Error Cuda about knowledge-distillation-pytorch HOT 1 CLOSED

Hi, this is the error I got while executing this comman, could you please check this?

python3 train.py --model_dir experiments/resnet18_distill/resnext_teacher
Loading the datasets...
Files already downloaded and verified
Files already downloaded and verified
Files already downloaded and verified
Files already downloaded and verified

• done.
  /u/halle/yeganeh/home_at/Desktop/git/knowledge-distillation-pytorch/model/resnext.py:82: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_.
  init.kaiming_normal(self.classifier.weight)
  /u/halle/yeganeh/home_at/Desktop/git/knowledge-distillation-pytorch/model/resnext.py:87: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_.
  init.kaiming_normal(self.state_dict()[key], mode='fan_out')
  THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=51 error=30 : unknown error
  Traceback (most recent call last):
  File "train.py", line 421, in
  teacher_model = nn.DataParallel(teacher_model).cuda()
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 260, in cuda
  return self._apply(lambda t: t.cuda(device))
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 187, in _apply
  module._apply(fn)
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/sitepython3 train.py --model_dir experiments/resnet18_distill/resnext_teacher
  Loading the datasets...
  Files already downloaded and verified
  Files already downloaded and verified
  Files already downloaded and verified
  Files already downloaded and verified
• done.
  /u/halle/yeganeh/home_at/Desktop/git/knowledge-distillation-pytorch/model/resnext.py:82: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_.
  init.kaiming_normal(self.classifier.weight)
  /u/halle/yeganeh/home_at/Desktop/git/knowledge-distillation-pytorch/model/resnext.py:87: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_.
  init.kaiming_normal(self.state_dict()[key], mode='fan_out')
  THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=51 error=30 : unknown error
  Traceback (most recent call last):
  File "train.py", line 421, in
  teacher_model = nn.DataParallel(teacher_model).cuda()
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 260, in cuda
  return self._apply(lambda t: t.cuda(device))
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 187, in _apply
  module._apply(fn)
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 187, in _apply
  module._apply(fn)
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
  param.data = fn(param.data)
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 260, in
  return self._apply(lambda t: t.cuda(device))
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/cuda/init.py", line 162, in _lazy_init
  torch._C._cuda_init()
  RuntimeError: cuda runtime error (30) : unknown error at /pytorch/aten/src/THC/THCGeneral.cpp:51
  -packages/torch/nn/modules/module.py", line 187, in _apply
  module._apply(fn)
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
  param.data = fn(param.data)
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 260, in
  return self._apply(lambda t: t.cuda(device))
  File "/u/halle/yeganeh/home_at/.local/lib/python3.6/site-packages/torch/cuda/init.py", line 162, in _lazy_init
  torch._C._cuda_init()
  RuntimeError: cuda runtime error (30) : unknown error at /pytorch/aten/src/THC/THCGeneral.cpp:51

From "* RuntimeError: cuda runtime error (30)", it looks like the error has to do with your GPU and CUDA environment. Can you confirm that that you have GPU and CUDA driver configured correctly?

from knowledge-distillation-pytorch.