA-capable device is detected at /opt/conda/conda-bld/pytorch_1524586445097/work/aten/src/THC/THCGeneral.cpp:70

请大神解答。谢谢。

Aurora11111 commented 6 years ago

you should reinstall your cuda,and export it's dir

zhoujianwen commented 5 years ago

@Aurora11111 What version of cuda should be used

Aurora11111 commented 5 years ago

@zhoujianwen

nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2018 NVIDIA Corporation Built on Sat_Aug_25_21:08:01_CDT_2018 Cuda compilation tools, release 10.0, V10.0.130

BUT,I think the mainly problem is not the verison.you can do this to solve the problem: ln -s /opt/cuda/include/* /home/rice/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/ in reference: https://github.com/Aurora11111/crnn-train-pytorch