Deep features for image retrieval - assignment

In [1]:

    

import graphlab


    

In [2]:

    

image_train = graphlab.SFrame('image_train_data/')
image_test = graphlab.SFrame('image_test_data/')


    

    




[INFO] This non-commercial license of GraphLab Create is assigned to kgrodzicki@gmail.comand will expire on October 14, 2016. For commercial licensing options, visit https://dato.com/buy/.

[INFO] Start server at: ipc:///tmp/graphlab_server-64 - Server binary: /usr/local/lib/python2.7/dist-packages/graphlab/unity_server - Server log: /tmp/graphlab_server_1448103269.log
[INFO] GraphLab Server Version: 1.6.1

In [4]:

    

image_train['label'].sketch_summary()


    

    
Out[4]:





+------------------+-------+----------+
|       item       | value | is exact |
+------------------+-------+----------+
|      Length      |  2005 |   Yes    |
| # Missing Values |   0   |   Yes    |
| # unique values  |   4   |    No    |
+------------------+-------+----------+

Most frequent items:
+-------+------------+-----+-----+------+
| value | automobile | cat | dog | bird |
+-------+------------+-----+-----+------+
| count |    509     | 509 | 509 | 478  |
+-------+------------+-----+-----+------+

In [5]:

    

dogs = image_train[image_train['label'] == 'dog']
automobiles = image_train[image_train['label'] == 'automobile']
cats = image_train[image_train['label'] == 'cat']
birds = image_train[image_train['label'] == 'bird']


    

In [22]:

    

cat_image = image_test[0:1]
cat_image['image'].show()


    

In [28]:

    

cat_model = graphlab.nearest_neighbors.create(cats,
                                              features=['deep_features'],
                                              label='id')
car_model = graphlab.nearest_neighbors.create(automobiles,
                                              features=['deep_features'],
                                              label='id')
dog_model = graphlab.nearest_neighbors.create(dogs,
                                              features=['deep_features'],
                                              label='id')
bird_model = graphlab.nearest_neighbors.create(birds,
                                              features=['deep_features'],
                                              label='id')


    

    




PROGRESS: Starting brute force nearest neighbors model training.
PROGRESS: Starting brute force nearest neighbors model training.
PROGRESS: Starting brute force nearest neighbors model training.
PROGRESS: Starting brute force nearest neighbors model training.

In [9]:

    

cat_model.query(cat_image)


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.196464    | 13.6ms       |
PROGRESS: | Done         |         | 100         | 135.341ms    |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[9]:





    

        
query_label
        
reference_label
        
distance
        
rank
    
    

        
0
        
16289
        
34.623719208
        
1
    
    

        
0
        
45646
        
36.0068799284
        
2
    
    

        
0
        
32139
        
36.5200813436
        
3
    
    

        
0
        
25713
        
36.7548502521
        
4
    
    

        
0
        
331
        
36.8731228168
        
5
    

[5 rows x 4 columns]

In [44]:

    

cat_model.query(cat_image)
cats[cats['id']==16289]['image'].show()


    

In [50]:

    

print dog_model.query(cat_image)
dogs[dogs['id'] == 16976]['image'].show()


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.196464    | 10.585ms     |
PROGRESS: | Done         |         | 100         | 62.67ms      |
PROGRESS: +--------------+---------+-------------+--------------+
+-------------+-----------------+---------------+------+
| query_label | reference_label |    distance   | rank |
+-------------+-----------------+---------------+------+
|      0      |      16976      | 37.4642628784 |  1   |
|      0      |      13387      | 37.5666832169 |  2   |
|      0      |      35867      | 37.6047267079 |  3   |
|      0      |      44603      | 37.7065585153 |  4   |
|      0      |       6094      | 38.5113254907 |  5   |
+-------------+-----------------+---------------+------+
[5 rows x 4 columns]







    

In [36]:

    

cat_model.query(cat_image)[0:5]['distance'].mean()


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.196464    | 16.485ms     |
PROGRESS: | Done         |         | 100         | 46.943ms     |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[36]:





36.15573070978294

In [37]:

    

dog_model.query(cat_image)[0:5]['distance'].mean()


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.196464    | 7.411ms      |
PROGRESS: | Done         |         | 100         | 72.725ms     |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[37]:





37.77071136184157

In [38]:

    

cat_model.query(cat_image)


    

    




PROGRESS: Starting pairwise querying.
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 0            | 1       | 0.196464    | 7.315ms      |
PROGRESS: | Done         |         | 100         | 56.16ms      |
PROGRESS: +--------------+---------+-------------+--------------+






    
Out[38]:





    

        
query_label
        
reference_label
        
distance
        
rank
    
    

        
0
        
16289
        
34.623719208
        
1
    
    

        
0
        
45646
        
36.0068799284
        
2
    
    

