Merge pull request #4 from NVIDIA/mask-utils-0.4

mask utils update for 0.4 cuda

utils.py

@@ -5,7 +5,7 @@ import torch
 
 def get_mask_from_lengths(lengths):
     max_len = torch.max(lengths)
-    ids = torch.arange(0, max_len, out=torch.LongTensor(max_len)).cuda()
+    ids = torch.arange(0, max_len).long().cuda()
     mask = (ids < lengths.unsqueeze(1)).byte()
     return mask