[MUSIC] So in this deep learning module, we talked about two really cool things
that you can do with deep learning. One is classify images, and
the other one is retrieve images. And in both of them,
we talked about deep features. So let's just go ahead and
build a notebook for image classifications using deep features. So, let's give this notebook a name. So, this is going to be
Image Classification with Deep Features. And I'm going to hide the header and the toolbar to get a little
bit more space, as usual. And we'll fire up. Actually I just did a little typo here so we will, Fire up GraphLabCreates. So let's import GraphLab, So here we go. So the first thing that we're going to do
is load a common image analysis dataset. So this is a benchmark
dataset called a SIFR10. We select a subset of those where
we just have four categories of objects we're trying to recognize. So I'm going to load the data set, and this data set has already been split
into train data and test data, because in computer vision, often that
split happens so every researcher uses the same training set and the same test
set, so the papers become more comparable. So, I'm just gonna load an S
frame that contains the data set. So, graphlab.SFrame and for the training data, there's a directory
here called image_train_data. And then for the test data, so
let's call that image_test. We have another SFrame. Code image_test_data. Here we go, so
we are loading this two data sets, and let's start by exploring
the data a little bit. So, exploring the image data. So, what we're gonna do is use canvas. So, I'm gonna point canvas
to show it on the notebook, as we have been doing
on several notebooks. So, it becomes all one thing
that we can take home. So, I'm gonna set graphlab.canvas and I'm going to set the target
to be the ipython notebook. So it's going to print anything on
the iPython notebook that we do. And let's start by taking
a look at the string data. So image string, and
here's a few columns but the column that we really care
about here is the image column. I am just going to type .show on that and we are going to take a quick
look at that image column. And these images are not too large,
so I'm temporarily going to increase the font here so
we can take a look at the images. And so if you look at it, there's a bird,
there's some cats, there's some dogs and some cars. So this data set is all about cats,
dogs, cars, and birds. [MUSIC]