Fix DDP documentation (pytorch#46861)

Summary:
Pull Request resolved: pytorch#46861

Noticed that in the DDP documentation:
https://pytorch.org/docs/master/generated/torch.nn.parallel.DistributedDataParallel.html?highlight=distributeddataparallel
there were some examples with `torch.nn.DistributedDataParallel`, fix this to
read `torch.nn.parallel.DistributedDataParallel`.
ghstack-source-id: 115453703

Test Plan: ci

Reviewed By: pritamdamania87, SciPioneer

Differential Revision: D24534486

fbshipit-source-id: 64b92dc8a55136c23313f7926251fe825a2cb7d5

Author: rohan-varma

torch/nn/parallel/distributed.py

@@ -329,7 +329,7 @@ class DistributedDataParallel(Module):
     Example::
 
         >>> torch.distributed.init_process_group(backend='nccl', world_size=4, init_method='...')
-        >>> net = torch.nn.DistributedDataParallel(model, pg)
+        >>> net = torch.nn.parallel.DistributedDataParallel(model, pg)
     """
     def __init__(self, module, device_ids=None,
                  output_device=None, dim=0, broadcast_buffers=True,
@@ -626,7 +626,7 @@ def no_sync(self):
 
         Example::
 
-            >>> ddp = torch.nn.DistributedDataParallel(model, pg)
+            >>> ddp = torch.nn.parallel.DistributedDataParallel(model, pg)
             >>> with ddp.no_sync():
             >>>   for input in inputs:
             >>>     ddp(input).backward()  # no synchronization, accumulate grads