cuda runtime error (38) : no CUDA-capable device is detected at /pytorch/torch/lib/THC/THCGeneral.c:70

ruoqianguo / DetNet_pytorch

An implementation of DetNet: A Backbone network for Object Detection.

MIT License

377 stars 117 forks source link

cuda runtime error (38) : no CUDA-capable device is detected at /pytorch/torch/lib/THC/THCGeneral.c:70 #16

Closed asgq123 closed 6 years ago

asgq123 commented 6 years ago

hello, when i train the pascal_voc_0712, this problem comes： cuda runtime error (38) : no CUDA-capable device is detected at /pytorch/torch/lib/THC/THCGeneral.c:70 could you tell me why? I don't sure if i need reinstall the graphics driver.thanks a lot. And my cuda version is 8.0, pytorch 0.3.0,graphics driver 384

asgq123 commented 6 years ago

just change CUDA_VISIBLE_DEVICES=3 to CUDA_VISIBLE_DEVICES=0,because my gpu name is 0.