Fix #70

02_production.ipynb

@@ -840,7 +840,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "> note: The `get_idx` assignment in this code is a little bit magic, and you absolutely don't have to understand it at this point. So feel free to ignore the entirety of this paragraph! This is just if you're curious… Showing different randomly varied versions of the same image is not something we normally have to do in deep learning, so it's not something that fastai provides directly. Therefore to draw the picture of data augmentation on the same image, we had to take advantage of fastai's sophisticated customisation features. DataLoader has a method called `get_idx`, which is called to decide which items should be selected next. Normally when we are training, this returns a random permutation of all of the indexes in the dataset. But pretty much everything in fastai can be changed, including how the `get_idx` method is defined, which means we can change how we sample data. So in this case, we are replacing it with a version which always returns the number one. That way, our DataLoader shows the same image again and again! This is a great example of the flexibility that fastai provides. "
+    "> note: The `get_idxs` assignment in this code is a little bit magic, and you absolutely don't have to understand it at this point. So feel free to ignore the entirety of this paragraph! This is just if you're curious… Showing different randomly varied versions of the same image is not something we normally have to do in deep learning, so it's not something that fastai provides directly. Therefore to draw the picture of data augmentation on the same image, we had to take advantage of fastai's sophisticated customisation features. DataLoader has a method called `get_idxs`, which is called to decide which items should be selected next. Normally when we are training, this returns a random permutation of all of the indexes in the dataset. But pretty much everything in fastai can be changed, including how the `get_idxs` method is defined, which means we can change how we sample data. So in this case, we are replacing it with a version which always returns the number one. That way, our DataLoader shows the same image again and again! This is a great example of the flexibility that fastai provides. "
    ]
   },
   {