gpu改成CPU出错了

[19chang19]

Traceback (most recent call last):
File "train.py", line 85, in
input = Variable(input).cuda()
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/cuda/init.py", line 178, in _lazy_init
_check_driver()
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/cuda/init.py", line 92, in _check_driver
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

出现这个问题时，我瞎改了下
input = Variable(input).cpu() #.cuda()
target = Variable(torch.from_numpy(np.array(target)).long()).cpu() #.cuda()

再跑一遍出现下面的错了。。。。。。

Traceback (most recent call last):
File "train.py", line 87, in
output = model(input)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/root/mycode/myimage_class/Model.py", line 102, in forward
x = self.backbone.layer2(x)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
input = module(input)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torchvision/models/resnet.py", line 106, in forward
out = self.conv3(out)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 343, in forward
return self.conv2d_forward(input, self.weight)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 340, in conv2d_forward
self.padding, self.dilation, self.groups)
File "/root/anaconda3/envs/pytorch3712/lib/python3.7/site-packages/torch/utils/data/_utils/signal_handling.py", line 66, in handler
_error_if_any_worker_fails()
RuntimeError: DataLoader worker (pid 24624) is killed by signal: Killed.