notebook.community

Edit and run 





In [1]:



    


import graphlab as gl

Load a commun image data analysis dataset





In [2]:



    


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



    


















    






[INFO] This non-commercial license of GraphLab Create is assigned to iliassweb@gmail.comand will expire on September 22, 2016. For commercial licensing options, visit https://dato.com/buy/.

[INFO] Start server at: ipc:///tmp/graphlab_server-4558 - Server binary: /home/zax/anaconda/lib/python2.7/site-packages/graphlab/unity_server - Server log: /tmp/graphlab_server_1446351785.log
[INFO] GraphLab Server Version: 1.6.1

Expolring the image data





In [3]:



    


gl.canvas.set_target('ipynb')



    











In [5]:



    


image_train['image'].show()

Train classifier on the raw image pixels Using logistic regression





In [7]:



    


raw_pixel_model = gl.logistic_classifier.create(image_train,
                                        target='label',
                                        features=['image_array'])



    


















    






PROGRESS: Creating a validation set from 5 percent of training data. This may take a while.
          You can set ``validation_set=None`` to disable validation tracking.

PROGRESS: Logistic regression:
PROGRESS: --------------------------------------------------------
PROGRESS: Number of examples          : 1900
PROGRESS: Number of classes           : 4
PROGRESS: Number of feature columns   : 1
PROGRESS: Number of unpacked features : 3072
PROGRESS: Number of coefficients    : 9219
PROGRESS: Starting L-BFGS
PROGRESS: --------------------------------------------------------
PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+
PROGRESS: | Iteration | Passes   | Step size | Elapsed Time | Training-accuracy | Validation-accuracy |
PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+
PROGRESS: | 1         | 6        | 0.000017  | 2.374218     | 0.357368          | 0.352381            |
PROGRESS: | 2         | 8        | 1.000000  | 3.355262     | 0.384737          | 0.438095            |
PROGRESS: | 3         | 9        | 1.000000  | 3.957353     | 0.430526          | 0.466667            |
PROGRESS: | 4         | 10       | 1.000000  | 4.560749     | 0.436842          | 0.523810            |
PROGRESS: | 5         | 11       | 1.000000  | 5.135515     | 0.445263          | 0.504762            |
PROGRESS: | 6         | 12       | 1.000000  | 5.740434     | 0.463684          | 0.533333            |
PROGRESS: | 10        | 16       | 1.000000  | 8.168517     | 0.505263          | 0.590476            |
PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+

Make a prediction with the simple model based on raw pixels





In [8]:



    


image_test[0:3]['image'].show()



    


















    



























In [10]:



    


image_test[0:3]['label']



    


















    
Out[10]:








dtype: str
Rows: 3
['cat', 'automobile', 'cat']

















In [11]:



    


raw_pixel_model.predict(image_test[0:3])



    


















    
Out[11]:








dtype: str
Rows: 3
['bird', 'cat', 'bird']

Evaluation raw pixel model on test data





In [12]:



    


raw_pixel_model.evaluate(image_test)



    


















    
Out[12]:








{'accuracy': 0.477, 'confusion_matrix': Columns:
 	target_label	str
 	predicted_label	str
 	count	int
 
 Rows: 16
 
 Data:
 +--------------+-----------------+-------+
 | target_label | predicted_label | count |
 +--------------+-----------------+-------+
 |     bird     |       dog       |  173  |
 |     dog      |       cat       |  238  |
 |     cat      |       cat       |  334  |
 |     bird     |    automobile   |  123  |
 |  automobile  |    automobile   |  616  |
 |     dog      |    automobile   |   97  |
 |     dog      |       dog       |  406  |
 |     cat      |       dog       |  287  |
 |  automobile  |       dog       |  105  |
 |  automobile  |       bird      |  121  |
 +--------------+-----------------+-------+
 [16 rows x 3 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.}

Can we improve the module using deep features





In [14]:



    


len(image_train)



    


















    
Out[14]:








2005

















In [27]:



    


deep_learning_model = gl.load_model('imagenet_model')
image_train['deep_features'] = deep_learning_model.extract_features(image_train)



    


















    






---------------------------------------------------------------------------
IOError                                   Traceback (most recent call last)
<ipython-input-27-31442fbefb7b> in <module>()
----> 1 deep_learning_model = gl.load_model('imagenet_model')
      2 image_train['deep_features'] = deep_learning_model.extract_features(image_train)

/home/zax/anaconda/lib/python2.7/site-packages/graphlab/toolkits/_model.pyc in load_model(location)
     61         else:
     62             # Not a ToolkitError so try unpickling the model.
---> 63             unpickler = gl_pickle.GLUnpickler(location)
     64 
     65             # Get the version

/home/zax/anaconda/lib/python2.7/site-packages/graphlab/_gl_pickle.pyc in __init__(self, filename)
    450         else:
    451             if not _os.path.exists(filename):
--> 452                 raise IOError('%s is not a valid file name.' % filename)
    453 
    454         # GLC 1.3 Pickle file

IOError: imagenet_model is not a valid file name.
















In [18]:



    


image_train.head()



    


















    
Out[18]:








    

        id
        image
        label
        deep_features
        image_array
    

    

        24
        Height: 32 Width: 32
        bird
        [0.242871761322,
1.09545373917, 0.0, ...		
        [73.0, 77.0, 58.0, 71.0,
68.0, 50.0, 77.0, 69.0, ...		
    

    

        33
        Height: 32 Width: 32
        cat
        [0.525087952614, 0.0,
0.0, 0.0, 0.0, 0.0, ...		
        [7.0, 5.0, 8.0, 7.0, 5.0,
8.0, 5.0, 4.0, 6.0, 7.0, ...		
    

