So, congratulations on
finishing week two. I hope you really enjoyed
this week as much as I did, because image augmentation
is frankly is one of my favorite things to
play with in TensorFlow. I really enjoy the fact that when you have got
a small dataset, like this one with
the horses versus humans, that you're able to manipulate that dataset without changing the underlying images to open up whole new scenarios for training and to be able
to train like we saw, like a man lying down
or a woman facing left, and to be able to train
for that even if you don't have those images
in your training set. But next week, we're going
to be doing something really exciting and that's
called transfer learning. So, stay tuned.