Python datasets 模块，imagenet() 实例源码

def _load_imagenet_annotation(self, index):
        """
        Load image and bounding boxes info from txt files of imagenet.
        """
        filename = os.path.join(self._data_path, 'Annotations', self._image_set, index + '.xml')

        # print 'Loading: {}'.format(filename)
        def get_data_from_tag(node, tag):
            return node.getElementsByTagName(tag)[0].childNodes[0].data

        with open(filename) as f:
            data = minidom.parseString(f.read())

        objs = data.getElementsByTagName('object')
        num_objs = len(objs)

        boxes = np.zeros((num_objs, 4), dtype=np.uint16)
        gt_classes = np.zeros((num_objs), dtype=np.int32)
        overlaps = np.zeros((num_objs, self.num_classes), dtype=np.float32)

        # Load object bounding boxes into a data frame.
        for ix, obj in enumerate(objs):
            x1 = float(get_data_from_tag(obj, 'xmin'))
            y1 = float(get_data_from_tag(obj, 'ymin'))
            x2 = float(get_data_from_tag(obj, 'xmax'))
            y2 = float(get_data_from_tag(obj, 'ymax'))
            cls = self._wnid_to_ind[
                    str(get_data_from_tag(obj, "name")).lower().strip()]
            boxes[ix, :] = [x1, y1, x2, y2]
            gt_classes[ix] = cls
            overlaps[ix, cls] = 1.0

        overlaps = scipy.sparse.csr_matrix(overlaps)

        return {'boxes' : boxes,
                'gt_classes': gt_classes,
                'gt_overlaps' : overlaps,
                'flipped' : False}