    

        36
        Height: 32 Width: 32
        cat
        [0.566015958786, 0.0,
0.0, 0.0, 0.0, 0.0, ...		
        [169.0, 122.0, 65.0,
131.0, 108.0, 75.0, ...		
    

    

        70
        Height: 32 Width: 32
        dog
        [1.12979578972, 0.0, 0.0,
0.778194487095, 0.0, ...		
        [154.0, 179.0, 152.0,
159.0, 183.0, 157.0, ...		
    

    

        90
        Height: 32 Width: 32
        bird
        [1.71786928177, 0.0, 0.0,
0.0, 0.0, 0.0, ...		
        [216.0, 195.0, 180.0,
201.0, 178.0, 160.0, ...		
    

    

        97
        Height: 32 Width: 32
        automobile
        [1.57818555832, 0.0, 0.0,
0.0, 0.0, 0.0, ...		
        [33.0, 44.0, 27.0, 29.0,
44.0, 31.0, 32.0, 45.0, ...		
    

    

        107
        Height: 32 Width: 32
        dog
        [0.0, 0.0,
0.220677852631, 0.0,  ...		
        [97.0, 51.0, 31.0, 104.0,
58.0, 38.0, 107.0, 61.0, ...		
    

    

        121
        Height: 32 Width: 32
        bird
        [0.0, 0.23753464222, 0.0,
0.0, 0.0, 0.0, ...		
        [93.0, 96.0, 88.0, 102.0,
106.0, 97.0, 117.0, ...		
    

    

        136
        Height: 32 Width: 32
        automobile
        [0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 7.5737862587, 0.0, ...		
        [35.0, 59.0, 53.0, 36.0,
56.0, 56.0, 42.0, 62.0, ...		
    

    

        138
        Height: 32 Width: 32
        bird
        [0.658935725689, 0.0,
0.0, 0.0, 0.0, 0.0, ...		
        [205.0, 193.0, 195.0,
200.0, 187.0, 193.0, ...		
    



[10 rows x 5 columns]



















In [ ]:



    






    











In [20]:

Given the deep features, let's train a Classifer





In [21]:



    


deep_features_model = gl.logistic_classifier.create(image_train,
                                                    features=['deep_features'],
                                            target='label'
                                            )



    


















    






PROGRESS: Creating a validation set from 5 percent of training data. This may take a while.
          You can set ``validation_set=None`` to disable validation tracking.

PROGRESS: WARNING: Detected extremely low variance for feature(s) 'deep_features' because all entries are nearly the same.
Proceeding with model training using all features. If the model does not provide results of adequate quality, exclude the above mentioned feature(s) from the input dataset.
PROGRESS: Logistic regression:
PROGRESS: --------------------------------------------------------
PROGRESS: Number of examples          : 1900
PROGRESS: Number of classes           : 4
PROGRESS: Number of feature columns   : 1
PROGRESS: Number of unpacked features : 4096
PROGRESS: Number of coefficients    : 12291
PROGRESS: Starting L-BFGS
PROGRESS: --------------------------------------------------------
PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+
PROGRESS: | Iteration | Passes   | Step size | Elapsed Time | Training-accuracy | Validation-accuracy |
PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+
PROGRESS: | 1         | 5        | 0.000132  | 3.875283     | 0.726842          | 0.771429            |
PROGRESS: | 2         | 9        | 0.250000  | 7.273369     | 0.761053          | 0.771429            |
PROGRESS: | 3         | 10       | 0.250000  | 8.388568     | 0.766316          | 0.790476            |
PROGRESS: | 4         | 11       | 0.250000  | 9.457524     | 0.769474          | 0.790476            |
PROGRESS: | 5         | 12       | 0.250000  | 10.530868    | 0.779474          | 0.800000            |
PROGRESS: | 6         | 13       | 0.250000  | 11.635419    | 0.789474          | 0.819048            |
PROGRESS: | 7         | 14       | 0.250000  | 12.648735    | 0.805263          | 0.819048            |
PROGRESS: | 8         | 15       | 0.250000  | 13.667129    | 0.836316          | 0.828571            |
PROGRESS: | 9         | 16       | 0.250000  | 14.733561    | 0.842632          | 0.809524            |
PROGRESS: | 10        | 17       | 0.250000  | 15.810148    | 0.852632          | 0.800000            |
PROGRESS: +-----------+----------+-----------+--------------+-------------------+---------------------+

Aply the deep features model





In [22]:



    


image_test[0:3]['image'].show()



    


















    



























In [24]:



    


image_test[0:3]['label']



    


















    
Out[24]:








dtype: str
Rows: 3
['cat', 'automobile', 'cat']

















In [25]:



    


deep_features_model.predict(image_test[0:3])



    


















    
Out[25]:








dtype: str
Rows: 3
['cat', 'automobile', 'cat']

Compute test_data accuracy of deep_features_model





In [26]:



    


deep_features_model.evaluate(image_test)



    


















    
Out[26]:








{'accuracy': 0.7855, 'confusion_matrix': Columns:
 	target_label	str
 	predicted_label	str
 	count	int
 
 Rows: 16
 
 Data:
 +--------------+-----------------+-------+
 | target_label | predicted_label | count |
 +--------------+-----------------+-------+
 |     dog      |    automobile   |   20  |
 |     bird     |       bird      |  783  |
 |  automobile  |       bird      |   24  |
 |     dog      |       bird      |   45  |
 |     cat      |    automobile   |   45  |
 |     cat      |       cat       |  668  |
 |     bird     |       cat       |  120  |
 |     cat      |       dog       |  214  |
 |     dog      |       dog       |  731  |
 |  automobile  |    automobile   |  960  |
 +--------------+-----------------+-------+
 [16 rows x 3 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 [ ]:

Content source: ledrui/Deep-features-for-image-classification

Similar notebooks:

notebook.community | gallery | about