def load()

in eval_retrieval.py [0:0]

• 35 lines of code
• 18 McCabe index (conditional complexity)

    def load(self):
        # Load the dataset GT
        self.lab_root = '{0}/lab/'.format(self.path)
        self.img_root = '{0}/jpg/'.format(self.path)
        lab_filenames = np.sort(os.listdir(self.lab_root))
        # Get the filenames without the extension
        self.img_filenames = [e[:-4] for e in np.sort(os.listdir(self.img_root))
                              if e[:-4] not in self.blacklisted]

        # Parse the label files. Some challenges as filenames do not correspond
        # exactly to query names. Go through all the labels to:
        # i) map names to filenames and vice versa
        # ii) get the relevant regions of interest of the queries,
        # iii) get the indexes of the dataset images that are queries
        # iv) get the relevants / non-relevants list
        self.relevants = {}
        self.junk = {}
        self.non_relevants = {}

        self.filename_to_name = {}
        self.name_to_filename = OrderedDict()
        self.q_roi = {}
        for e in lab_filenames:
            if e.endswith('_query.txt'):
                q_name = e[:-len('_query.txt')]
                q_data = open("{0}/{1}".format(self.lab_root, e)).readline().split(" ")
                q_filename = q_data[0][5:] if q_data[0].startswith('oxc1_') else q_data[0]
                self.filename_to_name[q_filename] = q_name
                self.name_to_filename[q_name] = q_filename
                good = set([e.strip() for e in open("{0}/{1}_ok.txt".format(self.lab_root, q_name))])
                good = good.union(set([e.strip() for e in open("{0}/{1}_good.txt".format(self.lab_root, q_name))]))
                junk = set([e.strip() for e in open("{0}/{1}_junk.txt".format(self.lab_root, q_name))])
                good_plus_junk = good.union(junk)
                self.relevants[q_name] = [i for i in range(len(self.img_filenames))
                                          if self.img_filenames[i] in good]
                self.junk[q_name] = [i for i in range(len(self.img_filenames))
                                     if self.img_filenames[i] in junk]
                self.non_relevants[q_name] = [i for i in range(len(self.img_filenames))
                                              if self.img_filenames[i] not in good_plus_junk]
                self.q_roi[q_name] = np.array([float(q) for q in q_data[1:]], dtype=np.float32)
                #np.array(map(float, q_data[1:]), dtype=np.float32)

        self.q_names = self.name_to_filename.keys()
        self.q_index = np.array([self.img_filenames.index(self.name_to_filename[qn])
                                 for qn in self.q_names])
        self.N_images = len(self.img_filenames)
        self.N_queries = len(self.q_index)