In [2]:
import graphlab
We will use a popular benchmark dataset in computer vision called CIFAR-10.
(We've reduced the data to just 4 categories = {'cat','bird','automobile','dog'}.)
This dataset is already split into a training set and test set. In this simple retrieval example, there is no notion of "testing", so we will only use the training data.
In [3]:
image_train = graphlab.SFrame('image_train_data/')
In [5]:
image_test = graphlab.SFrame('image_test_data/')
The two lines below allow us to compute deep features. This computation takes a little while, so we have already computed them and saved the results as a column in the data you loaded.
(Note that if you would like to compute such deep features and have a GPU on your machine, you should use the GPU enabled GraphLab Create, which will be significantly faster for this task.)
In [1]:
#deep_learning_model = graphlab.load_model('http://s3.amazonaws.com/GraphLab-Datasets/deeplearning/imagenet_model_iter45')
#image_train['deep_features'] = deep_learning_model.extract_features(image_train)
In [3]:
image_train.head()
Out[3]:
In [7]:
knn_model = graphlab.nearest_neighbors.create(image_train[image_train['label']=='cat'],features=['deep_features'],
label='id')
In [9]:
graphlab.canvas.set_target('ipynb')
cat = image_train[18:19]
cat['image'].show()
In [8]:
knn_model.query(image_test[0:1])
Out[8]:
We are going to create a simple function to view the nearest neighbors to save typing:
In [9]:
def get_images_from_ids(query_result):
return image_train.filter_by(query_result['reference_label'],'id')
In [10]:
cat_neighbors = get_images_from_ids(knn_model.query(cat))
In [11]:
cat_neighbors['image'].show()
In [12]:
car = image_train[8:9]
car['image'].show()
In [13]:
get_images_from_ids(knn_model.query(car))['image'].show()
In [14]:
show_neighbors = lambda i: get_images_from_ids(knn_model.query(image_train[i:i+1]))['image'].show()
In [15]:
show_neighbors(8)
In [16]:
show_neighbors(26)
In [ ]: