Update onnx.rst for v0.4 (pytorch#10810)

Summary:
Since we don't need `torch.autograd.Variable` anymore, I removed `torch.autograd.Variable` from `onnx.rst`.
Pull Request resolved: pytorch#10810

Differential Revision: D9500960

Pulled By: zou3519

fbshipit-source-id: 1bc820734c96a8c7cb5d804e6d51a95018db8e7f

Author: narumiruna

docs/source/onnx.rst

@@ -9,11 +9,10 @@ Here is a simple script which exports a pretrained AlexNet as defined in
 torchvision into ONNX.  It runs a single round of inference and then
 saves the resulting traced model to ``alexnet.onnx``::
 
-    from torch.autograd import Variable
-    import torch.onnx
+    import torch
     import torchvision
 
-    dummy_input = Variable(torch.randn(10, 3, 224, 224)).cuda()
+    dummy_input = torch.randn(10, 3, 224, 224, device='cuda')
     model = torchvision.models.alexnet(pretrained=True).cuda()
 
     # Providing input and output names sets the display names for values