I get this error while doing the training:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-30-d2b2adb629c5> in <module>
20 # Define the loss
21 loss = criterion(outputs, labels.long().cuda())
---> 22 loss.backward()
23 optimizer.step()
24
~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph)
91 products. Defaults to ``False``.
92 """
---> 93 torch.autograd.backward(self, gradient, retain_graph, create_graph)
94
95 def register_hook(self, hook):
~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables)
87 Variable._execution_engine.run_backward(
88 tensors, grad_tensors, retain_graph, create_graph,
---> 89 allow_unreachable=True) # allow_unreachable flag
90
91
RuntimeError: CUDNN_STATUS_EXECUTION_FAILED
I changed it to cpu and I get the following error:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-31-6b269cdd76cf> in <module>
20
21 # Define the loss
---> 22 loss = criterion(outputs, labels.long())
23 loss.backward()
24 optimizer.step()
~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
489 result = self._slow_forward(*input, **kwargs)
490 else:
--> 491 result = self.forward(*input, **kwargs)
492 for hook in self._forward_hooks.values():
493 hook_result = hook(self, input, result)
~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
191 _assert_no_grad(target)
192 return F.nll_loss(input, target, self.weight, self.size_average,
--> 193 self.ignore_index, self.reduce)
194
195
~/miniconda3/envs/deep_mol/lib/python3.6/site-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce)
1332 return torch._C._nn.nll_loss(input, target, weight, size_average, ignore_index, reduce)
1333 elif dim == 4:
-> 1334 return torch._C._nn.nll_loss2d(input, target, weight, size_average, ignore_index, reduce)
1335 elif dim == 3 or dim > 4:
1336 n = input.size(0)
RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed. at /opt/conda/conda-bld/pytorch_1525909934016/work/aten/src/THNN/generic/SpatialClassNLLCriterion.c:111
Could someone help?