Update simple_videofacerec.py

xrange(max(labels)) would start count at 1, were as we want it to start at 0. So that len(list_of_labels) == len(subject_names)

If the subject detected was the last folder used for training, we hit an Key Error, on self.model.subject_name[prediction].

py/apps/videofacerec/simple_videofacerec.py

@@ -197,7 +197,7 @@ def run(self):
         print "Loading dataset..."
         [images, labels, subject_names] = read_images(options.dataset, image_size)
         # Zip us a {label, name} dict from the given data:
-        list_of_labels = list(xrange(max(labels)))
+        list_of_labels = set(labels)
         subject_dictionary = dict(zip(list_of_labels, subject_names))
         # Get the model we want to compute:
         model = get_model(image_size=image_size, subject_names=subject_dictionary)