Merge pull request #73 from gchanan/cpugpudesc

soumith · web-flow · commit 6756514f09e9 · 2017-04-21T15:27:36.000-04:00
Simplify description of CPU/GPU tensor type consistency.
diff --git a/beginner_source/former_torchies/tensor_tutorial.py b/beginner_source/former_torchies/tensor_tutorial.py
@@ -127,9 +127,8 @@
 # CUDA Tensors
 # ------------
 #
-# CUDA Tensors are nice and easy in pytorch, and they are much more
-# consistent as well. Transfering a CUDA tensor from the CPU to GPU will
-# retain it’s type.
+# CUDA Tensors are nice and easy in pytorch, and transfering a CUDA tensor
+# from the CPU to GPU will retain its underlying type.
 
 # let us run this cell only if CUDA is available
 if torch.cuda.is_available():