        
0
        
32139
        
36.5200813436
        
3
    
    

        
0
        
25713
        
36.7548502521
        
4
    
    

        
0
        
331
        
36.8731228168
        
5
    

[5 rows x 4 columns]

In [40]:

    

cats[cats['id']==16289]['image'].show()


    

In [53]:

    

image_test_dog = image_test[image_test['label'] == 'dog']
image_test_automobiles = image_test[image_test['label'] == 'automobile']
image_test_cat = image_test[image_test['label'] == 'cat']
image_test_bird = image_test[image_test['label'] == 'bird']


    

In [54]:

    

dog_cat_neighbors = cat_model.query(image_test_dog, k=1)


    

    




PROGRESS: Starting blockwise querying.
PROGRESS: max rows per data block: 7668
PROGRESS: number of reference data blocks: 8
PROGRESS: number of query data blocks: 1
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 1000         | 64000   | 12.5737     | 883.899ms    |
PROGRESS: | Done         | 509000  | 100         | 1.15s        |
PROGRESS: +--------------+---------+-------------+--------------+

In [59]:

    

dog_distances = graphlab.SFrame({'dog-dog': dog_model.query(image_test_dog, k=1)['distance'],
                                 'dog-cat': cat_model.query(image_test_dog, k=1)['distance'],
                                 'dog-car': car_model.query(image_test_dog, k=1)['distance'],
                                 'dog-bird': bird_model.query(image_test_dog, k=1)['distance']})


    

    




PROGRESS: Starting blockwise querying.
PROGRESS: max rows per data block: 7668
PROGRESS: number of reference data blocks: 8
PROGRESS: number of query data blocks: 1
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 1000         | 64000   | 12.5737     | 432.271ms    |
PROGRESS: | Done         | 509000  | 100         | 507.797ms    |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: Starting blockwise querying.
PROGRESS: max rows per data block: 7668
PROGRESS: number of reference data blocks: 8
PROGRESS: number of query data blocks: 1
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 1000         | 63000   | 12.3772     | 797.001ms    |
PROGRESS: | Done         | 509000  | 100         | 895.339ms    |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: Starting blockwise querying.
PROGRESS: max rows per data block: 7668
PROGRESS: number of reference data blocks: 8
PROGRESS: number of query data blocks: 1
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 1000         | 63000   | 12.3772     | 437.886ms    |
PROGRESS: | Done         | 509000  | 100         | 473.275ms    |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: Starting blockwise querying.
PROGRESS: max rows per data block: 7668
PROGRESS: number of reference data blocks: 8
PROGRESS: number of query data blocks: 1
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | Query points | # Pairs | % Complete. | Elapsed Time |
PROGRESS: +--------------+---------+-------------+--------------+
PROGRESS: | 1000         | 60000   | 12.5523     | 366.859ms    |
PROGRESS: | Done         | 478000  | 100         | 459.878ms    |
PROGRESS: +--------------+---------+-------------+--------------+

In [60]:

    

dog_distances


    

    
Out[60]:





    

        
dog-bird
        
dog-car
        
dog-cat
        
dog-dog
    
    

        
41.7538647304
        
41.9579761457
        
36.4196077068
        
33.4773590373
    
    

        
41.3382958925
        
46.0021331807
        
38.8353268874
        
32.8458495684
    
    

        
38.6157590853
        
42.9462290692
        
36.9763410854
        
35.0397073189
    
    

        
37.0892269954
        
41.6866060048
        
34.5750072914
        
33.9010327697
    
    

        
38.272288694
        
39.2269664935
        
34.778824791
        
37.4849250909
    
    

        
39.1462089236
        
40.5845117698
        
35.1171578292
        
34.945165344
    
    

        
40.523040106
        
45.1067352961
        
40.6095830913
        
39.0957278345
    
    

        
38.1947918393
        
41.3221140974
        
39.9036867306
        
37.7696131032
    
    

        
40.1567131661
        
41.8244654995
        
38.0674700168
        
35.1089144603
    
    

        
45.5597962603
        
45.4976929401
        
42.7258732951
        
43.2422832585
    

[1000 rows x 4 columns]
Note: Only the head of the SFrame is printed.
You can use print_rows(num_rows=m, num_columns=n) to print more rows and columns.

In [62]:

    

def is_dog_correct(row):
    if row['dog-dog'] < row['dog-cat'] and row['dog-dog'] < row['dog-car'] and row['dog-dog'] < row['dog-bird']:
        return 1
    else:
        return 0


    

In [67]:

    

is_dog_correct(dog_distances[5:6])


    

    
Out[67]:





1

In [69]:

    

dog_distances['classified_correct'] = dog_distances.apply(is_dog_correct)


    

In [75]:

    

dog_distances['classified_correct'].sum()/float(len(image_test_dog))


    

    
Out[75]:





0.678

In [ ]: