[fbsync] fix docs typo (#3683)

Reviewed By: NicolasHug

Differential Revision: D28169151

fbshipit-source-id: c4b7a8db9a14a3cc651a8594b6a195c265b00da4

Author: cpuhrsch

torchvision/datasets/fakedata.py

@@ -10,7 +10,7 @@ class FakeData(VisionDataset):
     Args:
         size (int, optional): Size of the dataset. Default: 1000 images
         image_size(tuple, optional): Size if the returned images. Default: (3, 224, 224)
-        num_classes(int, optional): Number of classes in the datset. Default: 10
+        num_classes(int, optional): Number of classes in the dataset. Default: 10
         transform (callable, optional): A function/transform that  takes in an PIL image
             and returns a transformed version. E.g, ``transforms.RandomCrop``
         target_transform (callable, optional): A function/transform that takes in the