Added CIFAR-10 data to data sets.

GPy/util/data_resources.json

@@ -57,6 +57,20 @@
             "http://www.cs.nyu.edu/~roweis/data/"
         ]
     },
+    "cifar-10": {
+        "citation": "Learning Multiple Layers of Features from Tiny Images, Alex Krizhevsky, 2009, Tech report available here: http://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf",
+        "details": "The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset. They were collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton. Details are available on this webpage: http://www.cs.toronto.edu/~kriz/cifar.html. The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.",
+        "files": [
+            [
+                "cifar-10-python.tar.gz"
+            ]
+        ],
+        "license": null,
+        "size": 0,
+        "urls": [
+            "http://www.cs.toronto.edu/~kriz/"
+        ]
+    },
     "cmu_mocap_full": {
         "citation": "Please include this in your acknowledgements: The data used in this project was obtained from mocap.cs.cmu.edu.\\nThe database was created with funding from NSF EIA-0196217.",
         "details": "CMU Motion Capture data base. Captured by a Vicon motion capture system consisting of 12 infrared MX-40 cameras, each of which is capable of recording at 120 Hz with images of 4 megapixel resolution. Motions are captured in a working volume of approximately 3m x 8m. The capture subject wears 41 markers and a stylish black garment.",

GPy/util/datasets.py

@@ -409,7 +409,7 @@ def lee_yeast_ChIP(data_set='lee_yeast_ChIP'):
     transcription_factors = [col for col in X.columns if col[:7] != 'Unnamed']    
     annotations = X[['Unnamed: 1', 'Unnamed: 2', 'Unnamed: 3']]
     X = X[transcription_factors]
-    return data_details_return({'annotations' : annotations, 'X' : X, 'transcription_factors', transcription_factors}, data_set)
+    return data_details_return({'annotations' : annotations, 'X' : X, 'transcription_factors': transcription_factors}, data_set)
     
 
 def fruitfly_tomancak(data_set='fruitfly_tomancak', gene_number=None):
@@ -1145,6 +1145,30 @@ def creep_data(data_set='creep_rupture'):
     X = all_data[:, features].copy()
     return data_details_return({'X': X, 'y': y}, data_set)
 
+def cifar10(data_set='cifar-10'):
+    """The Candian Institute for Advanced Research 10 image data set. Code for loading in this data is taken from this Boris Babenko's blog post, original code available here: http://bbabenko.tumblr.com/post/86756017649/learning-low-level-vision-feautres-in-10-lines-of-code"""
+    dirpath = os.path.join(data_path, data_set)
+    filename = os.path.join(dirpath, 'cifar-10-python.tar.gz')
+    if not data_available(data_set):
+        download_data(data_set)
+        import tarfile
+        # This code is from Boris Babenko's blog post.
+        # http://bbabenko.tumblr.com/post/86756017649/learning-low-level-vision-feautres-in-10-lines-of-code
+        tfile = tarfile.open(filename, 'r:gz')
+        tfile.extractall(dirpath)
+
+    with open(os.path.join(dirpath, 'cifar-10-batches-py','data_batch_1'),'rb') as f:
+        data = pickle.load(f)
+
+    images = data['data'].reshape((-1,3,32,32)).astype('float32')/255
+    images = np.rollaxis(images, 1, 4)
+    patches = np.zeros((0,5,5,3))
+    for x in range(0,32-5,5):
+        for y in range(0,32-5,5):
+            patches = np.concatenate((patches, images[:,x:x+5,y:y+5,:]), axis=0)
+    patches = patches.reshape((patches.shape[0],-1))    
+    return data_details_return({'Y': patches}, data_set)
+
 def cmu_mocap_49_balance(data_set='cmu_mocap'):
     """Load CMU subject 49's one legged balancing motion that was used by Alvarez, Luengo and Lawrence at AISTATS 2009."""
     train_motions = ['18', '19']